ux case study reviews

Get a free custom homepage design for your new website.

Design, UI, UX , Inspiration

15 excellent ux case studies every creative should read.

• By Sandra Boicheva
• October 21st, 2021

In a previous article, we talked about UX portfolios and how they carefully craft a story of how designers work. Interestingly enough, recruiters decide if a UX freelance designer or an agency is a good match within 5 minutes into the portfolio . In order to persuade these recruiters, the portfolio needs to present an appealing story that showcases the skill, the thought process, and the choices taken for key parts of the designs. With this in mind, today we’ll talk about UX case studies and give 15 excellent examples of case studies with compelling stories.

The Storytelling Approach in UX Case Studies

An essential part of the portfolio of a UX designer is the case studies that pack a showcase of the designer’s skills, way of thinking, insights in the form of compelling stories. These case studies are often the selling point as recruiters look for freelancers and agencies who can communicate their ideas through design and explain themselves in a clear and appealing way. So how does this work?

Photography by Alvaro Reyes

Just like with every other story, UX case studies also start with an introduction, have a middle, and end with a conclusion .

• Introduction: This UX case study example starts with a design brief and presents the main challenges and requirements. In short, the UX designer presents the problem, their solution, and their role.
• Middle: The actual story of the case study example explains the design process and the techniques used. This usually starts with obstacles, design thinking, research, and unexpected challenges. All these elements lead to the best part of the story: the action part. It is where the story unveils the designer’s insights, ideas, choices, testing, and decisions.
• Conclusion: The final reveal shows the results and gives space for reflection where the designer explains what they’ve learned, and what they’ve achieved.

Now as we gave you the introduction, let’s get to the main storyline and enjoy 15 UX case studies that tell a compelling story.

1. Car Dealer Website for Mercedes-Benz Ukraine by Fulcrum

This case study is a pure pleasure to read. It’s well-structured, easy to read, and still features all the relevant information one needs to understand the project. As the previous client’s website was based on the official Mercedes Benz template, Fulcrum had to develop an appealing and functional website that would require less time to maintain, be more user-friendly, and increase user trust.

• Intro: Starts with a summary of the task.
• Problem: Lists the reasons why the website needs a redesign.
• Project Goals: Lists the 4 main goals with quick summaries.
• Project: Showcases different elements of the website with desktop and mobile comparison.
• Functionality: Explains how the website functionality helps clients to find, and order spare parts within minutes.
• Admin Panel: Lists how the new admin panel helps the client customize without external help.
• Elements: Grid, fonts, colors.
• Tech Stack: Shows the tools used for the backend, mobile, admin panel, and cloud.
• Client review: The case study ends with a 5-star review by the marketing director of Mercedes Benz Ukraine, Olga Belova.

This case study is an example of a detailed but easy to scan and read story from top to bottom, featuring all relevant information and ending on the highest note: the client’s review.

Advertisement

2. Galaxy Z Flips 5G Website by DFY

This is a big project that covers every aspect of the website, including the UX strategy. The creative studio aimed to fully illustrate and demonstrate the significant upgrades over previous models and to enable two-way communication with the customers through an interactive experience.

• Intro: Summary of the project and roles.
• Interactive Experience: The main project goal.
• Demonstration: Explains the decision to feature 360-degree views and hands-on videos instead of technical terms.
• Screens: Includes high-quality screenshots of significant pages and features.
• Ecosystem: Highlight a page with easy navigation across different products as a marketing decision that makes cross-selling seamless.
• Essentials: Showcases a slider of all products with key features that provide ample information.
• Showroom: Interactive experience that helps the user “play around” with the product.
• Credits: As a conclusion, DFY features the stakeholders involved.

A strong presentation of a very ambitious project. It keeps the case study visual while still providing enough insight into the thought process and the most important decisions.

3. Jambb Social Platform by Finna Wang

Here we have a beautiful case study for a platform that aims to help creators grow their communities by recognizing and rewarding their base of supporters. It tackles a curious problem that 99% of fans who contribute in non-monetary ways don’t get the same content, access, and recognition they deserve. This means the creators need a way to identify their fans across all social platforms to grow their business and give recognition. To get a clear picture of what the design has to accomplish, Finna Wang conducted stakeholder interviews with the majority of the client’s team.

• Intro: Listing roles, dates, team, and used tools.
• Project Overview: The main concept and the reasons behind it.
• Exploration: What problem will the platform solve, preliminary research, and conclusions from the research.  The section includes the project scope and problem statement.
• Design Process: A thorough explanation of the discoveries and the exact steps.
• User Flows:  3 user flows based on common tasks that the target user/fan would do on the site.
• Design Studio: Visualization process with wireframes, sitemap, prototypes.
• Design Iterations: The designer highlights the iterations they were primary behind.
• Style Guide: Typography, colors, visual elements breakdown.
• Usability Testing: Beta site vs Figma prototype; usertesting.com, revised problem statement.
• Prototype: Features an accessible high fidelity prototype in Figma you can view.
• Takeaways: Conclusions.

An extremely detailed professionally made and well-structured UX case study. It goes a step further by listing specific conclusions from the conducted research and featuring an accessible Figma prototype.

4. Memento Media by Masha Keyhani

This case study is dedicated to a very interesting project for saving family stories. It aims to help users capture and record memories from their past. To do so, the design team performed user research and competitive analysis. The entire project took a 6-week sprint.

• Overview: Introducing the client and the purpose of the app.
• My Role: Explaining the roles of the designer and their team.
• Design Process: A brief introduction of the design process and the design toolkit
• Home: The purpose of the Homepage and the thought process behind it.
• Question Selection: The decision behind this screen.
• Recording Process: Building the recording feature and the decisions behind it.
• User research: a thorough guide with the main focuses, strategies, and competitor analysts, including interviews.
• Research Objectives: The designer gives the intent of their research, the demographics, synthesis, and usability testing insights.
• Propositions: Challenges and solutions
• User Flow: Altering the user flow based on testing and feedback.
• Wireframes: Sketches, Lo-Fi wireframing.
• Design System: Typography, colors, iconography, design elements.
• The Prototype: It shows a preview of the final screens.

This UX study case is very valuable for the insights it presents. The design features a detailed explanation of the thinking process, the research phase, analysts, and testing which could help other creatives take some good advice from it for their future research.

5. Perfect Recipes App by Tubik

Here we have a UX case study for designing a simple mobile app for cooking, recipes, and food shopping. It aims to step away from traditional recipe apps by creating something more universal for users who love cooking with extended functionality. The best idea behind it is finding recipes based on what supplies the user currently has at home.

• Intro: Introducing the concept and the team behind it.
•  Project: What they wanted to make and what features would make the app different than the competitors.
• UI design: The decisions behind the design.
• Personalization: Explaining how the app gives the user room for personalization and customizing the features according to their personal preferences.
• Recipe Cards and Engaging Photos: The decisions behind the visuals.
• Cook Now feature: Explaining the feature.
• Shopping List: Explaining the feature.
• Pantry feature:  The idea to sync up the app with AmazonGo services. This case study section features a video.
• Bottom Line: What the team learned.

This UX case study is a good example of how to present your concept if you have your own idea for an app. You could also check the interactive preview of the app here .

6. SAM App by Mike Wilson

The client is the Seattle Art Museum while the challenge is to provide engaging multimedia content for users as well as self-guided tours. Mile Wilson has to create an experience that will encourage repeat visits and increase events and exhibition attendance.

• Intro: Listing time for the project, team members, and roles.
• The Client: A brief introduction of Seattle Art Museum
• The Challenge: What the app needs to accomplish.
• Research and Planning: Explaining the process for gathering insights, distributing surveys, interviews, and identifying specific ways to streamline the museum experience.
• Sloane: Creating the primary persona. This includes age, bio, goals, skills, and frustrations.
• Designing the Solution: Here the case study features the results of their research, information architecture, user flows, early sketching, paper prototypes, and wireframes.
• Conclusion: Explaining the outcome, what the team would have done differently, what’s next, and the key takeaways.

What we can take as a valuable insight aside from the detailed research analysis, is the structure of the conclusion. Usually, most case studies give the outcome and preview screens. However, here we have a showcase of what the designer has learned from the project, what they would do differently, and how they can improve from the experience.

7. Elmenus Case Study

This is a case study by UX designers Marwa Kamaleldin, Mario Maged, Nehal Nehad, and Abanoub Yacoub for redesigning a platform with over 6K restaurants. It aims to help users on the territory of Egypt to find delivery and dine-out restaurants.

• Overview: What is the platform, why the platform is getting redesigned, what is the target audience. This section also includes the 6 steps of the team’s design process.
• User Journey Map: A scheme of user scenarios and expectations with all phases and actions.
• Heuristic Evaluation: Principles, issues, recommendations, and severity of the issues of the old design.
• First Usability Testing: Goals, audience, and tasks with new user scenarios and actions based on the heuristic evaluation. It features a smaller section that lists the most severe issues from usability for the old design.
• Business Strategy: A comprehensive scheme that links problems, objectives, customer segment, measurements of success, and KPIs.
• Solutions: Ideas to solve all 4 issues.
• Wireframes: 4 directions of wireframes.
• Styleguide: Colors, fonts, typeface, components, iconography, spacing method.
• Design: Screens of the different screens and interactions.
• Second Usability Testing: Updated personas, scenarios, and goals. The section also features before-and-after screenshots.
• Outcome: Did the team solve the problem or not.

A highly visual and perfectly structured plan and process for redesigning a website. The case study shows how the team discovers the issues with the old design and what decisions they made to fix these issues.

8. LinkedIn Recruiter Tool by Evelynma

A fresh weekend project exploring the recruiting space of LinkedIn to find a way to help make it easier for recruiters to connect with ideal candidates.

• Background Info: What made the designer do the project.
• Problem and Solution: A good analysis of the problem followed by the designer’s solution.
• Process: This section includes an analysis of interviewing 7 passive candidates, 1 active candidate, 3 recruiters, and 1 hiring manager. The designer also includes their journey map of the recruiting experience, a sketch of creating personas, and the final 3 personas.
• Storyboard and User Flow Diagrams: The winning scenario for Laura’s persona and user flow diagram.
• Sketches and Paper Prototypes: Sticky notes for paper prototypes for the mobile experience.
• Visual Design: Web and mobile final design following the original LinkedIn pattern.
• Outcome: Explaining the opportunity.

This is an excellent UX case study when it comes to personal UX design projects. creating a solution to a client’s problem aside, personal project concepts is definitely something future recruiters would love to see as it showcases the creativity of the designers even further.

9. Turbofan Engine Diagnostics by Havana Nguyen

The UX designer and their team had to redesign some legacy diagnostics software to modernize the software, facilitate data transfers from new hardware, and improve usability. They built the desktop and mobile app for iOS and Android.

• Problem: The case study explain the main problem and what the team had to do to solve it.
• My Role: As a lead UX designer on a complicated 18-month project, Havana Nguyen had a lot of work to do, summarized in a list of 5 main tasks.
• Unique Challenges: This section includes 4 main challenges that made the project so complex. ( Btw, there’s a photo of sketched wireframes literally written on the wall.)
• My Process: The section includes a description of the UX design process highlighted into 5 comprehensive points.
• Final Thoughts: What the designer has learned for 18 months.

The most impressive thing about this case study is that it manages to summarize and explain well an extremely complex project. There are no prototypes and app screens since it’s an exclusive app for the clients to use.

10. Databox by FireArt

A very interesting project for Firearts’s team to solve the real AL & ML challenges across a variety of different industries. The Databox project is about building scalable data pipeline infrastructure & deploy machine learning and artificial intelligence models.

• Overview: The introduction of the case study narrows down the project goal, the great challenge ahead, and the solution.
• How We Start: The necessary phases of the design process to get an understanding of a product.
• User Flow: The entire scheme from the entry point through a set of steps towards the final action of the product.
• Wireframes: A small selection of wireframe previews after testing different scenarios.
• Styleguide: Typography, colors, components.
• Visual Design: Screenshots in light and dark mode.

A short visual case study that summarizes the huge amount of work into a few sections.

11. Travel and Training by Nikitin Team

Here’s another short and sweet case study for an app with a complete and up-to-date directory of fitness organizations in detailed maps of world cities.

• Overview: Explaining the project.
• Map Screen : Outlining the search feature by categories.
• Profiles: Profile customization section.
• Fitness Clubs: Explaining the feature.
• Icons: A preview of the icons for the app.
• App in Action: A video of the user experience.

This case study has fewer sections, however, it’s very easy to read and comprehend.

12. Carna by Ozmo

Ozmo provides a highly visual case study for a mobile application and passing various complexities of courses. The main goal for the UX designer is to develop a design and recognizable visual corporate identity with elaborate illustrations.

• Intro: A visual project preview with a brief description of the goal and role.
• Identity: Colors, fonts, and logo.
• Wireframes: The thinking process.
• Interactions: Showcase of the main interactions with animated visuals.
• Conclusion: Preview of the final screens.

The case study is short and highly visual, easy to scan and comprehend. Even without enough insight and text copy, we can clearly understand the thought process behind and what the designer was working to accomplish.

13. An Approach to Digitization in Education by Moritz Oesterlau

This case study is for an online platform for challenge-based learning. The designer’s role was to create an entire product design from research to conception, visualization, and testing. It’s a very in-depth UX case study extremely valuable for creatives in terms of how to structure the works in their portfolio.

• Intro: Introducing the client, project time, sector, and the designer’s role.
• Competitive Analysis: the case study starts off with the process of creating competitive profiles. It explains the opportunities and challenges of e-learning that were taken into consideration.
• Interviews and Surveys: Listing the goals of these surveys as well as the valuable insights they found.
• Building Empathy: The process and defining the three target profiles and how will the project cater to their needs. This section includes a PDF of the user personas.
• Structure of the Course Curriculum: Again with the attached PDF files, you can see the schemes of the task model and customer experience map.
• Information Architecture: The defined and evaluated sitemap for TINIA
• Wireframing, Prototyping, and Usability Testing :  An exploration of the work process with paper and clickable prototypes.
• Visual Design: Styleguide preview and detailed PDF.
• A/B and Click Tests: Reviewing the usability assumptions.
• Conclusion: A detailed reflection about the importance of the project, what the designer learned, and what the outcome was.

This is a very important case study and there’s a lot to take from it. First, the project was too ambitious and the goal was too big and vague. Although the result is rather an approximation and, above all, at the conceptual level requires further work, the case study is incredibly insightful, informative, and insightful.

14. In-class Review Game by Elizabeth Lin

This project was never realized but the case study remains and it’s worth checking out. Elizabeth Lin takes on how to create an engaging in-class review game with a lot of research, brainstorming, and a well-structured detailed process.

• Intro: What makes the project special.
• Research: Explaining how they approached the research and what they’ve learned.
• Brainstorming: the process and narrowing all How Might We questions to one final question: How might we create an engaging in-class math review game.
• Game Loop and Storyboarding: Sketch of the core game loop and the general flow of the game.
• Prototyping: Outlining basic game mechanics and rounds in detail.
• Future Explorations: The case study goes further with explorations showing how the product could look if we expanded upon the idea even further.
• What Happened?:  The outcome of the project.

This case study tells the story of the project in detail and expands on it with great ideas for future development.

15. Virtual Makeup Studio by Zara Dei

And for our last example, this is a case study that tells the story of an app-free shippable makeover experience integrated with the Covergirl website. The team has to find a way to improve conversion by supporting customers in their purchase decisions as well as to increase basket size by encouraging them to buy complementary products.

• Intro: Introducing the project and the main challenges.
• Discovery and Research: Using existing product information on the website to improve the experience.
• Onboarding and Perceived Performance: Avoiding compatibility issues and the barrier of a user having to download an app. The section explains the ideas for features that will keep users engaged, such as a camera with face scan animation.
• Fallback Experience and Error States: Providing clear error messaging along with troubleshooting instructions.
• Interactions: explaining the main interactions and the decisions behind them.
• Shared Design Language: Explaining the decision to provide links on each product page so users could be directed to their preferred retailer to place their order. Including recommended products to provide users with alternatives.
• Outcome and Learning: The good ending.
• Project Information: Listing all stakeholders, the UX designer’s role in a bullet list, and design tools.

In Conclusion

These were the 15 UX case studies we wanted to share with you as they all tell their story differently. If we can take something valuable about what are the best practices for making an outstanding case study, it will be something like this.

Just like with literature, storytelling isn’t a blueprint: you can write short stories, long in-depth analyses, or create a visual novel to show your story rather than tell. The detailed in-depth UX case studies with lots of insights aren’t superior to the shorter visual ones or vice versa. What’s important is for a case study to give a comprehensive view of the process, challenges, decisions, and design thinking behind the completed project .

In conclusion, a UX case study should always include a summary; the challenges; the personas; roles and responsibilities; the process; as well as the outcomes, and lessons learned.

Video Recap

Take a look at the special video we’ve made to visualize and discuss the most interesting and creative ideas implemented in the case studies.

In the meantime, why not browse through some more related insights on web development and web design?

• The 30 Best UX Books Every Creative Should Read in 2022
• Great UI Animation Examples to Make Your Jaw Drop [+Tips and Freebies]
• 60 Superb App Design Inspiration Examples

Popular Posts

• 20 UI/UX Design Trends that will Rock 2023 [Updated]
• Best 15 UI Color Palette & Scheme Generators for the Perfect Interface Design
• 10 Golden UI Design Principles and How To Use Them
• GET A QUICK QUOTE

Subscribe for our newsletter

We hate boring. Our newsletters are relevant and on point.  Excited? Let’s do this!

11 Inspiring UX Case Studies That Every Designer Should Study

A UX case study is a sort of detailed overview of a designer's work. They are often part of a UX designer's portfolio and showcase the designer's skill in managing tasks and problems. From a recruiter's perspective, such a UX portfolio shows the skill, insights, knowledge, and talent of the designer.

Therefore, UX case studies play an important role in the recruitment and demand for designers.

What Makes a Powerful Case Study

Building a UX case study includes showing the design process through compelling stories. They will use plain language to demonstrate how they handled key design issues, offering a comprehensive view of their process. Well done case studies often include:

• A  problem statement and solutions with real applications.
• Relevant numbers, data, or testimonials to demonstrate the work and efforts.
• A story that directly connects the problem to the solution.

Any competent UX professional will know that creating a stunning UX case study is about the little details.

11 Best UX Case Studies for Designers

The best way to understand what a good case study looks like is to go over other examples. Each of these UX case study examples shows a designer's insights, basic skills, and other designers' lessons learned through their experience.

1. Promo.com web editor

For this video-creation platform , UX designer Sascha was brought on to revamp v2.0, adding new features that could work alongside the existing UX design. The point was to work on interface details that would help create a user friendly platform, and that users could find simple enough to use.

User personas mapped by the UX designer revealed the most common confusion to be the process of inserting particular features into the video, such as subtitles. The designer's goal, therefore, was to create a platform with improved editor controls.

The designer then used a common text-editor layout to include top and side navigation bars that made it easy to access and implement text editing.

