aahmadnejad/BiasCXR

This repository is a debiassing project on CXR Dataset with embedding which is publicly available.

21
/ 100
Experimental

This project helps medical AI developers and researchers mitigate algorithmic bias in deep learning models trained on chest X-ray images. It takes raw chest X-ray data along with patient demographic information and applies intelligent sampling techniques. The output is a rebalanced dataset that leads to AI models with improved fairness across different patient groups while maintaining diagnostic accuracy.

No commits in the last 6 months.

Use this if you are developing AI models for medical imaging and are concerned about equitable performance across patient demographics like race, gender, age, or insurance status.

Not ideal if your dataset is not chest X-rays, or if you are not working with deep learning models for medical image classification.

medical-imaging-AI diagnostic-radiology healthcare-equity algorithmic-fairness medical-AI-development
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 4 / 25
Maturity 15 / 25
Community 0 / 25

How are scores calculated?

Stars

7

Forks

Language

Python

License

Last pushed

Apr 16, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/aahmadnejad/BiasCXR"

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