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.)