Key Learnings from Promo.com

This case study focuses on addressing a particular problem that customers were currently facing. Its main theme is to show a problem, and how the product designer addressed this problem. Its strength points include:

• clearly highlighting the problem (i.e. inaccessible and limited video-text editor options)
• conduction research to understand the nature of the problem and the kind of solutions customers want
• implementing research insights into the redesign to create a platform that actively served customer needs

2. Productivity tracker app

The main concept behind this UX case study is to address a pre-existing problem through the design of the app. Immediately from the start, the study highlights a common pain point among users: that of a lack of productivity due to device usage.

This UX case study example addressed some of the main problems within existing productivity apps included:a poor UI and UX that made navigation difficult

• a poorly-built information architecture
• limited functions on the mobile application

Key Learnings from the Productivity app case study

The case study highlights the simple design process that was then used to build the app. Wireframes were created, a moldboard developed, and finally, individual pages of the app were designed in line with the initial goals.

3. Postmates Unlimited

This case study clearly identifies the improvements made to the Postmates app in a simple overview before jumping into greater detail. The redesign goal, which it achieved, was to improve the experience and other interface details of the app.

The problems identified included:

• usability that led to high support ticket volume.
• technical app infrastructure issues that prevented scalability.
• lack of efficient product management, such as batching orders.

A UX research course can help understand the kind of research needed for a case study. The app redesign involved bringing couriers in and running usability testing on improvements. The final model, therefore, had input from real users on what worked and what caused issues.

Key Learnings from Postmates

The Postmates redesign works as a great UX case study for the simple way it approaches problem-solving. Following an overview of the work, it addresses the problems faced by users of the app. It then establishes research processes and highlights how changes were made to reduce these issues.

4. TV Guide

Addressing the fragmentation of content across channels, this case study sought to redesign how people consume media. The key problems identified included:

• the overabundance of content across various TV and streaming platforms
• the difficulty in discovering and managing content across all platforms

To deliver on the key goals of content personalization, smart recommendations, and offering cross-platform content search, the design process included conducting interviews, surveys, and checking customer reviews.

The design of TV Guide enables users to get custom recommendations sourced from friends' and family's watchlists.

Key Learnings from TV Guide

Like previous UX design case studies, this one tackled the issue head-on. Describing the research process, it goes into detail regarding the approach used by the UX designers to create the app. It takes readers on a journey, from identifying pain points, to testing solutions, and implementing the final version.

5. The FlexBox Inspector

Designer Victoria discusses how she developed the investigator tool for the Mozilla Firefox browser. Surveys into understanding the problems with the existing CSS Flexbox tool revealed a need for a user-friendly design. Interviews with a senior designer and other designers helped developers understand the features design-focused tools ought to have. A feature analysis revealed what most users look for in such tools.

The final result of the development process was a design that incorporated several new features, including:

• a new layout
• color-coded design
• multiple entry points to make workflow management efficient

Key Learnings from the Flexbox

This UX design case study starts with a clear goal, then addresses multiple user needs. It clearly defines the design process behind each feature developed by the time, and the reasoning for including that feature. To give a complete picture, it also discusses why certain features or processes were excluded.

6. The Current State of Checkouts

This Baymard UX design case study looks into the checkout process in over 70 e-commerce websites. Through competitive analysis, it isolates problem points in the UX design, which, if addressed, could improve the customer's checkout process.

The study found at least 31 common issues that were easily preventable. The study was designed and conducted on a large scale, over 12 years, to incorporate changing design patterns into the review.

Recommendations based on findings include:

• prominent guest checkout option
• simple password requirements
• specific delivery period
• price comparison tool for shipping vs store pickup

Key Learnings from Checkout Case Study

Each identified issue is backed up by data and research to highlight its importance. Further research backs up each recommendation made within the case study, with usability testing to support the idea. As far as UX case studies go, this one provides practical insight into an existing, widely used e-commerce feature, and offers practical solutions.

7. New York Times App

Using a creative illustration website, the designers proposed a landing page feature "Timely" that could counter the problems faced by the NYT app . Its major issues included too much irrelevant content, low usage, and undesirable coverage of content.

The goal behind Timely was to improve user incentives, build long-term loyalty, and encourage reading. Design mapping for the app covered:

• identifying the problem
• understanding audience needs
• creating wireframes
• designing and prototyping

The end result was an app that could help readers get notifications regarding news of interest at convenient moments (at breakfast, before bed). This encouraged interaction and improved readability with short-form articles.

Key Learnings from NYT App

The UX case study proposes a problem solution that works with an existing information architecture, instead adding custom graphics to the mobile app. It leads from a simple problem statement to discuss the project that could address these issues without changing was customers already loved.

UX case studies focused on redesign include the FitBit redesign, which started off by understanding personas and what users expect from a fitness tracker. Developing use cases and personas, Guerilla usability testing was employed to assess pain points.

These pain points were then ranked based on their importance to users and to app performance. They were addressed through:

• Highlighting essential parts and features of the app
• Changing easily missed icons to more recognizable icons
• relabelling tracking options to guide users better to its usage

Key Learnings from Fitbit

While the case study maps user experiences and offers solutions, it does not begin with an intensive research-based approach. The prototype is successful in testing, but problem factors are not identified with research-based statistics, meaning key factors could have been ignored.

9. Rating System UX

The designer behind the rating system UX redesign sought to solve issues with the 5-star rating system. Highlighted issues included:

• the lack of subjective accuracy of a 5-point rating system
• the issue of calculating the average of a zero-star rating
• average ratings are misleading

Better alternatives include:

• 5-star emoticon rating that relates the user experience
• Like/dislike buttons that make approval/disapproval simple

The final design incorporated both these styles to make full use of the rating system.

Key Learnings from Rating System UX

The UX case study stemmed from insight into the limitations of the existing rating system. The new design addressed old issues and incorporated better efficiencies.

The Intuit redesign was focused on making content readable, more engaging, and accessible. Looking into product personalization, the content was found to be lacking aesthetic value, as well as being hard to find. The goal was to create content that was easy to find, clear, and consistent.

The implemented solutions included:

• increased readability with increased body text and header spacing
• table of contents on the sidebar for easier navigation
• visible and prominent search bar
• illustrations and designs for pretty visuals

Key Learnings from Intuit

The Intuit case study approaches the problem from a practical point of view. It begins with isolating problems with the interface, in particular with the content. This is an example of a case study that breaks down problems into broader categories, and solves each problem with a practical solution.

This UX case study about a social platform tackles a commonly-faced problem from existing platforms. It addresses the issue of recognizing non-monetary user engagement, to help creators identify their user base.

The case study addresses the problem statement and establishes the design process (building wireframes and prototypes) as well as conducting user testing. The final result is to develop "Discover" pages, engaging layouts, and animated interactions to increase usability.

Key Learnings from Jambb

The study goes into detail regarding problem identification, then moves on to propose solutions that take into account the perspective of all stakeholders involved. It then explains why each design decision was made, and proves its efficacy through testing and prototyping.

Key Takeaways

Developing good UX case studies examples is as much about the details you include as the ones you leave out. Going over UX courses can give you a better understanding of what your case study should look like. A good case study should provide an overview of the problem, include numbers and statistics, and offer practical solutions that directly address the problem. The above-discussed UX case studies provide a good example of the dos and don'ts of a well-structured UX design case study that should be part of every UX portfolio .

Additional Resources

Check out these resources to learn more about UX case studies:

8 UX Case Studies to Read

UX Design Case Study

Frequently Asked Questions

Upskill your design team effectively.

Equip your design team with the best-in-class design training that sticks.

Do you know your design team skill level? Send them this quick test & see where their skills stand among 300K+ designers worldwide.

Level up your design career

Get step-by-step guide how to build or advance your UX design career.

Do you know your design skills level? Take a quick test & see where you stand among 300K+ designers worldwide.

Continue reading

The impact of ux design on application success: exploring costs and trends, 7 top ux careers & specialisations: skills, paths & opportunities, 15 figma plugins to boost your design workflow, cookie settings 🍪.

• Interactive UX learning for all levels
• 20+ UX courses and career paths
• Personalized learning & practice

Design-first companies are training their design teams. Are you?

• Measure & identify team skill gaps
• Tailor learning for your team’s needs
• Unlock extensive learning library
• Visualize team growth over time
• Retain your designers

A rapid desktop prototyping tool

Mockplus - Design Faster. Collaborate Better.

Prototype, design, collaborate, and design systems all in Mockplus

Top 22 Stunning UX Case Studies You Should Know in 2022

An immersive yet well-structured UX case study helps UX professionals show off their design talents in portfolio websites, and let them communicate better with employers, designers and others easily.

However, as a UX designer , how can you write a perfect UX case study to easily get hired or communicate with others better?

Mockplus has handpicked 22 of the best UX design case study examples in 2022 to help you get inspiration, improve your portfolios and make your own things with ease. A step-by-step guideline about how to create a UX case study is also followed.

What is a UX case study?

A UX case study tells the story of how you create a great website or app and, in particular, what you do to improve the UX of the site. UX designers—newbies and experts alike—will often share a case study on a portfolio website as a great way to get hired. Just like sending a resumé. 

So, it is a lot more than just a copy of everything you've done while designing the project. To really showcase your design talent and the breadth of your abilities, you need to make sure the following are all included:

• A full description of your role in the project;
• The biggest challenges you've faced;
• The solutions you've chosen, how you chose them and why;
• How you communicate and collaborate with others; and
• The outcomes and the lessons you’ve learned.  

To this, you should feel free to add any further information that you think would help you stand out from the crowd. 

It is also worth remembering that UX case studies are a good resource for UX design beginners to learn more practical design skills and to gain from the real experience of others in dealing deal with difficult or urgent problems.

22 Best UX case study examp le s you should learn

Whatever stage you’re at and whatever you are writing your case study for, these 22 top examples are bound to inspire you. 

1. Perfect Recipe -UX design for cooking and shopping

Designer s : Marina Yalanska and Vlad Taran

Case Study : Perfect Recipe

This is a mobile application that enables users to search for food recipes and to buy what they need to cook different dishes.

Why d id  we choose this  one?

This case study illustrates the entire UX design process is very simple, plain language. Many aspects of the process are included, along with some really inspirational ideas, such as product personalization, challenges and solutions, animated interactions, and other interface details.

Extra tips :

This example is from the Tubikstudio blog, which is very popular among designers. It regularly shares different branding, UI, and UX case studies. We would strongly recommend that you follow this blog to keep yourself up to date with the latest and most creative case studies.

View details

2. GnO Well Being - Branding, Web Desing & UX

Designer : Marina Yalanska and Olga Zakharyan

Case Study : GnO Well Being

This is a creative illustration website that presents and sells a weighted designer blanket that helps you get a good night’s sleep, the first step to good health and a better life.

Why d id  we choose this ?

This example is so much more than a great UX case study. In addition to the UX design , it gives you insight into many more key design issues, such as the logo, custom graphics, website pages, interactions and so on. There are many ideas here that you could copy for your own projects.

3. Splitwiser - UI/UX case redesign

Designer : Chethan KVS (a Product designer at Unacademy)

Case Study : Splitwise

This is a concept mobile app that enables users to track and split expenses with friends. The designer has also given it another name, "Splitwise." 

Why do we choose this ?

This case study shares the designer's insights into key design decisions, such as why he chose this product, why he decided to redesign the logo, how to improve the onboarding and other pages, how to optimize the user flow, how to balance all pages and functions, how to enhance UX through bottom bars, interactions, gestures, view modes, and more.

Everything is explained using intuitive images, earning it thousands of “likes”. This is a great example that is bound to help you write a stunning case study on redesigning UX.

This comes from a popular media channel called "UX Planet" that regularly posts examples of the best and latest UX case studies from around the world. Another great place to keep you up to speed with the latest UX designs.

4. Deeplyapp.com - UX & visual improvements

Designer : Sladana Kozar

Case Study : Deeplyapp

This is a health and self-care website app that helps users maintain mental well-being with meditations and exercises. This case study talks you through the design process of creating a user-friendly mobile app.

This case study focuses on improvements to the UX and visual features of this mobile app. Many aspects are included to help you understand it better, such as the design background, what to build, UI flow diagram, discoverability design, visual balance, and much more. A full set of app interfaces are presented for you to study as well.

You can also check out its Part 1 post for more details.

5. Talent Envoy - improving the recruitment process 

Designer : Enes Aktaş (Experienced UX designer)

Case Study : Talent Envoy

Talent Envoy is an intelligent job assistant that helps users find their ideal job and get to all the way to signing a contract faster and more easily.

This case study firstly points out the biggest challenges and problems faced by job-seekers—the shortage of US recruitment markets. It then talks to you through the detail of how the designers optimized the recruitment process. You will also find information on the user research process, the UI flowchart design, the related wireframe and Sketch designs, the main page design, and more. 

All the details have clear explanations and they offer a great example of how to use user research to solve problems and improve UI interfaces.

This one comes from another hot media channel called "Muzli" which shares the latest ideas, designs, and interactions about websites or website apps from all over the world. Don’t miss out on this site if you want to stay ahead of the curve. 

6. My Car Parking - UI/UX case study

Designer : Johny Vino (Experienced UX and interaction designer)

Case Study : My Car Parking

This is a mobile app that can help people get parking slots easily even when they travel beyond their normal routes. 

This is a masterclass in how to write a case study that is simple, well-structured, and easy to understand. Many intuitive lists and images are used to explain the design ideas and processes. 

It has received “claps” from over seven and a half thousand people and   is a perfect example of how to write a well-structured and easy-to-understand case study.

7. Parking Finder App - UI/UX case study

Designer : Soumitro Sobuj

Case Study : Parking Finder App

This is another concept mobile app that makes it easy for users to find parking slots even in big or overcrowded cities.

This case study is beautifully presented and gives a good presentation of the whole design process. It covers nearly all the issues that a textbook UX case study should have, such as problems and solutions, user-centered design, design strategy, user flow, information architecture , interface wireframes and visual designs, and much more besides. 

It is one of the best examples we have found of a case study that really teaches you how to write the perfect UX case study.

8. Pasion Del Cielo - coffee ordering experience

Designer : Jonathan Montalvo (Senior Designer, Branding, UXUI )

Case Study : Pasión del Cielo

This is a concept project about a real local coffee shop in Miami.

This case study demonstrates effective ways to engage users with the Pasión brand and how a site can make it as easy as possible to turn page views into coffee sales. 

There is a lot of analysis included to explain the entire design process, such as analyzing the competition, feature analysis, brand and interface improvements, and much more. Most important of all, many user personas have been created to evaluate and enhance the UX.

This is a good example to check for anyone looking to improve their own UX case study. Above all, it shows what can be done with rich images, bright colors, clear layouts, and well-crafted personas.

9. Workaway App - UX redesign

Designer : Rocket Pix (UXUI, web designer )

Case Study : Workaway App

This is a mobile app that provides international hospitality services; it helps users to contact each other to organize homestays and cultural exchanges.

This UX design case study explains how the designer redesigned the Workaway App to make it easier for users. Many intuitive charts (pie charts, flow charts, line charts), cards, and images are used to illustrate the ideas.

It is simple and easy to follow, and also a good example of how to create an intuitive case study with charts and cards.

10. Receipe App - UI/UX design process

Designer : Dorothea Niederee (UX, UI designer   )

Case Study : Recipe App

This is a food app design offering inspirational recipes for anyone who wants to eat healthier.

This case study gives a clear demonstration of the entire UI/UX design process. Three user personas are defined to present different users' needs. Some colors, typography, and UI elements are also shared.

This is a good example of how to define a detailed user persona in your UX case study.

11. Hobbfyy - a social and discovery app UX design

Designer : Mustafa Aljaburi (UX, UI designer   )

Case Study : Hobbfyy

This is a social and discovery app that makes it quick and easy to get everything you need for your hobbies.

This case study aims to show how to develop a site that will provide its users with solutions, in this case to get what they need for their hobbies. Beautiful images, a storytelling style, and special layouts are used to explain everything.

12. Bee Better - habit tracker app UX case study

Designer :   Anastasiia Mysliuk (UX, UI designer   )

Case Study : Bee Better

This is a habit tracker app that makes it easy for you to develop new useful habits.

This case study aims to solve problems associated with how we form and develop habits. It helps users find solutions and make habit formation more interesting; it motivates them to maintain their useful new habits. Many aspects of design, such as problems, solutions, the design process, discovery and research, user journey map, prototypes, and much more are illustrated and explained in simple language.

This would be a good example to follow if you are looking to create an easy-to-understand UX case study.

13.Sit My Pet - pet sitting app UX case study

Designer : Aiman Fakia (UX, UI, visual designer )

Case Study : Sit My Pet

This is a pet-setting app that provides pet owners with a digital service that helps them connect with pet sitters.

This UX case study describes a site that aims to make pet sitting more easily accessible for pet owners. It analyzes both its users and its competitors very well. The way solutions are evaluated, the user stories, and other related aspects are followed in detail to give you a better understanding of the project as a whole.

This is a good example of how to develop a UX design based on user needs.

14. Groad - food ordering system UX case study

Designer : Phap (UI designer )

Case Study : Groad

This is a food ordering app offering food delivery services from stores, restaurants, cafés, fast food bars, and others. 

This UX case study uses beautiful illustrations and colors to explain the entire design process. As well as the usual parts of the design process—UI flow chart, UI showcasing—the related logo and icon designs, typography, and other aspects are included. This is a good example if you are looking to learn how to create an immersive case study with beautiful illustrations and colors.

15. iOS VS Android UI/UX Case Study

Designer : Johanna Rüthers

Case Study : Econsy

Here is another concept app that helps people live more sustainably by using a scanning process to give them information about the ecological and social impact of products they are thinking of buying. 

This case study explains the differences in the mobile app’s appearance when it is applied on the Human Interface Guidelines (IOS) and Material Design Guidelines (Android). This will help you to create an app that works well on both Mac and Android devices.

More UI/UX case studies & designs:

16.Timo Bank - UI/UX Case Study

Timo Bank is a mobile banking app project produced by Leo Nguyen, a freelance designer and creative director. This case study aims to provide more intuitive transfer, payment, and money management solutions for mobile users.

This is a great example to consider if you are hoping to create a better banking app.

17. Endoberry Health App Design

Endoberry Health App Design provides useful solutions for women suffering from endometriosis. In turn, this gives doctors a better understanding of individual cases. The design challenges, solutions, and UI details are displayed and explained to illustrate the design project.

18. Job Portal App

Job Portal App has been specially made for designers and freelancers. This case study uses cute illustrations, simple words, and clear storytelling to explain how the designer worked out the ideal job hunting solutions for users.

19. Cafe Website - UI/UX Case Study

Café Website gives its users a great experience by making it quick and easy to order a coffee online. Many elegant page details are displayed.

20. Ping - the matchmaker app case study

Ping is a dating app that offers users a unique and effective way to find their perfect match. As you can see, its mascot is really cute and this case study will show you how a cute mascot can enhance the UX.

