Making AI-Powered Mobile Health Apps Fair for Everyone
Achieve Fairness in AI-Assisted Mobile Healthcare Apps through Unsupervised Federated Learning
This project aims to create fair and accurate artificial intelligence for mobile health apps, like those used for skin condition diagnosis, so they work well for all users.
Quick facts
| Grant type | R01 grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | University of Pittsburgh at Pittsburgh NIH-funded |
| Lab location | 1 site (Pittsburgh, United States) |
| Project ID | NIH-11097212 on NIH RePORTER |
What this research studies
Many mobile health apps use artificial intelligence (AI) to help with things like diagnosing skin conditions. However, these AI tools sometimes don't work as well for everyone because they were trained on data that didn't represent all types of people. This project is developing a new way for these AI apps to learn directly from many different users, right on their devices, without sharing private information. This approach helps the AI continuously improve and become more reliable and accurate for a wider range of people, no matter where they live or their background.
Who could benefit from this research
Good fit: This research is foundational and does not directly recruit patients, but future mobile health app users, particularly those seeking dermatology diagnoses, could benefit.
Not a fit: Patients not using mobile health applications or those with conditions outside the scope of AI-assisted diagnosis may not directly benefit from this specific research.
Why it matters
Potential benefit: If successful, this work could lead to more accurate and trustworthy mobile health apps that provide consistent benefits to all patients, regardless of their background or location.
How similar studies have performed: While the concept of federated learning is gaining traction, applying it specifically to achieve fairness in mobile healthcare AI for diverse populations is a novel and actively developing area.
Where this research is happening
Pittsburgh, United States
- University of Pittsburgh at Pittsburgh — Pittsburgh, United States (Active)
Researchers
- Principal investigator: Hu, Jingtong — University of Pittsburgh at Pittsburgh
- Study coordinator: Hu, Jingtong
About this research
- This is an active NIH-funded research project — typically early-stage science, not a clinical trial accepting patient enrollment.
- Some NIH-funded labs run parallel clinical studies or seek volunteers for related work. To check, contact the principal investigator or institution listed above.
- For full project details, budget, and progress reports, visit the official NIH RePORTER page below.