ys-zong/MEDFAIR

[ICLR 2023 spotlight] MEDFAIR: Benchmarking Fairness for Medical Imaging

35
/ 100
Emerging

This project helps medical researchers and practitioners evaluate if their AI models for medical imaging are fair across different demographic groups. It takes common medical image datasets and associated patient demographic data as input. The output helps users understand and compare how different fairness algorithms perform in reducing bias, ensuring AI models don't inadvertently disadvantage certain patient populations based on factors like age, sex, or race.

No commits in the last 6 months.

Use this if you are a medical researcher or data scientist building or evaluating AI models for medical image analysis and want to rigorously test and improve their fairness across diverse patient populations.

Not ideal if you are looking for a pre-trained, production-ready diagnostic tool or a general-purpose image analysis library unrelated to fairness benchmarking.

medical-imaging healthcare-AI diagnostic-fairness AI-ethics clinical-research
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 8 / 25
Community 18 / 25

How are scores calculated?

Stars

73

Forks

15

Language

Python

License

Last pushed

May 22, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/ys-zong/MEDFAIR"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.