21. Hubba Mobile App - UI/UX Case Study

Hubba Mobile App is a B2B online marketplace where retailers can find and purchase unique products for their stores or shops. This case study aims to explain the process of creating a special mobile app for this online marketplace. It offers a beautiful and clear presentation of the entire UI/UX design process.

22. Music App - music for children

Music App shares the fancy UI and colors from a music app made for children. It is a good example that is sure to inspire you to create a distinctive children's app.

How do you create a UX case study?

If you are still not entirely sure how to go about creating a distinctive UX case study, here are a few simple steps to walk you through the entire process from start to finish:

Step  1.  Figure out your purpose

The final outcome will depend on what it is you are trying to achieve. So, before you start writing a UX design case, you should first figure out in detail what its purpose is. Ask yourself some basic questions:

• Is it for a job interview?
• Is it for improving your personal portfolio?
• Is it designed to show off your design talents on social media?
• Is it just created to practice your design skills?
• Is it made to share design experiences with other designers?

In short, figuring out your purpose and setting a goal can make the entire design process so much easier.

Step   2.   Plan or outline your case study

Whatever you want to do, it is always a good idea to start with a plan. When it comes to writing a UX case study, you should also outline your entire UX case study and decide on what sections you want to include.

For example, nowadays, a good UX design case study often covers:

• Overview : Start with a short paragraph that introduces your project.
• Challenges  and  goals : Explain the project background and point out the biggest challenges or problems you've encountered. Explain the goals you want to achieve and how you will overcome the challenges you have identified. 
• Roles  and  responsibilities : Tell readers what role you play in the project and the specific features of your role that will help create a better product.
• Design process : Introduce the entire design process in detail so that readers can see clearly what you have done to make life easier for users. Many employers check this part very carefully to see whether you have the basic skills and abilities they are looking for. So, never underestimate the importance of this section. 
• Solutions  and  outcomes : No matter what problems you have faced, the solutions and the final outcomes achieved are what really matters. So, always use this section to showcase your skills and achievements. 

You might also want to add further sections:

• User research :   Some full-stack designers also include this to give a more comprehensive view of their design skills.
• UI designs : Some experienced designers also display their relevant UIs, and UI flow, along with low- and high-fidelity prototypes to enrich the content.

Of course, if you are a newbie, and you still have questions, why not go online and search for UX case study templates that you can study and follow.

Step 3.  Explain the design process clearly

As we've explained above, the design process is always one of the most important parts of a good UX case study. You should always introduce clearly as many of the relevant parts of the process as possible. For example: show how you and your team communicate and collaborate effectively; demonstrate how you have developed ideas to address user problems; explain how you and your team have dealt with emergencies or mishaps.  

You can also introduce the UX design tools that you have chosen to simplify the entire design process. Mockplus, is an online product design platform, enabled us to adapt quickly and effectively to working from home during the recent Coronavirus lockdown. Prototyping our designs, sharing ideas, working together in an effective team, taking the process from design to handoff, it all works smoothly with this single tool.

Step  4. Improve readability and visual appeal

The content should be the main focus of your case study—but not the only focus. To make the case study as good as possible, you also need to think about its readability and visual appeal. Here are some suggestions to follow:

• Explain everything as clearly as possible.
• Add images, illustrations, charts, cards, icons, and other visuals.
• Create a clear storytelling structure or layout.
• Choose an immersive color scheme.
• Add eye-catching animations and interactions.
• Use vivid video, audio, and other multimedia resources.

The final visual effect can be make-or-break for whether your UX case study is going to stand out from the crowd. You should always take it seriously.

Step   5. Summarize

Every UX case study can be a good chance to practice and improve your design skills. So, in your conclusion, don’t forget to analyze the entire process and summarize the outcomes. Always take a minute to figure out what lessons you should take away from the process, what tips should be remembered, what should be improved, and—most important—what your next steps are going to be.

UX case studies are one of the most essential parts of a UX designer's portfolio. The ability to write a well-structured UX case study is also one of the basic skills that a competent UX professional should have. So, UX case studies play a very important role in UX designer's life.

We hope our picks of the best UX design case studies along with our step-by-step guide will help you create a stunning UX case study.

In- house content editor, specialize in SEO content writing. She is a fruit lover and visionary person.

Uploads design files from Sketch, Figma, Axure, Photoshop, and Adobe XD into our design handoff tool.

A free online prototyping tool that can create wireframes or highly interactive prototypes in just minutes.

A vector-based UI design tool enables you design in the way you want to.

Your single source of truth to build, maintain and evolve design assets in one place.

Related Content

Design Faster. Collaborate Better.

Designing the best user experience. Mockplus does it all!

Interactive prototyping

Unified collaboration

Scalable design systems

© 2014-2023 Mockplus Technology Co., Ltd. All rights reserved.

The Complete Guide to UX Case Studies

: October 23, 2023

: August 21, 2023

Writing a UX case study can be overwhelming with the proper guidance. Designing for the user experience and writing about it in a case study is much more than writing content for a webpage. You may ask, “If my design speaks for itself, should I include a UX case study in my portfolio?”

Yes, you should include UX case studies in your portfolio. And here’s why.

You need to make your portfolio stand out among the crowd. A UX case study is a great way to do that. Let’s take a minute to define what a UX case study is and look at some examples.

Table of Contents

What is a UX case study?

The benefits of ux case studies, examples of ux case studies, tips for creating a ux case study.

UX portfolios are essential to showcasing UX designer skills and abilities. Every UX designer knows better designs bring better results. Sometimes, it’s easy to let the design speak for itself — after all, it is meant to engage the audience.

But, in doing that, you, as the designer, leave many things unsaid. For example, the initial problem, the need for the design in the first place, and your process for arriving at the design you created.

This is why you need to include UX case studies in your portfolio.

UX case studies tell a curated story or journey of your design. It explains the “who, what, when, where, and how” of your design. The text should be short and sweet but also walk the reader through the thinking behind the design and the outcome of it.

[Video: Creating a UX Case Study: Right and Wrong Way to Approach It]

There are many benefits to including UX case studies in your portfolio. Think of your UX portfolio as a well-decorated cake. The designs are the cake, and UX case studies are the icing on the cake— they will catch your audience's eye and seal the deal.

Take a look at the benefits of adding UX case studies to your portfolio.

Don't forget to share this post!

What Is End-User Experience Monitoring? [+Tips For Implementing It]

What Is GUI? Graphical User Interfaces, Explained

Horizontal Scrolling in Web Design: How to Do It Well

UX Accessibility: Everything You Need to Know

Your Guide to Creating UX Problem Statements

UX Prototyping: Your Complete Guide

The Chrome UX Report: How to Use It to Improve Your Website UX

Building Your First-Time User Experience: How to Get It Right

Perfecting Your Digital UX Design — The Tips You Need to Know

Creating a User Experience Survey: Your Ultimate Guide

3 templates for conducting user tests, summarizing UX research, and presenting findings.

CMS Hub is flexible for marketers, powerful for developers, and gives customers a personalized, secure experience

How to Craft an Outstanding Case Study for Your UX Portfolio

Writing case studies for your UX portfolio can feel opaque and overwhelming. There are so many examples out there, and often the ones that make the rounds are the stunning portfolios of top visual designers. It can be inspiring to see the most beautiful work, but don’t let that distract you from the straightforward format of a good UX case study. 

At the core, a UX case study relies on excellent storytelling with a clear, understandable structure . This article breaks down the anatomy of a UX case study to help you tell a simple and effective story that shows off your skills. We’ll start with some general guidelines and structure, then break it down one piece at a time:

UX portfolio overview

What is a ux case study, general guidelines, how to structure a case study, how to fill in the details, defining the problem, understanding your users, early or alternate ideation, final design solution, next steps and learnings.

• Final thoughts

1. Before we get started

Before we dive into all the art and science of the case study, here’s a quick refresher on what a job-winning UX portfolio looks like. In this video, pro designer Dee analyses various design portfolios to pick out what works—and what doesn’t:

Simply put, a case study is the story of a design project you’ve worked on. The goal, of course, is to showcase the skills you used on the project and help potential employers envision how you’d use those skills if you worked for them.

A case study is typically written like a highly visual article, with text walking readers through a curated set of images. Curated is an important word here, because it should be short and sweet. It’s a chance to share what you want potential employers to know about your work on this project.

With that in mind, case studies are really a UX designer’s secret weapon in two ways. First, they get you in the door by showing more about your work than a resume and a top UX cover letter ever could. Another benefit is that they’re really handy in job interviews. If someone asks about a past project, you can walk them through the case study you’ve already created (this is sometimes a requirement anyway).

I mentioned that UX case studies are about storytelling. I’d actually say they’re about stories-telling, since they need to tell two intertwined stories .

The first is the story of your project. This answers questions like what problem you solved, who your users were, what solutions you explored, and what impact they had.

The second story is about you as a designer and your process. This is more about which methods you chose to use and why, how you worked within constraints, and how you worked as a member of a team (or without one).

So what are the steps for an effective case study? Well, like most things in design (and life), it depends. Every case study will be different, depending on what stories you’re telling. The six-part outline below, though, should guide you through an effective format for any UX project story. Here’s the outline (we’ll dive into each component in just a minute):

• Defining the Problem
• Understanding your Users
• Final solution

It’s worth it to add a few general notes before we dive into each of the list items above. For each section, include 1-2 short paragraphs and an image of a deliverable that visually tells the story your paragraphs explain. A reader should be able to either just read or just look at the images and roughly get what this moment in the story is communicating.

When choosing images to include, focus on quality over quantity.  Choose your best deliverables for each stage and briefly relate them back to the larger narrative. It can be tempting to overload the page with everything you created along the way, but these extra details should stay in your back pocket for interviews.

Lastly, make sure your case study is scannable . In the best of circumstances, people don’t read word for word on the web. Make sure your text is reasonably concise, use headers and strong visual hierarchy, and use bullet points and lists when possible. If you need a refresher on how to achieve this, check out our guide to the principles of visual hierarchy .

Ok, let’s take a look at each step in a bit more detail.

2. Anatomy of a UX case study

Like any story, the introduction sets the stage and gives much of the necessary context readers will need to understand your project. This is one section where people actually might take some extra time to read carefully as they try to discern what this case study is about. Make sure they have all the details they need.

Some key questions to answer are:

• What is your company and/or product?
• What user problem did you try to solve?
• What was your role?
• What tools and methods did you use?
• What are the major insights, impacts, or metrics related to the project

After introducing the project, dive more deeply into the problem you tackled. You touched upon this in the introduction, but this section is an opportunity to make a strong case for why this project exists. Did a competitor analysis or market research demand a new product? Was there past user research in your company that suggests a needed redesign of the product?

Remember that you’ll want to create a through line in the narrative, so try to lay out the problem in a way that frames your design work as a solution.

Deliverables that work really well for this section would be:

• Analytics or usage data
• Market research of internal business metrics
• Survey results or interview highlights

After explaining the problem, show how it impacts your users and their interaction with your product. If you did original user research or you’re seeking user research-oriented jobs, sharing interview scripts, affinity maps , and spreadsheets can be useful in showing your process.

However, this section shouldn’t be only about your process. A key goal of this section is articulating who your users are and what their needs are. These findings should set up your design work that follows, so try to set up that connection.

A few types of the deliverables you might share here are:

• User personas
• Mental models
• Journey maps or customer experience maps

Keep in mind you want to communicate users’ key motivations and challenges, as well as any more specific user groups you identified.

This section can really scale up or down depending on what you have to show. Research shows that hiring managers  don’t just want the final product , so it’s clear that showing some of your process is helpful. Especially for students or designers without a fully built product to show, this can be a moment for you to shine.

Don’t worry about the low fidelity of these documents, but the rougher they are, the more you’ll need to guide readers through them. Everything you show here should teach the reader something new about your process and/or your users.

Artifacts you might include are:

• Pen and paper or low fidelity digital wireframes

If you did early testing or faced constraints that determined your future design work, be sure to include them here, too.

This section should include the most final work you did on the project (e.g. wireframe flows or color mockups) and any final product it led to (if you have it). Be clear, though, about which work is yours and which isn’t.

Explain any key decisions or constraints that changed the design from the earlier stages. If you incorporated findings from usability testing, that’s great. If not, try to call out some best practices to help you explain your decisions. Referring to Material Design, WCAG, or Human Interface Guidelines can show the why behind your design.

If you’re able to show the impact of your work, this can take a good case study and make it outstanding. If your project has already been built and made available to users, have a look at any analytics, satisfaction data, or other metrics. See what you could highlight  in your case study to show how your design improved the user experience or achieved business goals. Ideally, you can refer back to your original problem statement and business goals from the introduction.

If you don’t have any way of showing the impact of your project, lay out how you would measure the impact. Showing you know how to measure success demonstrates you could do this on future projects.

Lastly, conclude your case study by sharing either your next design steps and/or some key insights you learned from the project. This isn’t just fluff! No project is perfect or final. Showing next steps is a great way to demonstrate your thinking iterative approach (without having to do the work!).

Also, many companies do (or should do) retrospectives after each project to identify challenges and improve future processes. Use this process and the insights you gain from it to inform your case study. Letting employers know you’re capable of reflection shows humility, self-awareness, and the value you can bring to a team.

3. Final thoughts

Since each case study is a unique story you’re telling about your project, it’s a little art and a little science. But starting with the structure laid out in this article will show who you are as a designer and how you solved a problem. And those are two stories companies want to hear!

If you’d like to learn more about how to craft a great UX portfolio, check out these articles:

• 5 Golden rules to build a job-winning UX portfolio
• The best UX design portfolio examples from around the web
• The best free UX/UI portfolio websites to use
• Salary negotiation for UX designers

New Case Study

How to avoid (and repair) these 3 critical design blunders

Case studies

Design Blunders

Social Proof: Why people's behaviors affect our actions

Social Proof

Adobe: The growing issue with “Free” trials UX

Adobe Trial UX

Letterboxd: How to nail product market fit with clear Jobs‑To‑Be‑Done

Jobs-To-Be-Done

Spotify Wrapped: 6 psychology principles that make it go viral every year

Spotify Wrapped

The psychology of Temu’s casino‑like shopping UX

Temu Onboarding

GoDaddy: How to improve checkout flows ethically

GoDaddy Checkout UX

Framing Effect: Why context affects decisions

Framing effect

The psychology behind highly effective landing pages

Landing page conversion

Apple vs Meta Threads: The Illusion of Privacy

Apple privacy policy

Beehiiv subscription: 5 small UX mistakes that make a BIG difference

Newsletter subscription

The Search War: Bing AI Chat vs. Google

The Psychology Behind Loom's Explosive Growth

Loom onboarding

Episode 1: Can Bing's new AI search challenge Google? 

Bing onboarding

Typeform: How to offboard users the right way

Typeform offboarding

How to increase signup confirmation rates with Sniper Links

Email confirmation UX

Labor Perception Bias: Why faster isn't always better

Labor perception bias

Tech ethics: If cookie consent prompts were honest…

Cookie consent

Amber Alert Redesign: 5 UX Improvements That Could Save Lives

Amber alerts UX

Google: How to increase feature adoption the right way

Google feature adoption

How Linkedin Increased Notification Opt-in Rates by 500%

Linkedin notifications

The Psychology of Advertising: Why this ad made me stop scrolling

Advertising psychology

The Ugly Truth About Net Promoter Score Surveys

Net promoter surveys

The Psychology Behind Amazon's Purchase Experience

Amazon purchase UX

One Simple Psychology Framework To Improve Your Onboarding

Blinkist onboarding

How Blinkist Increased Trial Conversions by 23% (Ethically)

Trial paywall optimization

YouTube’s Attempt To Solve The Paradox of Choice

Youtube retention

Adobe: The Psychology of User Offboarding

Adobe offboarding

Signal: How To Ethically Boost Your Revenues

Signal monetization

Chrome vs Brave: How To Use Ethical Design To Win Customers

Brave onboarding

The Psychology of Clubhouse’s User Retention (...and churn)

Clubhouse retention

The Scary Future Of Instagram

Instagram monetization

The Psychology of Misinformation on Facebook

Facebook misinformation

The Psychology Behind TikTok's Addictive Feed

Tiktok feed psychology

How To Properly Apply Jobs-To-Be-Done To User Onboarding

Headspace onboarding

How To Notify Users Without Being Spammy

Lifecycle emails

User Onboarding: Is HEY Email Worth It?

Hey onboarding

7 Product Team Pitfalls You Should Avoid

Product team pitfalls

How Tinder Converts 8% Of Singles Into Customers In Less Than 15min.

Tinder monetization

Coronavirus Dashboard UX: How Design Impacts Your Perception

COVID dashboard UX

How Morning Brew Grew To 1.5 Million Subs In 5 Years

Morning Brew retention

Uber Eats: How To Ethically Use Scarcity To Increase Sales

Uber Eats retention

Airbnb: How To Reduce Churn With Personalization

Airbnb personalization

6 Ways Mario Kart Tour Triggers You Into Gambling Your Money

Mario Kart monetization

Strava: 7 Strategies To Convert More Freemium Users

Strava monetization

Tesla: How To Grow Through Word-of-Mouth

Tesla charging UX

How Hopper Perfectly Nails Permission Requests UX

Hopper onboarding

9 Ways To Boost SaaS Revenues With A Better Upgrade UX

Zapier monetization

Superhuman's Secret 1-on-1 Onboarding Revealed

Superhuman onboarding

Trello User Onboarding: 7 Tactics To Inspire You

Trello onboarding

5 Deadly Onboarding Mistakes You Should Avoid

Sleepzy onboarding

Duolingo's User Retention: 8 Tactics Tested On 300 Million Users

Duolingo retention

Calm Referral Strategy: Drive Viral Growth With Simple Rewards

Calm referrals

Spotify vs Apple: How Spotify is betting $230M on podcasts to win over Apple users (Ep. 2)

Spotify onboarding

Spotify vs Apple: How Spotify is betting $230M on podcasts to win over Apple users (Ep. 1)

Spotify vs Apple

• Reviews / Why join our community?
• For companies
• Frequently asked questions

How to create the perfect structure for a UX case study

UX case studies form the core content of a UX professional’s portfolio. They are essential to getting you hired, because case studies are a window to your professional practice, by showing how you think, adapt, cooperate and ultimately solve challenges. A UX case study has to tell a story about you. Like all good stories, case studies benefit greatly from a solid structure that guides the reader through your thinking and experience. Here, we will explore how to craft the perfect structure for your UX case studies.

