Skip to Main Content
An official website of the United States government
Login Change: CDAS is now using the NIH Researcher Auth Service (RAS) to manage our existing login options. When logging into CDAS, you will be taken to RAS, where you can select your preferred login provider to access CDAS.

Assess positive-sum fairness of CXR classifiers leveraging demographic attributes

Principal Investigator

Name
Samia Belhadj

Degrees
M.D.

Institution
Lunit Inc.

Position Title
Data Scientist

Email
samia.belhadj@lunit.io

About this CDAS Project

Study
PLCO (Learn more about this study)

Project ID
PLCO-1490

Initial CDAS Request Approval
Feb 27, 2024

Title
Assess positive-sum fairness of CXR classifiers leveraging demographic attributes

Summary
We would like to study and discuss harmful vs non-harmful fairness on CXR classifiers. To do so, we want to train different classifiers which leverage or not demographic attributes ans compare their results.

Aims

- Study positive-sum fairness (harmful and non-harmful fairness)
- Study the impact of demographic attributes on the performance and fairness of a model

Collaborators

Sanguk Park (Lunit Inc.)
Samia Belhadj (Lunit Inc.)
Hesham Dar (Lunit Inc.)
Thijs Kooi (Lunit Inc.)