Let’s begin with a few quotes about case studies and interviews, from UX recruiters worldwide, compiled in 2017 by Cassandra Naji ( marketing content manager at Justinmind, the popular UX prototyping software):

”I want to see how you think strategically, how you connected the dots to land at the right solution. What does your process look like? What steps did you take to learn more about your users?” (Melissa Perri, Product Manager and UX Designer at Produx Labs) ”Having a really strong portfolio where you can talk through your whole process , not just showing research, user flows , wireframes, etc, but turning it into a story for example why you moved onto each part of the process so a hiring manager can really get inside your thought process.” (Tom Cotterill, UX Recruiter at Source LF) ” Storytelling is important. The interviewer wants to understand your process , your contribution to the team, and how your mind works.” (Rebecca Levi, UX/ UI / Product Design Recruiting Manager, The Joanne Weaver Group) “My tip would be, tell stories . When designers present a flat portfolio it doesn’t tell me about how they approach the work they do and how they deal with the ebbs and flows of design. Tell me how you navigate from start to end of a project, I like to see a case study approach.” (Sarah Bellrichard, SVP of Wholesale Internet Solutions & UX at Wells Fargo) “So, when I interview you, tell me a story about how you made something awesome even though it was super uncertain what it was going to turn out to be. And get meta and walk me through how you approach problems, how you navigate through idea generation and synthesis, and how you build solutions.” (Jeff Onken, Design Strategist & UX Manager at Northrop Grumman)

You might begin to see the pattern here: Recruiters from both large and small companies alike are all immensely interested in the same thing: your thinking and professional process. They want you to tell them a story about how you tackled previous UX challenges. To progress through to an actual interview, where you can elaborate on your stories in person, first you must pass the portfolio review obstacle – UX case studies in your portfolio are your first opportunity to tell recruiters your stories. These stories have to be tantalizing enough that the recruiter will want to invite you to learn more about them, and you. So, in order to get the recruiters’ attention, first we need to understand the power of stories, so we can understand why they are so much in demand by recruiters, and then see what story elements your UX case study should contain.

The power of storytelling in UX hiring

In our long history as a species, stories have always played an important role in our societies. Pick any time and any populated place on the planet, and some research into that culture during that era will bear this out as a fact. Writer and copyeditor Shannon Turlington (2010) offers some excellent insight from her 20+ years of experience in science and academic writing, about the importance of stories for humans.

“We use stories not only to learn but also to speculate, to pose questions and then find solutions.” - Shannon Turlington

Through storytelling, we pass on important information and lessons from generation to generation. Some stories are fictional; others are accounts of true events. But we don’t use stories just to learn. Stories are also an exercise in speculation and the exploration of possibilities. They are a great way to ask the “what if” questions in life, and find possible answers to these. In fact, storyboarding is one of the most well-known UX tools used to do just that!

Since we don’t know how the stories of our own lives will end, absorbing stories that have a beginning, middle and end can provide great satisfaction. Generally speaking, stories have the ability to provoke strong emotional responses , so they are an immensely powerful tool that can connect people to one another and, if sufficiently persuasive, bring about dramatic and profound changes in thinking.

Copyright holder: Gerd Leonhard, Flickr. Copyright terms and license: CC BY-SA 2.0

For UX professionals, telling the story of how they tackled the challenges of wicked UX design problems provides recruiters with the confidence that an applicant has great communication skills, matched with excellent technical skills and a deep understanding of methodological approaches to product development.

Assuming that you might be looking for a UX job in the near future, let’s take a look at who is going to be hiring you. They have a specific and immediate need in mind: to find a new member to join their UX team, someone brilliant who will bring inspiration, talent and hard work that will raise the team to new heights. We already know from their testimonials above that they are interested in your stories. Why?

Quite simply, by going through applicants’ portfolios, recruiters are subconsciously asking themselves a what-if question: “What if this person joined our team? What would it be like to work with this person?”. Therefore, what better way for you to answer this question for them than to provide a story? Telling a great story about your own experiences as a UX professional gives this satisfaction of having something come full circle: starting from somewhere and arriving somewhere else. It helps the recruiter see the world through your own eyes, and in the process, hopefully recognize someone who has fought a difficult challenge with skill, integrity, commitment, courage and perseverance – just the right kind of person to solve the wicked problems of design.

Structuring a captivating story

Orson Scott Card, an American science-fiction writer, wrote in 2010 that most novels are dominated by four types of story structures: milieu, idea, character and event. From this classification, we can single out the “idea” structure because it accurately frames the type of experience that a UX professional has throughout his or her working life. In Card’s own words:

“Idea stories are about the process of seeking and discovering new information through the eyes of characters who are driven to make the discoveries. The structure is very simple: The idea story begins by raising a question; it ends when the question is answered.” – Orson Scott Card

Idea stories have a structure of discovery, so the question is naturally a “why”, “how” or “what if”, exactly the type of thing that UX professionals ask themselves daily. So, in this context, there is a question that begets an answer (that’s the design problem), the protagonist (i.e., you as a UX professional) tells the story of how he or she arrived at an answer for that question (helping the reviewer see the process through the protagonist’s eyes), and, finally, there is a conclusion, an answer to the question (that’s your final product and its impact).

Copyright holder: Smita Nair Jain, Flickr. Copyright terms and license: Public Domain

A good UX case study is the story of how you broke a design challenge down into its components, and then expertly put this knowledge together to deliver a superb user experience.

Turning a UX case study into a story

Of course, we’re not saying here that you need to write a whole novel to explain what happened in a UX project you undertook in the past. A case study has to be succinct, but all the crucial elements of the story need to be there: the starting question, the process, the answer. And remember that just like any project that you designed, your UX case study is also a product of design – something that you give shape and essence to, with care and attention to detail, attempting to solve a real need: the recruiter’s need to see how you think, and, through this, your own need to become employed. So, we can conclude that the perfect UX case study has three parts, which we will outline next.

The beginning of a UX case study

Here is where you should explain the question that you tried to answer, and the context. For example, look at how the following statement describes the goals, vision and challenges to be addressed by a project:

“We wanted to design a new app that reminds busy people to do important things. The challenge was that simple reminders are often issued at a place or time where the user can’t really act on them, like a reminder to buy milk, while the user is at the office. Wouldn’t it be better to issue that reminder as the user is walking past a supermarket, on the way home?”

If you were part of a larger UX team here, you should also state your role in the project – for example, you might write something like “ My role in the project was to undertake user research and evaluation of prototypes ”.

The process of the UX case study

This part of the case study explains the steps that you took to arrive at a solution. Here, you should highlight the activities that you took and illustrate those activities with sketches, photographs, diagrams or other design artifacts or deliverables that you produced. Bear in mind that the focus here is on the process , so emphasis on iterations, rising challenges, alternatives, decision points and conflict resolution is paramount.

You should always start with some user research that frames the problem. For example, you might write this:

“We analyzed the to-do lists of 140 users aged 18-40 for a period of 3 weeks and discovered that about 60% of their tasks were location-dependent. From this analysis, we made 4 user personas and defined their experiences in managing to-do lists with customer journey maps .”

You could show one persona and one journey map here to illustrate.

Then, show how you progressed into ideation for solutions – for example, putting in a sequence of sketches that shows a user interface design evolution from napkin drawing, to low-fidelity wireframes, then interactive low-fidelity prototypes and a final pixel-perfect design shows that you have progressed from early concepts to an end product.

It’s important to annotate these with information, too, which describes how the evolution took place through consultation and evaluation . For example, next to your napkin drawing, you might say “ we carried out a focus group with 20 users to co-design an early prototype based on this idea ” and then show 2-3 alternative low-fidelity UI sketches that emerged as an output of that process. Then you might show a wireframe emerge from these sketches and say something like “ undertaking heuristic and lab-based user evaluation, we selected Alternative 2 as the way forward, but improved it with features from Alternatives 1 & 3 which were found to work better in the lab ”.

The conclusion of the UX case study

This last part of the structure shows your final answer to the original question. It’s not enough here simply to show your final deliverable. In this section, you have to demonstrate impact – how did your designed product improve the situation? Remember that the final step in every Design-Thinking process is evaluation. So, mention what you learned through lab tests, field tests, analytics mining or other data you have – e.g., “ In a 3-week field trial with 30 users, we found that these location-sensitive reminders led to less cluttered to-do lists for our users, since they were able to act on the reminders and cross them off their list instead of postponing them. ” Charts and statistics are great for demonstrating this impact.

However, don’t just stay stuck on the impact bit. It’s also important to highlight the lessons you learned and that you later reflected on your experience. What would you do differently if you had more time or resources to spend on the project? You might say this, for example: “ We found that 20% of the tasks in the to-do lists related to things that other people had to do, instead of the user. We didn’t have the budget or time to address this challenge, but in the future, we could revisit the project and focus on collaborative aspects of task managemen t.” Do remember to acknowledge your co-workers and collaborating stakeholders in the last section, too, as this shows a teamworking spirit.

“To design is to communicate clearly by whatever means you can control or master.” — Milton Glaser, celebrated American graphic designer

UX case studies are an exercise in communication

One of the most important skills for a UX professional is the ability to communicate. A UX case study is a demonstration of that ability, so writing good case studies doesn’t only demonstrate your technical and other professional skills; it also gives you a chance to prove how effective your communication skills are.

We will end this piece with a final note on UX case study structures. Many UX professionals believe that a great case study should end with a great product, but this is not always the case. First of all, remember that greatness is a relative attribute – what works well for you might be less than optimal for the person next to you and his/her own circumstances. It is also a temporary attribute: An app that was great back in 2005 was probably next to useless by 2017 – given that so much of the hardware and people’s lives had changed in the interim. However, what remains is the process – how you masterfully employed your critical thinking and knowledge of methodology to solve a difficult design problem, in the context and constraints that applied to the project at the time.

In this sense, don’t be shy to demonstrate those grand projects where the shining element was your approach to the work, even though the end product might have lost some of its luster.

The Take Away

A UX case study is an account of the events that led you to the discovery of some new knowledge, the answer to a UX design problem. Keeping in mind the recruiters’ need to answer their “what if” question (i.e., “What would it be like if this person joined our team and we had to work with him/her every day?”), structuring your case studies in the shape of an “idea” type of story will help recruiters get a glimpse of the world through your eyes, and provide a (hopefully) positive response to their question.

Your case study is a glimpse into your way of thinking: It is a demonstrator of process and critical reflection, rather than of the end product. There are only three parts to a UX case study structure (the beginning, the process and the conclusion), but knowing how much and what type of content is appropriate for each part will get you off to a good start on writing eye-grabbing case studies.

References & Where to Learn More

Hero Image: Copyright holder: Jacopo Romei, Flickr. Copyright terms and license: CC BY-SA 2.0

Course: “User Experience: The Beginner’s Guide”

Turlington, S. (2010). Why are stories so important?

Card, O. S. (2015). The 4 Story Structures that Dominate Novels

Naji, C. (2017). 8 tips for UX job interviews: questions & insights from UX managers

How to Create a UX Portfolio

Get Weekly Design Insights

Topics in this article, what you should read next, how to change your career from graphic design to ux design.

• 1.4k shares

How to Change Your Career from Marketing to UX Design

• 1.1k shares
• 3 years ago

How to Change Your Career from Web Design to UX Design

The Ultimate Guide to Understanding UX Roles and Which One You Should Go For

How to write the conclusion of your case study

• 5 years ago

7 Tips to Improve Your UX Design Practice

7 Powerful Steps for Creating the Perfect Freelance CV

Tips for Writing a CV for a UX Job Application

15 Popular Reasons to Become a Freelancer or Entrepreneur

• 4 years ago

The Design Career Map – Learn How to Get Ahead in Your Work

Open Access—Link to us!

We believe in Open Access and the  democratization of knowledge . Unfortunately, world-class educational materials such as this page are normally hidden behind paywalls or in expensive textbooks.

If you want this to change , cite this article , link to us, or join us to help us democratize design knowledge !

Privacy Settings

Our digital services use necessary tracking technologies, including third-party cookies, for security, functionality, and to uphold user rights. Optional cookies offer enhanced features, and analytics.

Experience the full potential of our site that remembers your preferences and supports secure sign-in.

Governs the storage of data necessary for maintaining website security, user authentication, and fraud prevention mechanisms.

Enhanced Functionality

Saves your settings and preferences, like your location, for a more personalized experience.

Referral Program

We use cookies to enable our referral program, giving you and your friends discounts.

Error Reporting

We share user ID with Bugsnag and NewRelic to help us track errors and fix issues.

Optimize your experience by allowing us to monitor site usage. You’ll enjoy a smoother, more personalized journey without compromising your privacy.

Analytics Storage

Collects anonymous data on how you navigate and interact, helping us make informed improvements.

Differentiates real visitors from automated bots, ensuring accurate usage data and improving your website experience.

Lets us tailor your digital ads to match your interests, making them more relevant and useful to you.

Advertising Storage

Stores information for better-targeted advertising, enhancing your online ad experience.

Personalization Storage

Permits storing data to personalize content and ads across Google services based on user behavior, enhancing overall user experience.

Advertising Personalization

Allows for content and ad personalization across Google services based on user behavior. This consent enhances user experiences.

Enables personalizing ads based on user data and interactions, allowing for more relevant advertising experiences across Google services.

Receive more relevant advertisements by sharing your interests and behavior with our trusted advertising partners.

Enables better ad targeting and measurement on Meta platforms, making ads you see more relevant.

Allows for improved ad effectiveness and measurement through Meta’s Conversions API, ensuring privacy-compliant data sharing.

LinkedIn Insights

Tracks conversions, retargeting, and web analytics for LinkedIn ad campaigns, enhancing ad relevance and performance.

LinkedIn CAPI

Enhances LinkedIn advertising through server-side event tracking, offering more accurate measurement and personalization.

Google Ads Tag

Tracks ad performance and user engagement, helping deliver ads that are most useful to you.

Share the knowledge!

Share this content on:

or copy link

Cite according to academic standards

Simply copy and paste the text below into your bibliographic reference list, onto your blog, or anywhere else. You can also just hyperlink to this article.

New to UX Design? We’re giving you a free ebook!

Download our free ebook The Basics of User Experience Design to learn about core concepts of UX design.

In 9 chapters, we’ll cover: conducting user interviews, design thinking, interaction design, mobile UX design, usability, UX research, and many more!

New to UX Design? We’re Giving You a Free ebook!

UX Case Study Guide

Case studies can often feel like a hefty, impenetrable task. Where do you even start? Compressing, structuring, and organizing a few weeks or even months of work in a few hundred words can be quite challenging to many of us. 

Fortunately, creating one isn’t really that complicated once you’ve learned the basics—and this is precisely what this article is all about. 

Read on to learn about the purpose of a case study and how you should go about creating one. Also, we’ll take a closer look at some valuable tips to get you through your first case study that’ll safeguard you from the most common pitfalls. 

UX Case Studies

Take a look at the UX case studies we've created.

Okay, so what are case studies?

Basically, a case study is an in-depth exploration of the decision-making of a person or group of people. The idea behind them is to document the subject’s actions in a particular setting and analyze their behavior and choices. 

When writing one, think of yourself as a protagonist in a story or novel. While this may sound somewhat pompous to some, it’s actually a helpful approach to take when creating a case study, and there are a couple of reasons for that. 

First off, the point of a case study is to present your thought process and reasoning skills within your field of expertise. While most projects are undoubtedly different, they all have relatively similar phases they go through—the same goes for the types of decisions you make throughout these phases. Being descriptive and analytical about the types of issues you’ve faced as a designer and the solutions you’ve come across is an awesome way of showcasing your skills. 

Secondly, storytelling is an extremely powerful persuasion tool—and there’s an extensive body of research to support these claims. People are passionate about stories. We empathize with the characters in the novels we read and the movies we see, to a point where we can drop an occasional tear once in a while. We’ve never seen or known these people, but we still happen to care. 

Well, this is all fine and dandy, but why even create a case study in the first place? 

What might you need them for?

Case studies are a great way of outlining your qualities as a designer and decision-maker. However, these documents can take a wide array of shapes and sizes.  

Designers will often create case studies to showcase their creativity, analytical skills, quantitative reasoning skills, and communication skills during job interviews. 

On the other hand, design firms or agencies typically create them to highlight the quality of the services delivered and the impact that they had on the client’s bottom line, market share, or overall success. 

What does a UX case study include?

Before discussing structure, we’d like to mention that when working on the first of your case study, don’t focus on length too much. Later, you’ll have the opportunity to trim things down with some visual support. But for now, be as descriptive as you can be with the information that’s relevant to your input in the project at hand. Alright, let’s talk about structure.  

1. Outline the task at hand

The purpose of the outline is to provide your reader with a “big picture” understanding of the project. Typically, this section should be fairly brief—think of it as a really quick onboarding.

Here’s a fictitious example: 

Project title: Headspace App Redesign

Problem: The Headspace app is continuously losing engagement from its users. Their main areas of concern are:

High uninstall rates

Dwindling MAU

Solution: Rethink Headspace’s content strategy. Design better push notifications. Gamify the experience to create long-lasting meditation streaks.

2. Highlight your role and the process 

This section gives you the chance to expand on how you or your team has planned on delivering the solutions outlined above and what your personal contribution was in the grand scheme of things. 

For instance, you can state that your responsibilities on this project predominantly revolved around interaction design and visual design.  

Then, you can follow it up with a process outline that allows you to highlight the quality of your decision-making. Ideally, the process should abide by modern industry standards. 

3. Expand on the outcomes

It’s always a great idea to focus on hard numbers when speaking about outcomes. Of course, the quality of your design will play a significant role in how your work will be appreciated, but at the same time, the people reviewing your case studies are organizations or clients that need solid results. The more specific you can get about the impact your design has had on the clients’ bottom line, the better. 

Here are a few examples of outcomes that we’ve presented in some of our case studies: 

78% increase in conversion rates. Thanks to better usability, the schools are a lot more likely to upgrade their trial accounts and become paying customers.

4x increase in perceived value. Good-looking apps look more trustworthy and valuable, which is why we’ve invested our time in creating a modern and sleek interface.

Acquisition of new clients. Based on new tailored features and interactive prototypes, we helped acquire big Governmental and Corporate clients.

Reduced costs by 3x: Increased developers’ efficiency and reduced costs by having a user-centered design approach.

It’s always best to focus on actual numbers rather than arbitrary improvements. Your viewpoint as a designer is quite different from a client who probably has a different background and different goals in mind. By sticking with hard numbers, you’ll be able to accentuate the objective value your team or yourself can produce. 

Tips for writing a great case study

On the surface, writing a case study may appear simple. I mean, a project outline, the process, and the outcome—nothing complicated there. That’s only partly true. The hard part is creating an impactful and engaging case study. Below, you’ll find some useful recommendations to make your project overview captivating and legible. 

Storytelling

We mentioned storytelling above, and we’re going to do it again. Yes, storytelling is an incredibly overlooked part of creating a case study. Your goal here is to be descriptive—you want to get your readers to empathize with you. You want them to feel what you felt at the beginning of the project. Don’t hesitate to create some dramatic tension where you can (but don’t go overboard). 

Clear structure

Given that you don’t get too excited with the dramatic tension, you should think of a very clear and easy-to-scan structure for your case study. The person reading it should have a clear understanding of what section they’re reading at all times. 

Use bullet points where you can. They help organize the text, make the information much more accessible , and provide your case study with clear information architecture. 

Avoid large blocks of text

This is critical. There’s nothing more dissuading than a wall of text with no paragraphs. You’ve probably been there as well, reading something mildly interesting where you see a 20-line paragraph, thinking to yourself “Nah.”

Typically, it’s a good idea to keep your paragraphs up to 5 lines in length, but in a case study, it’s reasonable to even go with less. 

Add visuals where you can

Remember the wall of text we mentioned above? That applies to content that doesn’t have visual support as well. There are many reasons why you’d want to include some images in your case study, but the most important ones are:

After all, this is a highlight of your design skills;

You’re providing visual support to your storytelling, making it more compelling and captivating;

You make the text much more accessible by watering down all that text with some media while allows the eyes to rest a bit; 

Pet projects work too

Case studies don’t necessarily have to be about “Headspace-tier” redesigns. Feel free to write one about a pet project of yours—the most important part here is highlighting your thought process between a problem and a solution. 

Even if you can’t code, you can still showcase, come up with an idea, validate it, and come up with a UX solution. These ideas or problems don’t have to be anything too drastic either. We would suggest picking a struggle that you yourself are dealing with so that you have some insight into it right off the bat.

Seek inspiration

Check out the links below for inspiration:

https://growth.design/

https://adamfard.com/ux-project

The bottom line

By following the steps above, you’ll be able to knock out an awesome case study while also avoiding the most common pitfalls first-timers face. However, bear in mind that case studies have a wide array of purposes, and you should always adjust them to your particular needs.

Don't forget to share this post:

Want to improve your App?

We help you to resolve Usability, Retention Rate and Conversion issues:

Related Stories

Explore ai writing tools: a quick guide.

Curious about how AI writing tools can transform your writing? These tools leverage cutting-edge AI to enhance creativity, ensure error-free grammar, and streamline content production. Whether you're working on marketing materials, academic essays, or captivating blog posts, our guide delves into the seamless integration of AI tools with SEO tactics, improving productivity and sparking innovation in content creation. Dive in now and start revolutionizing your writing!

AI in Business Intelligence

Curious about how AI in Business Intelligence is changing the game? Dive into how advanced analytics, machine learning, and natural language processing are not just buzzwords but real tools reshaping strategic decision-making and operational efficiency in the business world. Let's explore the transformative journey of AI-driven BI tools together.

AI in Business Operation: Maximizing Efficiency

Discover how AI in business operations is revolutionizing efficiency and innovation, from predictive analytics enhancing supply chain management to AI-driven tools transforming customer experiences. Explore the transformative power of artificial intelligence as it reshapes decision-making, operational streamlining, and customer engagement across industries.

Exclusive UX Articles & Strategies

for Startups, UX Designers & Entrepreneurs

20+ Outstanding UX/UI Design Case Studies

Discover an expertly curated collection of 20+ inspirational UX/UI design case studies that will empower you to create outstanding case studies for your own portfolio.

• Comprehensive end-to-end case studies covering research, ideation, design, testing, and conclusions.
• Perfect for designers building portfolios and looking for inspiration to create their own case studies.
• Learn new methods and techniques, improve your understanding, and apply them to your projects.
• Gain insights from the successes and challenges of accomplished designers.

Want to get access to 30+ more case studies including smart tagging system?

Download full version

All case studies included in this collection are sourced from real designers' portfolios and are used for the purpose of learning and inspiration. The original authors retain all rights to their work.

Product Design Bundle and save

User Research New

Content Design

UX Design Fundamentals

Software and Coding Fundamentals for UX

• UX training for teams
• Hire our alumni
• Student Stories
• State of UX Hiring Report 2024
• Our mission
• Advisory Council

Education for every phase of your UX career

Professional Diploma

Learn the full user experience (UX) process from research to interaction design to prototyping.

Combine the UX Diploma with the UI Certificate to pursue a career as a product designer.

Professional Certificates

Learn how to plan, execute, analyse and communicate user research effectively.

Master content design and UX writing principles, from tone and style to writing for interfaces.

Understand the fundamentals of UI elements and design systems, as well as the role of UI in UX.

Short Courses

Gain a solid foundation in the philosophy, principles and methods of user experience design.

Learn the essentials of software development so you can work more effectively with developers.

Give your team the skills, knowledge and mindset to create great digital products.

Join our hiring programme and access our list of certified professionals.

Learn about our mission to set the global standard in UX education.

Meet our leadership team with UX and education expertise.

Members of the council connect us to the wider UX industry.

Our team are available to answer any of your questions.

Fresh insights from experts, alumni and the wider design community.

Success stories from our course alumni building thriving careers.

Discover a wealth of UX expertise on our YouTube channel.

Latest industry insights. A practical guide to landing a job in UX.

A complete guide to presenting UX research findings

In this complete guide to presenting UX research findings, we’ll cover what you should include in a UX research report, how to present UX research findings and tips for presenting your UX research.

The State of UX Hiring Report 2024

Learn how to start your UX career with hard facts and practical advice from those who have gone before you. In this report, we look at UX hiring trends in 2024 to help you break into the industry.

User experience research sets out to identify the problem that a product or service needs to solve and finds a way to do just that. Research is the first and most important step to optimising user experience.

UX researchers do this through interviews, surveys, focus groups, data analysis and reports. Reports are how UX researchers present their work to other stakeholders in a company, such as designers, developers and executives.

In this guide, we’ll cover what you should include in a UX research report, how to present UX research findings and tips for presenting your UX research.

Components of a UX research report

How to write a ux research report, 5 tips on presenting ux research findings.

Ready to present your research findings? Let’s dive in.

[GET CERTIFIED IN USER RESEARCH]

There are six key components to a UX research report.

Introduction

The introduction should give an overview of your UX research . Then, relate any company goals or pain points to your research. Lastly, your introduction should briefly touch on how your research could affect the business.

Research goals

Simply put, your next slide or paragraph should outline the top decisions you need to make, the search questions you used, as well as your hypothesis and expectations.

Business value

In this section, you can tell your stakeholders why your research matters. If you base this research on team-level or product development goals, briefly touch on those.

Methodology

Share the research methods you used and why you chose those methods. Keep it concise and tailored to your audience. Your stakeholders probably don’t need to hear everything that went into your process.

Key learnings

This section will be the most substantial part of your report or presentation. Present your findings clearly and concisely. Share as much context as possible while keeping your target audience – your stakeholders – in mind.

Recommendations

In the last section of your report, make actionable recommendations for your stakeholders. Share possible solutions or answers to your research questions. Make your suggestions clear and consider any future research studies that you think would be helpful.

1. Define your audience

Most likely, you’ll already have conducted stakeholder interviews when you were planning your research. Taking those interviews into account, you should be able to glean what they’re expecting from your presentation.

Tailor your presentation to the types of findings that are most relevant, how those findings might affect their work and how they prefer to receive information. Only include information they will care about the most in a medium that’s easy for them to understand.

Do they have a technical understanding of what you’re doing or should you keep it a non-technical presentation? Make sure you keep the terminology and data on a level they can understand.

What part of the business do they work in? Executives will want to know about how it affects their business, while developers will want to know what technological changes they need to make.

2. Summarise

As briefly as possible, summarise your research goals, business value and methodology. You don’t need to go into too much detail for any of these items. Simply share the what, why and how of your research.

Answer these questions:

• What research questions did you use, and what was your hypothesis?
• What business decision will your research assist with?
• What methodology did you use?

You can briefly explain your methods to recruit participants, conduct interviews and analyse results. If you’d like more depth, link to interview plans, surveys, prototypes, etc.

3. Show key learnings

Your stakeholders will probably be pressed for time. They won’t be able to process raw data and they usually don’t want to see all of the work you’ve done. What they’re looking for are key insights that matter the most to them specifically. This is why it’s important to know your audience.

Summarise a few key points at the beginning of your report. The first thing they want to see are atomic research nuggets. Create condensed, high-priority bullet points that get immediate attention. This allows people to reference it quickly. Then, share relevant data or artefacts to illustrate your key learnings further.

Relevant data:

• Recurring trends and themes
• Relevant quotes that illustrate important findings
• Data visualisations

Relevant aspects of artefacts:

• Quotes from interviews
• User journey maps
• Affinity diagrams
• Storyboards

For most people you’ll present to, a summary of key insights will be enough. But, you can link to a searchable repository where they can dig deeper. You can include artefacts and tagged data for them to reference.

[GET CERTIFIED IN UX]

4. Share insights and recommendations

Offer actionable recommendations, not opinions. Share clear next steps that solve pain points or answer pending decisions. If you have any in mind, suggest future research options too. If users made specific recommendations, share direct quotes.

5. Choose a format

There are two ways you could share your findings in a presentation or a report. Let’s look at these two categories and see which might be the best fit for you.

Usually, a presentation is best for sharing data with a large group and when presenting to non-technical stakeholders. Presentations should be used for visual communication and when you only need to include relevant information in a brief summary.

A presentation is usually formatted in a:

• Case studies
• Atomic research nuggets
• Pre-recorded video

If you’re presenting to a smaller group, technical stakeholder or other researchers, you might want to use a report. This gives you the capacity to create a comprehensive record. Further, reports could be categorised based on their purpose as usability, analytics or market research reports.

A report is typically formatted in a:

• Notion or Confluence page
• Slack update

You might choose to write a report first, then create a presentation. After the presentation, you can share a more in-depth report. The report could also be used for records later.

1. Keep it engaging

When you’re presenting your findings, find ways to engage those you’re presenting to. You can ask them questions about their assumptions or what you’re presenting to get them more involved.

For example, “What do you predict were our findings when we asked users to test the usability of the menu?” or “What suggestions do you think users had for [a design problem]?”

If you don’t want to engage them with questions, try including alternative formats like videos, audio clips, visualisations or high-fidelity prototypes. Anything that’s interactive or different will help keep their engagement. They might engage with these items during or after your presentation.

Another way to keep it engaging is to tell a story throughout your presentation. Some UX researchers structure their presentations in the form of Joseph Campbell’s Hero’s Journey . Start in the middle with your research findings and then zoom out to your summary, insights and recommendations.

2. Combine qualitative and quantitative data

When possible, use qualitative data to back up quantitative data. For example, include a visualisation of poll results with a direct quote about that pain point.

Use this opportunity to show the value of the work you do and build empathy for your users. Translate your findings into a format that your stakeholders – designers, developers or executives – will be able to understand and act upon.

3. Make it actionable

Actionable presentations are engaging and they should have some business value . That means they need to solve a problem or at least move toward a solution to a problem. They might intend to optimise usability, find out more about the market or analyse user data.

Here are a few ways to make it actionable:

• Include a to-do list at the end
• Share your deck and repository files for future reference
• Recommend solutions for product or business decisions
• Suggest what kind of research should happen next (if any)
• Share answers to posed research questions

4. Keep it concise and effective

Make it easy for stakeholders to dive deeper if they want to but make it optional. Yes, this means including links to an easily searchable repository and keeping your report brief.

Humans tend to focus best on just 3-4 things at a time. So, limit your report to three or four major insights. Additionally, try to keep your presentation down to 20-30 minutes.

Remember, you don’t need to share everything you learned. In your presentation, you just need to show your stakeholders what they are looking for. Anything else can be sent later in your repository or a more detailed PDF report.

5. Admit the shortcomings of UX research

If you get pushback from stakeholders during your presentation, it’s okay to share your constraints.

Your stakeholders might not understand that your sample size is big enough or how you chose the users in your study or why you did something the way you did. While qualitative research might not be statistically significant, it’s usually representative of your larger audience and it’s okay to point that out.

Because they aren’t researchers, it’s your job to explain your methodology to them but also be upfront about the limitations UX research can pose. When all of your cards are on the table, stakeholders are more likely to trust you.

When it comes to presenting your UX research findings, keep it brief and engaging. Provide depth with external resources after your presentation. This is how you get stakeholders to find empathy for your users. This is how you master the art of UX.

Need to go back to the basics and learn more about UX research? Dive into these articles:

What is UX research? The 9 best UX research tools to use in 2022

Subscribe to our newsletter

Get the best UX insights and career advice direct to your inbox each month.

Thanks for subscribing to our newsletter

You'll now get the best career advice, industry insights and UX community content, direct to your inbox every month.

Upcoming courses

Professional diploma in ux design.

Learn the full UX process, from research to design to prototyping.

Professional Certificate in UI Design

Master key concepts and techniques of UI design.

Certificate in Software and Coding Fundamentals for UX

Collaborate effectively with software developers.

Certificate in UX Design Fundamentals

Get a comprehensive introduction to UX design.

Professional Certificate in Content Design

Learn the skills you need to start a career in content design.

Professional Certificate in User Research

Master the research skills that make UX professionals so valuable.

Upcoming course

Build your UX career with a globally-recognised, industry-approved certification. Get the mindset, the skills and the confidence of UX designers.

You may also like

The 10 best user interface (UI) design tools to try in 2024

The ultimate guide to usability testing for UX in 2024

A beginner’s guide to typography design

Build your UX career with a globally recognised, industry-approved qualification. Get the mindset, the confidence and the skills that make UX designers so valuable.

A popular YouTuber's negative video of Humane's AI Pin raises questions about critical reviews in the age of innovation

• This post originally appeared in the Insider Today newsletter.
• You can sign up for Business Insider's daily newsletter here .

Hello there! If you're struggling to decide the foods worth buying organic, best-selling author Michael Pollan has some suggestions for the ones worth splurging on to avoid harmful chemicals .  

In today's big story, we're looking at a critical tech review that caused a bit of a stir on social media .

What's on deck:

Markets: Goldman Sachs quiets the haters with a monster earnings report .

Tech: Leaked docs show one of Prime Video's biggest issues, forcing customers to abandon shows .

Business: The best bet in business these days? Targeting young men who like to gamble .

But first, the review is in!

If this was forwarded to you, sign up here.

The big story

Up for review.

"The Worst Product I've Ever Reviewed… For Now"

Marques Brownlee, the YouTuber better known as MKBHD, didn't mince words with the title of his review of Humane's AI Pin .

In a 25-minute video , Brownlee details all the issues he encountered using the AI device. (Spoiler alert: There were a lot.)

Brownlee's review aligns with other criticisms of the device . But not all of those came from someone with as much sway. His YouTube channel has more than 18 million subscribers.

One user on X pointed that out , calling the review "almost unethical" for "potentially killing someone else's nascent project" in a post reposted over 2,000 times. 

Most of the internet disagreed, and a Humane exec even thanked Brownlee on X for the "fair and valid critiques." 

But it highlights the power of Brownlee's reviews. Earlier this year, a negative video of Fisker's Ocean SUV by Brownlee also made waves on social media . 

Critical reviews in the age of innovation raise some interesting questions.

To be clear, there was nothing wrong with Brownlee's review. Humane's AI Pin costs $700. Watering down his review to ease the blow would be a disservice to the millions of fans relying on his perspective before making such a significant purchase.

Too often, companies view potential customers as an extension of their research and development. They are happy to sell a product that is still a work in progress on the promise they'll fix it on the fly. ("Updates are coming!")

But in a world of instant gratification, it can be hard to appreciate that innovation takes time. 

Even Apple can run into this conundrum. Take the Apple Vision Pro. Reviewers are impressed with the technology behind the much-anticipated gadget — but are still struggling to figure out what they can do with it . Maybe, over time, that will get sorted out. It's also worth remembering how cool tech can be, as Business Insider's Peter Kafka wrote following a bunch of trips in Waymo's software-powered taxis in San Francisco . Sure, robotaxis have their issues, Peter said, but they also elicit that "golly-gee-can-you-believe-it" sense.

As for Humane, America loves a comeback story. Just look at "Cyberpunk 2077." The highly anticipated video game had a disastrous launch in 2020 , but redeemed itself three years later, ultimately winning a major award .

Still, Humane shouldn't get a pass for releasing a product that didn't seem ready for primetime, according to the reviews. 

And its issue could be bigger than glitchy tech. Humane's broader thesis about reducing screen time might not be as applicable. As BI's Katie Notopolous put it: " I love staring at my iPhone ."

3 things in markets

1. Goldman finally strikes gold. After a rough stretch, the vaunted investment bank crushed earnings expectations , sending its stock soaring. A big tailwind, according to CEO David Solomon, is AI spawning " enormous opportunities " for the bank. 

2. Buy the dip, Wedbush says. Last week's drop among tech stocks shouldn't scare away investors , according to Wedbush. A strong earnings report, buoyed by the ongoing AI craze, should keep them soaring, strategists said. But JPMorgan doesn't see it that way, saying prices are already stretched .   

3. China's economy beat analysts' expectations. The country's GDP grew 5.3% in the first quarter of 2024, according to data published by the National Bureau of Statistics on Tuesday. It's a welcome return to form for the world's second-largest economy, although below-par new home and retail sales remain a cause for concern .

3 things in tech

1. Amazon Prime Video viewers are giving up on its shows. Leaked documents show viewers are fed up with the streamer's error-ridden catalog system , which often has incomplete titles and missing episodes. In 2021, 60% of all content-related complaints were about Prime Video's catalog.

2. Eric Newcomer is bringing his Cerebral Valley AI Summit to New York. The conference, originally held in San Francisco, is famous for producing one of the largest generative AI acquisitions ever. Now, it's coming to New York in June .

3. OpenAI is plotting an expansion to NYC. Two people familiar with the plans told BI that the ChatGPT developer is looking to open a New York office next year. That would be the company's fifth office, alongside its current headquarters in San Francisco, a just-opened site in Tokyo, and spots in London and Dublin.

3 things in business

1. America's young men are spending their money like never before. From sports betting to meme coins, young men are more willing than ever to blow money in the hopes of making a fortune .

2. Investors are getting into women's sports. With women like Caitlin Clark dominating March Madness headlines, investors see a big opportunity. BI compiled a list of 13 investors and fund managers pouring money into the next big thing in sports.

3. Bad news for Live Nation. The Wall Street Journal reports that the Justice Department could hit the concert giant with an antitrust lawsuit as soon as next month. Live Nation, which owns Ticketmaster, has long faced criticism over its high fees.

In other news

Blackstone hires Walmart AI whiz to supercharge its portfolio companies .

Taylor Swift, Rihanna, Blackpink's Lisa: Celebrities spotted at Coachella 2024 . 

NYC's rat czar says stop feeding the pigeons if you want the vermin gone .

A major Tesla executive left after 18 years at the company amid mass layoffs .

Some Tesla factory workers realized they were laid off when security scanned their badges and sent them back on shuttles, sources say .

New York is in, San Francisco is very much out for tech workers relocating .

AI could split workers into 2: The ones whose jobs get better and the ones who lose them completely .

Oh look at that! Now Google is using AI to answer search queries .

A longtime banker gives a rare inside look at how he is thinking about his next career move, from compensation to WFH .

Clarence Thomas didn't show up for work today .

What's happening today

Today's earnings: United Airlines, Bank of America, Morgan Stanley, and others are reporting . 

It's Free Cone Day at participating Ben & Jerry's stores. 

The Insider Today team: Dan DeFrancesco , deputy editor and anchor, in New York. Jordan Parker Erb , editor, in New York. Hallam Bullock , senior editor, in London. George Glover , reporter, in London.

Watch: Nearly 50,000 tech workers have been laid off — but there's a hack to avoid layoffs

• Main content

• SUGGESTED TOPICS
• The Magazine
• Newsletters
• Managing Yourself
• Managing Teams
• Work-life Balance
• The Big Idea
• Data & Visuals
• Reading Lists
• Case Selections
• HBR Learning
• Topic Feeds
• Account Settings
• Email Preferences

Case Study: How Aggressively Should a Bank Pursue AI?

• Thomas H. Davenport
• George Westerman

A Malaysia-based CEO weighs the risks and potential benefits of turning a traditional bank into an AI-first institution.

Siti Rahman, the CEO of Malaysia-based NVF Bank, faces a pivotal decision. Her head of AI innovation, a recent recruit from Google, has a bold plan. It requires a substantial investment but aims to transform the traditional bank into an AI-first institution, substantially reducing head count and the number of branches. The bank’s CFO worries they are chasing the next hype cycle and cautions against valuing efficiency above all else. Siti must weigh the bank’s mixed history with AI, the resistance to losing the human touch in banking services, and the risks of falling behind in technology against the need for a prudent, incremental approach to innovation.

Two experts offer advice: Noemie Ellezam-Danielo, the chief digital and AI strategy at Société Générale, and Sastry Durvasula, the chief information and client services officer at TIAA.

Siti Rahman, the CEO of Malaysia-headquartered NVF Bank, hurried through the corridors of the university’s computer engineering department. She had directed her driver to the wrong building—thinking of her usual talent-recruitment appearances in the finance department—and now she was running late. As she approached the room, she could hear her head of AI innovation, Michael Lim, who had joined NVF from Google 18 months earlier, breaking the ice with the students. “You know, NVF used to stand for Never Very Fast,” he said to a few giggles. “But the bank is crawling into the 21st century.”

• Thomas H. Davenport is the President’s Distinguished Professor of Information Technology and Management at Babson College, a visiting scholar at the MIT Initiative on the Digital Economy, and a senior adviser to Deloitte’s AI practice. He is a coauthor of All-in on AI: How Smart Companies Win Big with Artificial Intelligence (Harvard Business Review Press, 2023).
• George Westerman is a senior lecturer at MIT Sloan School of Management and a coauthor of Leading Digital (HBR Press, 2014).

Partner Center

• Open access
• Published: 18 April 2024

The predictive power of data: machine learning analysis for Covid-19 mortality based on personal, clinical, preclinical, and laboratory variables in a case–control study

• Maryam Seyedtabib   ORCID: orcid.org/0000-0003-1599-9374 1 ,
• Roya Najafi-Vosough   ORCID: orcid.org/0000-0003-2871-5748 2 &
• Naser Kamyari   ORCID: orcid.org/0000-0001-6245-5447 3  

BMC Infectious Diseases volume  24 , Article number:  411 ( 2024 ) Cite this article

Metrics details

Background and purpose

The COVID-19 pandemic has presented unprecedented public health challenges worldwide. Understanding the factors contributing to COVID-19 mortality is critical for effective management and intervention strategies. This study aims to unlock the predictive power of data collected from personal, clinical, preclinical, and laboratory variables through machine learning (ML) analyses.

A retrospective study was conducted in 2022 in a large hospital in Abadan, Iran. Data were collected and categorized into demographic, clinical, comorbid, treatment, initial vital signs, symptoms, and laboratory test groups. The collected data were subjected to ML analysis to identify predictive factors associated with COVID-19 mortality. Five algorithms were used to analyze the data set and derive the latent predictive power of the variables by the shapely additive explanation values.

Results highlight key factors associated with COVID-19 mortality, including age, comorbidities (hypertension, diabetes), specific treatments (antibiotics, remdesivir, favipiravir, vitamin zinc), and clinical indicators (heart rate, respiratory rate, temperature). Notably, specific symptoms (productive cough, dyspnea, delirium) and laboratory values (D-dimer, ESR) also play a critical role in predicting outcomes. This study highlights the importance of feature selection and the impact of data quantity and quality on model performance.

This study highlights the potential of ML analysis to improve the accuracy of COVID-19 mortality prediction and emphasizes the need for a comprehensive approach that considers multiple feature categories. It highlights the critical role of data quality and quantity in improving model performance and contributes to our understanding of the multifaceted factors that influence COVID-19 outcomes.

Peer Review reports

Introduction

The World Health Organization (WHO) has declared COVID-19 a global pandemic in March 2020 [ 1 ]. The first cases of SARSCoV-2, a new severe acute respiratory syndrome coronavirus, were detected in Wuhan, China, and rapidly spread to become a global public health problem [ 2 ]. The clinical presentation and symptoms of COVID-19 may be similar to those of Middle East Respiratory Syndrome (MERS) and Severe Acute Respiratory Syndrome (SARS), however the rate of spread is higher [ 3 ]. By December 31, 2022, the pandemic had caused more than 729 million cases and nearly 6.7 million deaths (0.92%) were confirmed in 219 countries worldwide [ 4 ]. For many countries, figuring out what measures to take to prevent death or serious illness is a major challenge. Due to the complexity of transmission and the lack of proven treatments, COVID-19 is a major challenge worldwide [ 5 , 6 ]. In middle- and low-income countries, the situation is even more catastrophic due to high illiteracy rates, a very poor health care system, and lack of intensive care units [ 5 ]. In addition, understanding the factors contributing to COVID-19 mortality is critical for effective management and intervention strategies [ 6 ].

Numerous studies have shown several factors associated with COVID-19 outcomes, including socioeconomic, environmental, individual demographic, and health factors [ 7 , 8 , 9 ]. Risk factors for COVID -19 mortality vary by study and population studied [ 10 ]. Age [ 11 , 12 ], comorbidities such as hypertension, cardiovascular disease, diabetes, and COPD [ 13 , 14 , 15 ], sex [ 13 ], race/ethnicity [ 11 ], dementia, and neurologic disease [ 16 , 17 ], are some of the factors associated with COVID-19 mortality. Laboratory factors such as elevated levels of inflammatory markers, lymphopenia, elevated creatinine levels, and ALT are also associated with COVID-19 mortality [ 5 , 18 ]. Understanding these multiple risk factors is critical to accurately diagnose and treat COVID-19 patients.

Accurate diagnosis and treatment of the disease requires a comprehensive assessment that considers a variety of factors. These factors include personal factors such as medical history, lifestyle, and genetics; clinical factors such as observations on physical examinations and physician reports; preclinical factors such as early detection through screening or surveillance; laboratory factors such as results of diagnostic tests and medical imaging; and patient-reported signs and symptoms. However, the variety of characteristics associated with COVID-19 makes it difficult for physicians to accurately classify COVID-19 patients during the pandemic.

In today's digital transformation era, machine learning plays a vital role in various industries, including healthcare, where substantial data is generated daily [ 19 , 20 , 21 ]. Numerous studies have explored machine learning (ML) and explainable artificial intelligence (AI) in predicting COVID-19 prognosis and diagnosis [ 22 , 23 , 24 , 25 ]. Chadaga et al. have developed decision support systems and triage prediction systems using clinical markers and biomarkers [ 22 , 23 ]. Similarly, Khanna et al. have developed a ML and explainable AI system for COVID-19 triage prediction [ 24 ]. Zoabi has also made contributions in this field, developing ML models that predict COVID-19 test results with high accuracy based on a small number of features such as gender, age, contact with an infected person and initial clinical symptoms [ 25 ]. These studies emphasize the potential of ML and explainable AI to improve COVID-19 prediction and diagnosis. Nonetheless, the efficacy of ML algorithms heavily relies on the quality and quantity of data utilized for training. Recent research has indicated that deep learning algorithms' performance can be significantly enhanced compared to traditional ML methods by increasing the volume of data used [ 26 ]. However, it is crucial to acknowledge that the impact of data volume on model performance can vary based on data characteristics and experimental setup, highlighting the need for careful consideration and analysis when selecting data for model training. While the studies emphasize the importance of features in training ML algorithms for COVID-19 prediction and diagnosis, additional research is required on methods to enhance the interpretability of features.

Therefore, the primary aim of this study is to identify the key factors associated with mortality in COVID -19 patients admitted to hospitals in Abadan, Iran. For this purpose, seven categories of factors were selected, including demographic, clinical and conditions, comorbidities, treatments, initial vital signs, symptoms, and laboratory tests, and machine learning algorithms were employed. The predictive power of the data was assessed using 139 predictor variables across seven feature sets. Our next goal is to improve the interpretability of the extracted important features. To achieve this goal, we will utilize the innovative SHAP analysis, which illustrates the impact of features through a diagram.

Materials and methods

Study population and data collection.

Using data from the COVID-19 hospital-based registry database, a retrospective study was conducted from April 2020 to December 2022 at Ayatollah Talleghani Hospital (a COVID‑19 referral center) in Abadan City, Iran.

A total of 14,938 patients were initially screened for eligibility for the study. Of these, 9509 patients were excluded because their transcriptase polymerase chain reaction (RT-PCR) test results were negative or unspecified. The exclusion of patients due to incomplete or missing data is a common issue in medical research, particularly in the use of electronic medical records (EMRs) [ 27 ]. In addition, 1623 patients were excluded because their medical records contained more than 70% incomplete or missing data. In addition, patients younger than 18 years were not included in the study. The criterion for excluding 1623 patients due to "70% incomplete or missing data" means that the medical records of these patients did not contain at least 30% of the data required for a meaningful analysis. This threshold was set to ensure that the dataset used for the study contained a sufficient amount of complete and reliable information to draw accurate conclusions. Incomplete or missing data in a medical record may relate to key variables such as patient demographics, symptoms, lab results, treatment information, outcomes, or other data points important to the research. Insufficient data can affect the validity and reliability of study results and lead to potential bias or inaccuracies in the findings. It is important to exclude such incomplete records to maintain the quality and integrity of the research findings and to ensure that the conclusions drawn are based on robust and reliable data. After these exclusions, 3806 patients remained. Of these patients, 474 died due to COVID -19, while the remaining 3332 patients recovered and were included in the control group. To obtain a balanced sample, the control group was selected with a propensity score matching (PSM). The PSM refers to a statistical technique used to create a balanced comparison group by matching individuals in the control group (in this case, the survived group) with individuals in the case group (in this case, the deceased group) based on their propensity scores. In this study, the propensity scores for each person represented the probability of death (coded as a binary outcome; survived = 0, deceased = 1) calculated from a set of covariates (demographic factors) using the matchit function from the MatchIt library. Two individuals, one from the deceased group and one from the survived group, are considered matched if the difference between their propensity scores is small. Non-matching participants are discarded. The matching aims to reduce bias by making the distribution of observed characteristics similar between groups, which ultimately improves the comparability of groups in observational studies [ 28 ]. In total, the study included 1063 COVID-19 patients who belonged to either the deceased group (case = 474) or the survived group (control = 589) (Fig.  1 ).

Flowchart describing the process of patient selection

In the COVID‑19 hospital‑based registry database, one hundred forty primary features in eight main classes including patient’s demographics (eight features), clinical and conditions features (16 features), comorbidities (18 features), treatment (17 features), initial vital sign (14 features), symptoms during hospitalization (31 features), laboratory results (35 features), and an output (0 for survived and 1 for deceased) was recorded for COVID-19 patients. The main features included in the hospital-based COVID-19 registry database are provided in Appendix Table  1 .

To ensure the accuracy of the recorded information, discharged patients or their relatives were called and asked to review some of the recorded information (demographic information, symptoms, and medical history). Clinical symptoms and vital signs were referenced to the first day of hospitalization (at admission). Laboratory test results were also referenced to the patient’s first blood sample at the time of hospitalization.

The study analyzed 140 variables in patients' records, normalizing continuous variables and creating a binary feature to categorize patients based on outcomes. To address the issue of an imbalanced dataset, the Synthetic Minority Over-sampling Technique (SMOTE) was utilized. Some classes were combined to simplify variables. For missing data, an imputation technique was applied, assuming a random distribution [ 29 ]. Little's MCAR test was performed with the naniar package to assess whether missing data in a dataset is missing completely at random (MCAR) [ 30 ]. The null hypothesis in this test is that the data are MCAR, and the test statistic is a chi-square value.

The Ethics Committee of Abadan University of Medical Science approved the research protocol (No. IR.ABADANUMS.REC.1401.095).

Predictor variables

All data were collected in eight categories, including demographic, clinical and conditions, comorbidities, treatment, initial vital signs, symptoms, and laboratory tests in medical records, for a total of 140 variables.

The "Demographics" category encompasses eight features, three of which are binary variables and five of which are categorical. The "Clinical Conditions" category includes 16 features, comprising one quantitative variable, 12 binary variables, and five categorical features. " Comorbidities ", " Treatment ", and " Symptoms " each have 18, 17, and 30 binary features, respectively. Also, there is one quantitative variable in symptoms category. The "Initial Vital Signs" category features 11 quantitative variables, two binary variables, and one categorical variable. Finally, the "Laboratory Tests" category comprises 35 features, with 33 being quantitative, one categorical, and one binary (Appendix Table  1 ).

Outcome variable

The primary outcome variable was mortality, with December 31, 2022, as the last date of follow‐up. The feature shows the class variable, which is binary. For any patient in the survivor group, the outcome is 0; otherwise, it is 1. In this study, 44.59% ( n  = 474) of the samples were in the deceased group and were labeled 1.

Data balancing

In case–control studies, it is common to have unequal size groups since cases are typically fewer than controls [ 31 ]. However, in case–control studies with equal sizes, data balancing may not be necessary for ML algorithms [ 32 ]. When using ML algorithms, data balancing is generally important when there is an imbalance between classes, i.e., when one class has significantly fewer observations than the other [ 33 ]. In such cases, balancing can improve the performance of the algorithm by reducing the bias in favor of the majority class [ 34 ]. For case–control studies of the same size, the balance of the classes has already been reached and balancing may not be necessary. However, it is always recommended to evaluate the performance of the ML algorithm with the given data set to determine the need for data balancing. This is because unbalanced case–control ratios can cause inflated type I error rates and deflated type I error rates in balanced studies [ 35 ].

Feature selection

Feature selection is about selecting important variables from a large dataset to be used in a ML model to achieve better performance and efficiency. Another goal of feature selection is to reduce computational effort by eliminating irrelevant or redundant features [ 36 , 37 ]. Before generating predictions, it is important to perform feature selection to improve the accuracy of clinical decisions and reduce errors [ 37 ]. To identify the best predictors, researchers often compare the effectiveness of different feature selection methods. In this study, we used five common methods, including Decision Tree (DT), eXtreme Gradient Boosting (XGBoost), Support Vector Machine (SVM), Naïve Bayes (NB), and Random Forest (RF), to select relevant features for predicting mortality of COVID -19 patients. To avoid overfitting, we performed ten-fold cross-validation when training our dataset. This approach may help ensure that our model is optimized for accurate predictions of health status in COVID -19 patients.

Model development, evaluation, and clarity

In this study, the predictive models were developed with five ML algorithms, including DT, XGBoost, SVM, NB, and RF, using the R programming language (v4.3.1) and its packages [ 38 ]. We used cross-validation (CV) to tune the hyperparameters of our models based on the training subset of the dataset. For training and evaluating our ML models, we used a common technique called tenfold cross validation [ 39 ]. The primary training dataset was divided into ten folding, each containing 10% of the total data, using a technique called stratified random sampling. For each of the 30% of the data, a ML model was built and trained on the remaining 70% of the data. The performance of the model was then evaluated on the 30%-fold sample. This process was repeated 100 times with different training and test combinations, and the average performance was reported.

Performance measures include sensitivity (recall), specificity, accuracy, F1-score, and the area under the receiver operating characteristics curve (AUC ROC). Sensitivity is defined as TP / (TP + FN), whereas specificity is TN / (TN + FP). F1-score is defined as the harmonic mean of Precision and Recall with equal weight, where Precision equals TP + TN / total. Also, AUC refers to the area under the ROC curve. In the evaluation of ML techniques, values were classified as poor if below 50%, ok if between 50 and 80%, good if between 80 and 90%, and very good if greater than 90%. These criteria are commonly used in reporting model evaluations [ 40 , 41 ].

Finally, the shapely additive explanation (SHAP) method was used to provide clarity and understanding of the models. SHAP uses cooperative game theory to determine how each feature contributes to the prediction of ML models. This approach allows the computation of the contribution of each feature to model performance [ 42 , 43 ]. For this purpose, the package shapr was used, which includes a modified iteration of the kernel SHAP approach that takes into account the interdependence of the features when computing the Shapley values [ 44 ].

Patient characteristics

Table 1 shows the baseline characteristics of patients infected with COVID-19, including demographic data such as age and sex and other factors such as occupation, place of residence, marital status, education level, BMI, and season of admission. A total of 1063 adult patients (≥ 18 years) were enrolled in the study, of whom 589 (55.41%) survived and 474 (44.59%) died. Analysis showed that age was significantly different between the two groups, with a mean age of 54.70 ± 15.60 in the survivor group versus 65.53 ± 15.18 in the deceased group ( P  < 0.001). There was also a significant association between age and survival, with a higher proportion of patients aged < 40 years in the survivor group (77.0%) than in the deceased group (23.0%) ( P  < 0.001). No significant differences were found between the two groups in terms of sex, occupation, place of residence, marital status, and time of admission. However, there was a significant association between educational level and survival, with a lower proportion of patients with a college degree in the deceased group (37.2%) than in the survivor group (62.8%) ( P  = 0.017). BMI also differed significantly between the two groups, with the proportion of patients with a BMI > 30 (kg/cm 2 ) being higher in the deceased group (56.5%) than in the survivor group (43.5%) ( P  < 0.001).

Clinical and conditions

Important insights into the various clinical and condition characteristics associated with COVID-19 infection outcomes provides in Table  2 . The results show that patients who survived the infection had a significantly shorter hospitalization time (2.20 ± 1.63 days) compared to those who died (4.05 ± 3.10 days) ( P  < 0.001). Patients who were admitted as elective cases had a higher survival rate (84.6%) compared to those who were admitted as urgent (61.3%) or emergency (47.4%) cases. There were no significant differences with regard to the number of infections or family infection history. However, patients who had a history of travel had a lower decease rate (40.1%).

A significantly higher proportion of deceased patients had cases requiring CPR (54.7% vs. 45.3%). Patients who had underlying medical conditions had a significantly lower survival rate (38.3%), with hyperlipidemia being the most prevalent condition (18.7%). Patients who had a history of alcohol consumption (12.5%), transplantation (30.0%), chemotropic (21.4%) or special drug use (0.0%), and immunosuppressive drug use (30.0%) also had a lower survival rate. Pregnant patients (44.4%) had similar survival outcomes compared to non-pregnant patients (55.6%). Patients who were recent or current smokers (36.4%) also had a significantly lower survival rate.

Comorbidities

Table 3 summarizes the comorbidity characteristics of COVID-19 infected patients. Out of 1063 patients, 54.84% had comorbidities. Chi-Square tests for individual comorbidities showed that most of them had a significant association with COVID-19 outcomes, with P -values less than 0.05. Among the various comorbidities, hypertension (HTN) and diabetes mellitus (DM) were the most prevalent, with 12% and 11.5% of patients having these conditions, respectively. The highest fatality rates were observed among patients with cardiovascular disease (95.5%), chronic kidney disease (62.5%), gastrointestinal (GI) (93.3%), and liver diseases (73.3%). Conversely, patients with neurology comorbidities had the lowest fatality rate (0%). These results highlight the significant role of comorbidities in COVID-19 outcomes and emphasize the need for special attention to be paid to patients with pre-existing health conditions.

The treatment characteristics of the COVID-19 patients and the resulting outcomes are shown in Table  4 . The table shows the frequency of patients who received different types of medications or therapies during their treatment. According to the results, the use of antibiotics (35.1%), remdesivir (29.6%), favipiravir (36.0%), and Vitamin zinc (33.5%) was significantly associated with a lower mortality rate ( P  < 0.001), suggesting that these medications may have a positive impact on patient outcomes. On the other hand, the use of Heparin (66.1%), Insulin (82.6%), Antifungal (89.6%), ACE inhibitors (78.1%), and Angiotensin II Receptor Blockers (ARB) (83.8%) was significantly associated with increased mortality ( P  < 0.001), suggesting that these medications may have a negative effect on the patient's outcome. Also, It seems that taking hydroxychloroquine (51.0%) is associated with a worse outcome at lower significance ( P  = 0.022). The use of Atrovent, Corticosteroids and Non-Steroidal Anti-Inflammatory Drugs (NSAIDs) did not show a significant association with survival or mortality rates. Similarly, the use of Intravenous Immunoglobulin (IVIg), Vitamin C, Vitamin D, and Diuretic did not show a significant association with the patient’s outcome.

Initial vital signs

Table 5 provides initial vital sign characteristics of COVID-19 patients, including heart rate, respiratory rate, temperature, blood pressure, oxygen therapy, and radiography test result. The findings shows that deceased patients had higher HR (83.03 bpm vs. 76.14 bpm, P  < 0.001), lower RR (11.40 bpm vs. 16.25 bpm, P  < 0.001), higher temperature (37.43 °C vs. 36.91 °C, P  < 0.001), higher SBP (128.16 mmHg vs. 123.33 mmHg, P  < 0.001), and higher O 2 requirements (invasive: 75.0% vs. 25.0%, P  < 0.001) compared to the survived patients. Additionally, deceased patients had higher MAP (99.35 mmHg vs. 96.08 mmHg, P  = 0.005), and lower SPO 2 percentage (81.29% vs. 91.95%, P  < 0.001) compared to the survived patients. Furthermore, deceased patients had higher PEEP levels (5.83 cmH2O vs. 0.69 cmH2O, P  < 0.001), higher FiO2 levels (51.43% vs. 8.97%, P  < 0.001), and more frequent bilateral pneumonia (63.0% vs. 37.0%, P  < 0.001) compared to the survived patients. There appears to be no relationship between diastolic blood pressure and treatment outcome (83.44 mmHg vs. 85.61 mmHg).

Table 6 provides information on the symptoms of patients infected with COVID-19 by survival outcome. The table also shows the frequency of symptoms among patients. The most common symptom reported by patients was fever, which occurred in 67.0% of surviving and deceased patients. Dyspnea and nonproductive cough were the second and third most common symptoms, reported by 40.4% and 29.3% of the total sample, respectively. Other common symptoms listed in the Table were malodor (28.7%), dyspepsia (28.4%), and myalgia (25.6%).

The P -values reported in the table show that some symptoms are significantly associated with death, including productive cough, dyspnea, sore throat, headache, delirium, olfactory symptoms, dyspepsia, nausea, vomiting, sepsis, respiratory failure, heart failure, MODS, coagulopathy, secondary infection, stroke, acidosis, and admission to the intensive care unit. Surviving and deceased patients also differed significantly in the average number of days spent in the ICU. There was no significant association between patient outcomes and symptoms such as nonproductive cough, chills, diarrhea, chest pain, and hyperglycemia.

Laboratory tests

Table 7 shows the laboratory values of COVID-19 patients with the average values of the different laboratory results. The results show that the deceased patients had significantly lower levels of red blood cells (3.78 × 106/µL vs. 5.01 × 106/µL), hemoglobin (11.22 g/dL vs. 14.10 g/dL), and hematocrit (34.10% vs. 42.46%), whereas basophils and white blood cells did not differ significantly between the two groups. The percentage of neutrophils (65.59% vs. 62.58%) and monocytes (4.34% vs. 3.93%) was significantly higher in deceased patients, while the percentage of lymphocytes and eosinophils did not differ significantly between the two groups. In addition, deceased patients had higher levels of certain biomarkers, including D-dimer (1.347 mgFEU/L vs. 0.155 mgFEU/L), lactate dehydrogenase (174.61 U/L vs. 128.48 U/L), aspartate aminotransferase (93.09 U/L vs. 39.63 U/L), alanine aminotransferase (74.48 U/L vs. 28.70 U/L), alkaline phosphatase (119.51 IU/L vs. 81.34 IU/L), creatine phosphokinase-MB (4.65 IU/L vs. 3.33 IU/L), and positive troponin I (56.5% vs. 43.5%). The proportion of patients with positive C-reactive protein was also higher in the deceased group.

Other laboratory values with statistically significant differences between the two groups ( P  < 0.001) were INR, ESR, BUN, Cr, Na, K, P, PLT, TSH, T3, and T4. The surviving patients generally had lower values in these laboratory characteristics than the deceased patients.

Model performance and evaluation

Five ML algorithms, namely DT, XGBoost, SVM, NB, and RF, were used in this study to build mortality prediction models COVID -19. The models were based on the optimal feature set selected in a previous step and were trained on the same data set. The effectiveness of the models was evaluated by calculating sensitivity, specificity, accuracy, F1 score, and AUC metrics. Table 8 shows the results of this performance evaluation. The average values are expressed from the test set as the mean (standard deviation).

The results show that the performance of the models varies widely in the different feature categories. The Laboratory Tests category achieved the highest performance, with all models scoring 100% in all metrics. The Symptoms and initial Vital Signs categories also show high performance, with XGBoost achieving the highest accuracy of 98.03% and DT achieving the highest sensitivity of 92.79%.

The Clinical and Conditions category also showed high performance, with all models showing accuracy above 91%. XGBoost achieved the highest sensitivity and specificity of 92.74% and 92.96%, respectively. In contrast, the Demographics category showed the lowest performance, with all models achieving less than 66.5% accuracy.

In summary, the results suggest that certain feature categories may be more useful than others in predicting mortality from COVID-19 and that some ML models may perform better than others depending on the feature category used.

Feature importance

SHapley Additive exPlanations (SHAP) values indicate the importance or contribution of each feature in predicting model output. These values help to understand the influence and importance of each feature on the model's decision-making process.

In Fig.  2 , the mean absolute SHAP values are shown to depict global feature importance. Figure  2 shows the contribution of each feature within its respective group as calculated by the XGBoost prediction model using SHAP. According to the SHAP method, the features that had the greatest impact on predicting COVID-19 mortality were, in descending order: D-dimer, CPR, PEEP, underlying disease, ESR, antifungal treatment, PaO2, age, dyspnea, and nausea.

Feature importance based on SHAP-values. The mean absolute SHAP values are depicted, to illustrate global feature importance. The SHAP values change in the spectrum from dark (higher) to light (lower) color

On the other hand, Fig.  3 presents the local explanation summary that indicates the direction of the relationship between a variable and COVID-19 outcome. As shown in Fig.  3 (I to VII), older age and very low BMI were the two demographic factors with the greatest impact on model outcome, followed by clinical factors such as higher CPR, hospitalization, and hyperlipidemia. Higher mortality rates were associated with patients who smoked and had traveled in the past 14 days. Patients with underlying diseases, especially HTN, died more frequently. In contrast, the use of remdesivir, Vit Zn, and favipiravir is associated with lower mortality. Initial vital signs such as high PEEP, low PaO2 and RR had the greatest impact, as did symptoms such as dyspnea, MODS, sore throat and LOC. A higher risk of mortality is observed in patients with higher D-dimer levels and ESR as the most consequential laboratory tests, followed by K, AST and CPK-MB.

The SHAP-based feature importance of all categories (I to VII) for COVID‑19 mortality prediction, calculated with the XGBoost model. The local explanatory summary shows the direction of the relationship between a feature and patient outcome. Positive SHAP values indicate death, whereas negative SHAP values indicate survival. As the color scale shows, higher values are blue while lower values are orenge

Using the feature types listed in Appendix Table  1 , Fig.  4 shows that the performance of ML algorithms can be improved by increasing the number of features used in training, especially in distinguishing between symptoms, comorbidities, and treatments. In addition, the amount and quality of data used for training can significantly affect algorithm performance, with laboratory tests being more informative than initial vital signs. Regarding the influence of features, quantitative features tend to have a more positive effect on performance than qualitative features; clinical conditions tend to be more informative than demographic data. Thus, both the amount of data and the type of features used have a significant impact on the performance of ML algorithms.

Association between feature sets and performance of machine learning algorithms in predicting COVID-19’s mortality

The COVID-19 pandemic has presented unprecedented public health challenges worldwide and requires a deep understanding of the factors contributing to COVID-19 mortality to enable effective management and intervention. This study used machine learning analysis to uncover the predictive power of an extensive dataset that includes wide range of personal, clinical, preclinical, and laboratory variables associated with COVID-19 mortality.

This study confirms previous research on COVID-19 outcomes that highlighted age as a significant predictor of mortality [ 45 , 46 , 47 ], along with comorbidities such as hypertension and diabetes [ 48 , 49 ]. Underlying conditions such as cardiovascular and renal disease also contribute to mortality risk [ 50 , 51 ].

Regarding treatment, antibiotics, remdesivir, favipiravir, and vitamin zinc are associated with lower mortality [ 52 , 53 ], whereas heparin, insulin, antifungals, ACE, and ARBs are associated with higher mortality [ 54 ]. This underscores the importance of drug choice in COVID -19 treatment.

Initial vital signs such as heart rate, respiratory rate, temperature, and oxygen therapy differ between surviving and deceased patients [ 55 ]. Deceased patients often have increased heart rate, lower respiratory rate, higher temperature, and increased oxygen requirements, which can serve as early indicators of disease severity.

Symptoms such as productive cough, dyspnea, and delirium are significantly associated with COVID-19 mortality, emphasizing the need for immediate monitoring and intervention [ 56 ]. Laboratory tests show altered hematologic and biochemical markers in deceased patients, underscoring the importance of routine laboratory monitoring in COVID-19 patients [ 57 , 58 ].

The ML algorithms were used in the study to predict mortality COVID-19 based on these multilayered variables. XGBoost and Random Forest performed better than other algorithms and had high recall, specificity, accuracy, F1 score, and AUC. This highlights the potential of ML, particularly the XGBoost algorithm, in improving prediction accuracy for COVID-19 mortality [ 59 ]. The study also highlighted the importance of drug choice in treatment and the potential of ML algorithms, particularly XGBoost, in improving prediction accuracy. However, the study's findings differ from those of Moulaei [ 60 ], Nopour [ 61 ], and Mehraeen [ 62 ] in terms of the best-performing ML algorithm and the most influential variables. While Moulaei [ 60 ] found that the random forest algorithm had the best performance, Nopour [ 61 ] and Ikemura [ 63 ] identified the artificial neural network and stacked ensemble models, respectively, as the most effective. Additionally, the most influential variables in predicting mortality varied across the studies, with Moulaei [ 60 ] highlighting dyspnea, ICU admission, and oxygen therapy, and Ikemura [ 63 ] identifying systolic and diastolic blood pressure, age, and other biomarkers. These differences may be attributed to variations in the datasets, feature selection, and model training.

However, it is important to note that the choice of algorithm should be tailored to the specific dataset and research question. In addition, the results suggest that a comprehensive approach that incorporates different feature categories may lead to more accurate prediction of COVID-19 mortality. In general, the results suggest that the performance of ML models is influenced by the number and type of features in each category. While some models consistently perform well across different categories (e.g., XGBoost), others perform better for specific types of features (e.g., SVM for Demographics).

Analysis of the importance of characteristics using SHAP values revealed critical factors affecting model results. D-dimer values, CPR, PEEP, underlying diseases, and ESR emerged as the most important features, highlighting the importance of these variables in predicting COVID-19 mortality. These results provide valuable insights into the underlying mechanisms and risk factors associated with severe COVID-19 outcomes.

The types of features used in ML models fall into two broad categories: quantitative (numerical) and qualitative (binary or categorical). The performance of ML methods can vary depending on the type of features used. Some algorithms work better with quantitative features, while others work better with qualitative features. For example, decision trees and random forests work well with both types of features [ 64 ], while neural networks often work better with quantitative features [ 65 , 66 ]. Accordingly, we consider these levels for the features under study to better assess the impact of the data.

The success of ML algorithms depends largely on the quality and quantity of the data on which they are trained [ 67 , 68 , 69 ]. Recent research, including the 2021 study by Sarker IH. [ 26 ], has shown that a larger amount of data can significantly improve the performance of deep learning algorithms compared to traditional machine learning techniques. However, it should be noted that the effect of data size on model performance depends on several factors, such as data characteristics and experimental design. This underscores the importance of carefully and judiciously selecting data for training.

Limitations

One of the limitations of this study is that it relies on data collected from a single hospital in Abadan, Iran. The data may not be representative of the diversity of COVID -19 cases in different regions, and there may be differences in data quality and completeness. In addition, retrospectively collected data may have biases and inaccuracies. Although the study included a substantial number of COVID -19 patients, the sample size may still limit the generalizability of the results, especially for less common subgroups or certain demographic characteristics.

Future works

Future studies could adopt a multi-center approach to improve the scope and depth of research on COVID-19 outcomes. This could include working with multiple hospitals in different regions of Iran to ensure a more diverse and representative sample. By conducting prospective studies, researchers can collect data in real time, which reduces the biases associated with retrospective data collection and increases the reliability of the results. Increasing sample size, conducting longitudinal studies to track patient progression, and implementing quality assurance measures are critical to improving generalizability, understanding long-term effects, and ensuring data accuracy in future research efforts. Collectively, these strategies aim to address the limitations of individual studies and make an important contribution to a more comprehensive understanding of COVID-19 outcomes in different populations and settings.

Conclusions

In summary, this study demonstrates the potential of ML algorithms in predicting COVID-19 mortality based on a comprehensive set of features. In addition, the interpretability of the models using SHAP-based feature importance, which revealed the variables strongly correlated with mortality. This study highlights the power of data-driven approaches in addressing critical public health challenges such as the COVID-19 pandemic. The results suggest that the performance of ML models is influenced by the number and type of features in each feature set. These findings may be a valuable resource for health professionals to identify high-risk patients COVID-19 and allocate resources effectively.

Availability of data and materials

The datasets used and/or analyzed during the current study are available from the corresponding author on reasonable request.

Abbreviations

World Health Organization

Middle east respiratory syndrome

Severe acute respiratory syndrome

Reverse transcription polymerase chain reaction

Propensity score matching

Synthetic minority over-sampling technique

Missing completely at random

Decision tree

EXtreme gradient boosting

Support vector machine

Naïve bayes

Random forest

Cross-validation

True positive

True negative

False positive

False negative

• Machine learning

Artificial Intelligence

Shapely additive explanation

Cardiopulmonary Resuscitation

Hypertension

Diabetes mellitus

Cardiovascular disease

Chronic Kidney disease

Chronic obstructive pulmonary disease

Human immunodeficiency virus

Hepatitis B virus

Such as influenza, pneumonia, asthma, bronchitis, and chronic obstructive airways disease

Gastrointestinal

Such as epilepsy, learning disabilities, neuromuscular disorders, autism, ADD, brain tumors, and cerebral palsy

Such as fatty liver disease and cirrhosis

Blood disease

Skin diseases

Mental disorders

Intravenous immunoglobulin

Non-steroidal anti-Inflammatory drugs

Angiotensin converting enzyme inhibitors

Angiotensin II receptor blockers

Beats per minute

Respiratory rate

Temperatures

Systolic blood pressure

Diastolic blood pressure

Mean arterial pressure

Oxygen saturation

Partial pressure of oxygen in the alveoli

Positive end-expiratory pressure

Fraction of inspired oxygen

Radiography (X-ray) test result

Smell disorders

Indigestion

Level of consciousness

Multiple organ dysfunction syndrome

Coughing up blood; Coagulopathy: bleeding disorder

High blood glucose

Intensive care unit

Red blood cell

White blood cell

Low-density lipoprotein

High-density lipoprotein

Prothrombin time

Partial thromboplastin time

International normalized ratio

Erythrocyte sedimentation rate

C-reactive-protein

Lactate dehydrogenase

Aspartate aminotransferase

Alanine aminotransferase

Alkaline phosphatase

Creatine phosphokinase-MB

Blood urea nitrogen

Thyroid stimulating hormone

Triiodothyronine

Coronavirus disease (COVID-19) pandemic. Available from: https://www.who.int/europe/emergencies/situations/covid-19 . [cited 2023 Sep 5].

Moolla I, Hiilamo H. Health system characteristics and COVID-19 performance in high-income countries. BMC Health Serv Res. 2023;23(1):1–14. https://doi.org/10.1186/s12913-023-09206-z . [cited 2023 Sep 5].

Article   Google Scholar  

Peeri NC, Shrestha N, Rahman MS, Zaki R, Tan Z, Bibi S, et al. The SARS, MERS and novel coronavirus (COVID-19) epidemics, the newest and biggest global health threats: what lessons have we learned? Int J Epidemiol. 2020;49(3):717–26.

Article   PubMed   Google Scholar  

WHO Coronavirus (COVID-19) Dashboard | WHO Coronavirus (COVID-19) Dashboard With Vaccination Data. Available from: https://covid19.who.int/ . [cited 2023 Sep 5].

Dessie ZG, Zewotir T. Mortality-related risk factors of COVID-19: a systematic review and meta-analysis of 42 studies and 423,117 patients. BMC Infect Dis. 2021;21(1):1–28. https://doi.org/10.1186/s12879-021-06536-3 . [cited 2023 Sep 5].

Article   CAS   Google Scholar  

Wong ELY, Ho KF, Wong SYS, Cheung AWL, Yau PSY, Dong D, et al. Views on Workplace Policies and its Impact on Health-Related Quality of Life During Coronavirus Disease (COVID-19) Pandemic: Cross-Sectional Survey of Employees. Int J Heal Policy Manag. 2022;11(3):344–53. Available from: https://www.ijhpm.com/article_3879.html .

Google Scholar  

Drefahl S, Wallace M, Mussino E, Aradhya S, Kolk M, Brandén M, et al. A population-based cohort study of socio-demographic risk factors for COVID-19 deaths in Sweden. Nat Commun. 2020;11(1):5097.

Article   CAS   PubMed   PubMed Central   Google Scholar  

Islam N, Khunti K, Dambha-Miller H, Kawachi I, Marmot M. COVID-19 mortality: a complex interplay of sex, gender and ethnicity. Eur J Public Health. 2020;30(5):847–8.

Sarmadi M, Marufi N, Moghaddam VK. Association of COVID-19 global distribution and environmental and demographic factors: An updated three-month study. Environ Res. 2020;188:109748.

Aghazadeh-Attari J, Mohebbi I, Mansorian B, Ahmadzadeh J, Mirza-Aghazadeh-Attari M, Mobaraki K, et al. Epidemiological factors and worldwide pattern of Middle East respiratory syndrome coronavirus from 2013 to 2016. Int J Gen Med. 2018;11:121–5.

Risk of COVID-19-Related Mortality. Available from: https://www.cdc.gov/coronavirus/2019-ncov/science/data-review/risk.html . [cited 2023 Aug 26].

Bhaskaran K, Bacon S, Evans SJW, Bates CJ, Rentsch CT, MacKenna B, et al. Factors associated with deaths due to COVID-19 versus other causes: population-based cohort analysis of UK primary care data and linked national death registrations within the OpenSAFELY platform. Lancet Reg Heal. 2021;6:100-9.

Dessie ZG, Zewotir T. Mortality-related risk factors of COVID-19: a systematic review and meta-analysis of 42 studies and 423,117 patients. BMC Infect Dis. 2021;21(1):855. https://doi.org/10.1186/s12879-021-06536-3 .

Talebi SS, Hosseinzadeh A, Zare F, Daliri S, JamaliAtergeleh H, Khosravi A, et al. Risk Factors Associated with Mortality in COVID-19 Patient’s: Survival Analysis. Iran J Public Health. 2022;51(3):652–8.

PubMed   PubMed Central   Google Scholar  

Singh J, Alam A, Samal J, Maeurer M, Ehtesham NZ, Chakaya J, et al. Role of multiple factors likely contributing to severity-mortality of COVID-19. Infect Genet Evol J Mol Epidemiol Evol Genet Infect Dis. 2021;96:105101.

CAS   Google Scholar  

Bhaskaran K, Bacon S, Evans SJ, Bates CJ, Rentsch CT, MacKenna B, et al. Factors associated with deaths due to COVID-19 versus other causes: population-based cohort analysis of UK primary care data and linked national death registrations within the OpenSAFELY platform. Lancet Reg Heal - Eur. 2021;6:100109. Available from:  https://www.pmc/articles/PMC8106239/ . [cited 2023 Aug 26].

Ge E, Li Y, Wu S, Candido E, Wei X. Association of pre-existing comorbidities with mortality and disease severity among 167,500 individuals with COVID-19 in Canada: A population-based cohort study. PLoS One. 2021;16(10):e0258154. https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0258154 . [cited 2023 Aug 26].

Tian S, Liu H, Liao M, Wu Y, Yang C, Cai Y, et al. Analysis of mortality in patients with COVID-19: clinical and laboratory parameters. Open Forum Infect Dis. 2020;7(5). Available from:  https://dx.doi.org/10.1093/ofid/ofaa152 . [cited 2023 Aug 26].

Rashidi HH, Tran N, Albahra S, Dang LT. Machine learning in health care and laboratory medicine: General overview of supervised learning and Auto-ML. Int J Lab Hematol. 2021;43:15–22.

Najafi-Vosough R, Faradmal J, Hosseini SK, Moghimbeigi A, Mahjub H. Predicting hospital readmission in heart failure patients in Iran: a comparison of various machine learning methods. Healthc Inform Res. 2021;27(4):307–14.

Article   PubMed   PubMed Central   Google Scholar  

Alanazi A. Using machine learning for healthcare challenges and opportunities. Informatics Med Unlocked. 2022;100924:1–5.

Chadaga K, Prabhu S, Sampathila N, Chadaga R, Umakanth S, Bhat D, et al. Explainable artificial intelligence approaches for COVID-19 prognosis prediction using clinical markers. Sci Rep. 2024;14(1):1783.

Chadaga K, Prabhu S, Bhat V, Sampathila N, Umakanth S, Chadaga R, et al. An explainable multi-class decision support framework to predict COVID-19 prognosis utilizing biomarkers. Cogent Eng. 2023;10(2):2272361.

Khanna VV, Chadaga K, Sampathila N, Prabhu S, Chadaga R. A machine learning and explainable artificial intelligence triage-prediction system for COVID-19. Decis Anal J. 2023;100246:1–14.

Zoabi Y, Deri-Rozov S, Shomron N. Machine learning-based prediction of COVID-19 diagnosis based on symptoms. npj Digit Med. 2021;4(1):1–5.

IH Sarker 2021 Machine Learning: Algorithms, Real-World Applications and Research Directions SN Comput Sci. 2 3 160 Available from: https://doi.org/10.1007/s42979-021-00592-x .

Jones JA, Farnell B. Missing and Incomplete Data Reduces the Value of General Practice Electronic Medical Records as Data Sources in Research. Aust J Prim Health. 2007;13(1):74–80. Available from: https://www.publish.csiro.au/py/py07010 . [cited 2023 Dec 16].

Austin PC. An Introduction to Propensity Score Methods for Reducing the Effects of Confounding in Observational Studies. Multivariate Behav Res. 2011;46(3):399–424.

Torjusen H, Lieblein G, Næs T, Haugen M, Meltzer HM, Brantsæter AL. Food patterns and dietary quality associated with organic food consumption during pregnancy; Data from a large cohort of pregnant women in Norway. BMC Public Health. 2012;12(1):1–11.

Little RJA. A test of missing completely at random for multivariate data with missing values. J Am Stat Assoc. 1988;83(404):1198–202.

Tenny S, Kerndt CC, Hoffman MR. Case Control Studies. Encycl Pharm Pract Clin Pharm Vol 1-3 [Internet]. 2023;1–3:V2-356-V2-366. [cited 2024 Apr 14] Available from: https://www.ncbi.nlm.nih.gov/books/NBK448143/ .

Stanfill B, Reehl S, Bramer L, Nakayasu ES, Rich SS, Metz TO, et al. Extending Classification Algorithms to Case-Control Studies. Biomed Eng Comput Biol. 2019;10:117959721985895. Available from: https://www.pmc/articles/PMC6630079/ .[cited 2023 Sep 3].

Mulugeta G, Zewotir T, Tegegne AS, Juhar LH, Muleta MB. Classification of imbalanced data using machine learning algorithms to predict the risk of renal graft failures in Ethiopia. BMC Med Inform Decis Mak. 2023;23(1):1–17. https://bmcmedinformdecismak.biomedcentral.com/articles/10.1186/s12911-023-02185-5 . [cited 2023 Sep 3].

Sadeghi S, Khalili D, Ramezankhani A, Mansournia MA, Parsaeian M. Diabetes mellitus risk prediction in the presence of class imbalance using flexible machine learning methods. BMC Med Inform Decis Mak. 2022;22(1):36. https://doi.org/10.1186/s12911-022-01775-z .

Zhou W, Nielsen JB, Fritsche LG, Dey R, Gabrielsen ME, Wolford BN, et al. Efficiently controlling for case-control imbalance and sample relatedness in large-scale genetic association studies. Nat Genet. 2018;50(9):1335. Available from:  https://www.pmc/articles/PMC6119127/ . [cited 2023 Sep 3].

Miao J, Niu L. A Survey on Feature Selection. Procedia Comput Sci. 2016;91(1):919–26.

Remeseiro B, Bolon-Canedo V. A review of feature selection methods in medical applications. Comput Biol Med. 2019;112:103375.

Article   CAS   PubMed   Google Scholar  

R Studio Team. A language and environment for statistical computing. R Found Stat Comput. 2021;1.

Training Sets, Test Sets, and 10-fold Cross-validation - KDnuggets. Available from: https://www.kdnuggets.com/2018/01/training-test-sets-cross-validation.html . [cited 2023 Sep 4].

Hossin M, Sulaiman MN. A review on evaluation metrics for data classification evaluations. Int J data Min Knowl Manag Process. 2015;5(2):1.

Seyedtabib M, Kamyari N. Predicting polypharmacy in half a million adults in the Iranian population: comparison of machine learning algorithms. BMC Med Inform Decis Mak. 2023;23(1):84. https://doi.org/10.1186/s12911-023-02177-5 .

Lundberg SM, Lee S-I. A unified approach to interpreting model predictions. Adv Neural Inf Process Syst. 2017;30:4765–74.

Greenwell B. Fastshap: Fast approximate shapley values. Man R Packag v0 05. 2020;9–12.  https://www.CRANR-projectorg/package=fastshap . Last accessed.

Aas K, Jullum M, Løland A. Explaining individual predictions when features are dependent: More accurate approximations to Shapley values. Artif Intell. 2021;298:103502.

Mesas AE, Cavero-Redondo I, Álvarez-Bueno C, Sarriá Cabrera MA, de Maffei Andrade S, Sequí-Dominguez I, et al. Predictors of in-hospital COVID-19 mortality: A comprehensive systematic review and meta-analysis exploring differences by age, sex and health conditions. PLoS One. 2020;15(11):e0241742.

Yanez ND, Weiss NS, Romand J-A, Treggiari MM. COVID-19 mortality risk for older men and women. BMC Public Health. 2020;20(1):1–7.

Sasson I. Age and COVID-19 mortality. Demogr Res. 2021;44:379–96.

Huang I, Lim MA, Pranata R. Diabetes mellitus is associated with increased mortality and severity of disease in COVID-19 pneumonia–a systematic review, meta-analysis, and meta-regression. Diabetes Metab Syndr Clin Res Rev. 2020;14(4):395–403.

Albitar O, Ballouze R, Ooi JP, Ghadzi SMS. Risk factors for mortality among COVID-19 patients. Diabetes Res Clin Pract. 2020;166:108293.

Di Castelnuovo A, Bonaccio M, Costanzo S, Gialluisi A, Antinori A, Berselli N, et al. Common cardiovascular risk factors and in-hospital mortality in 3,894 patients with COVID-19: survival analysis and machine learning-based findings from the multicentre Italian CORIST Study. Nutr Metab Cardiovasc Dis. 2020;30(11):1899–913.

Ssentongo P, Ssentongo AE, Heilbrunn ES, Ba DM, Chinchilli VM. Association of cardiovascular disease and 10 other pre-existing comorbidities with COVID-19 mortality: A systematic review and meta-analysis. PLoS ONE. 2020;15(8):e0238215.

Beran A, Mhanna M, Srour O, Ayesh H, Stewart JM, Hjouj M, et al. Clinical significance of micronutrient supplements in patients with coronavirus disease 2019: A comprehensive systematic review and meta-analysis. Clin Nutr ESPEN. 2022;48:167–77.

Perveen RA, Nasir M, Murshed M, Nazneen R, Ahmad SN. Remdesivir and favipiravir changes hepato-renal profile in COVID-19 patients: a cross sectional observation in Bangladesh. Int J Med Sci Clin Inven. 2021;8(1):5196–201.

El-Arif G, Khazaal S, Farhat A, Harb J, Annweiler C, Wu Y, et al. Angiotensin II Type I Receptor (AT1R): the gate towards COVID-19-associated diseases. Molecules. 2022;27(7):2048.

Ikram AS, Pillay S. Admission vital signs as predictors of COVID-19 mortality: a retrospective cross-sectional study. BMC Emerg Med. 2022;22(1):1–10.

Martí-Pastor A, Moreno-Perez O, Lobato-Martínez E, Valero-Sempere F, Amo-Lozano A, Martínez-García M-Á, et al. Association between Clinical Frailty Scale (CFS) and clinical presentation and outcomes in older inpatients with COVID-19. BMC Geriatr. 2023;23(1):1.

Lippi G, Plebani M. Laboratory abnormalities in patients with COVID-2019 infection. Clin Chem Lab Med. 2020;58(7):1131–4.

Naghashpour M, Ghiassian H, Mobarak S, Adelipour M, Piri M, Seyedtabib M, et al. Profiling serum levels of glutathione reductase and interleukin-10 in positive and negative-PCR COVID-19 outpatients: A comparative study from southwestern Iran. J Med Virol. 2022;94(4):1457–64.

Sharifi-Kia A, Nahvijou A, Sheikhtaheri A. Machine learning-based mortality prediction models for smoker COVID-19 patients. BMC Med Inform Decis Mak. 2023;23(1):1–15.

Moulaei K, Shanbehzadeh M, Mohammadi-Taghiabad Z, Kazemi-Arpanahi H. Comparing machine learning algorithms for predicting COVID-19 mortality. BMC Med Inform Decis Mak. 2022;22(1):2. https://doi.org/10.1186/s12911-021-01742-0 .

Nopour R, Erfannia L, Mehrabi N, Mashoufi M, Mahdavi A, Shanbehzadeh M. Comparison of Two Statistical Models for Predicting Mortality in COVID-19 Patients in Iran. Shiraz E-Medical J 2022 236 [Internet]. 2022;23(6):119172. [cited 2024 Apr 14] Available from: https://brieflands.com/articles/semj-119172 .

Mehraeen E, Karimi A, Barzegary A, Vahedi F, Afsahi AM, Dadras O, et al. Predictors of mortality in patients with COVID-19–a systematic review. Eur J Integr Med. 2020;40:101226.

Ikemura K, Bellin E, Yagi Y, Billett H, Saada M, Simone K, et al. Using Automated Machine Learning to Predict the Mortality of Patients With COVID-19: Prediction Model Development Study. J Med Internet Res [Internet]. 2021;23(2):e23458. Available from: https://www.jmir.org/2021/2/e23458 .

Breiman L. Random forests. Mach Learn. 2001;45:5–32.

Hinton G, Srivastava N, Swersky K. Neural networks for machine learning lecture 6a overview of mini-batch gradient descent. Cited on. 2012;14(8):2.

Zheng A, Casari A. Feature Engineering for Machine Learning: Principles and Techniques for Data Scientists. O’Reilly [Internet]. 2018;218. [cited 2024 Apr 14] Available from: https://www.amazon.com/Feature-Engineering-Machine-Learning-Principles/dp/1491953241 .

Adamson AS, Smith A. Machine Learning and Health Care Disparities in Dermatology. JAMA Dermatology. 2018;154(11):1247–8. Available from:  https://jamanetwork.com/journals/jamadermatology/fullarticle/2688587 . [cited 2023 Sep 15].

Kavakiotis I, Tsave O, Salifoglou A, Maglaveras N, Vlahavas I, Chouvarda I. Machine Learning and Data Mining Methods in Diabetes Research. Comput Struct Biotechnol J. 2017;1(15):104–16.

Schmidt J, Marques MRG, Botti S, Marques MAL. Recent advances and applications of machine learning in solid-state materials science. Comput Mater. 2019;5(1):83. https://doi.org/10.1038/s41524-019-0221-0 .

Download references

Acknowledgements

We thank the Research Deputy of the Abadan University of Medical Sciences for financially supporting this project.

Summary points

∙ How can datasets improve mortality prediction using ML models for COVID-19 patients?

∙ In order, quantity and quality variables have more effect on the model performances.

∙ Intelligent techniques such as SHAP analysis can be used to improve the interpretability of features in ML algorithms.

∙ Well-structured data are critical to help health professionals identify at-risk patients and improve pandemic outcomes.

This research was supported by grant No. 1456 from the Abadan University of Medical Sciences. However, the funding source did not influence the study design, data collection, analysis and interpretation, report writing, or decision to publish the article.

Author information

Authors and affiliations.

Department of Biostatistics and Epidemiology, School of Health, Ahvaz Jundishapur University of Medical Sciences, Ahvaz, Iran

Maryam Seyedtabib

Research Center for Health Sciences, Hamadan University of Medical Sciences, Hamadan, Iran

Roya Najafi-Vosough

Department of Biostatistics and Epidemiology, School of Health, Abadan University of Medical Sciences, Abadan, Iran

Naser Kamyari

You can also search for this author in PubMed   Google Scholar

Contributions

MS: Conceptualization, Methodology, Validation, Formal analysis, Investigation, Resources, Data curation, Writing–original draft, writing—review & editing, Visualization, Project administration. RNV: Conceptualization, Data curation, Formal analysis, Investigation, Writing–original draft, writing—review & editing. NK: Conceptualization, Methodology, Software, Validation, Formal analysis, Investigation, Resources, Data curation, Writing–original draft, writing—review & editing, Visualization, Supervision.

Corresponding author

Correspondence to Naser Kamyari .

Ethics declarations

Ethics approval and consent to participate.

This study was approved by the Research Ethics Committee (REC) of Abadan University of Medical Sciences under the ID number IR.ABADANUMS.REC.1401.095. Methods used complied with all relevant ethical guidelines and regulations. The Ethics Committee of Abadan University of Medical Sciences waived the requirement for written informed consent from study participants.

Competing interests

The authors declare no competing interests.

Additional information

Publisher’s note.

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary Information

Supplementary material 1., rights and permissions.

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/ . The Creative Commons Public Domain Dedication waiver ( http://creativecommons.org/publicdomain/zero/1.0/ ) applies to the data made available in this article, unless otherwise stated in a credit line to the data.

Reprints and permissions

About this article

Cite this article.

Seyedtabib, M., Najafi-Vosough, R. & Kamyari, N. The predictive power of data: machine learning analysis for Covid-19 mortality based on personal, clinical, preclinical, and laboratory variables in a case–control study. BMC Infect Dis 24 , 411 (2024). https://doi.org/10.1186/s12879-024-09298-w

Download citation

Received : 22 December 2023

Accepted : 05 April 2024

Published : 18 April 2024

DOI : https://doi.org/10.1186/s12879-024-09298-w

Share this article

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative

• Predictive model
• Coronavirus disease
• Data quality
• Performance

BMC Infectious Diseases

ISSN: 1471-2334

• Submission enquiries: [email protected]
• General enquiries: [email protected]

Evidence Review of the Adverse Effects of COVID-19 Vaccination and Intramuscular Vaccine Administration

Vaccines are a public health success story, as they have prevented or lessened the effects of many infectious diseases. To address concerns around potential vaccine injuries, the Health Resources and Services Administration (HRSA) administers the Vaccine Injury Compensation Program (VICP) and the Countermeasures Injury Compensation Program (CICP), which provide compensation to those who assert that they were injured by routine vaccines or medical countermeasures, respectively. The National Academies of Sciences, Engineering, and Medicine have contributed to the scientific basis for VICP compensation decisions for decades.

HRSA asked the National Academies to convene an expert committee to review the epidemiological, clinical, and biological evidence about the relationship between COVID-19 vaccines and specific adverse events, as well as intramuscular administration of vaccines and shoulder injuries. This report outlines the committee findings and conclusions.

Read Full Description

• Digital Resource: Evidence Review of the Adverse Effects of COVID-19 Vaccination
• Digital Resource: Evidence Review of Shoulder Injuries from Intramuscular Administration of Vaccines
• Press Release

Recent News

NAS Launches Science and Innovation Fund for Ukraine

Science Academies Issue Statements to Inform G7 Talks

Supporting Family Caregivers in STEMM

A Vision for High-Quality Preschool for All

• Load More...