Journal
AIES '19: PROCEEDINGS OF THE 2019 AAAI/ACM CONFERENCE ON AI, ETHICS, AND SOCIETY
Volume -, Issue -, Pages 271-278Publisher
ASSOC COMPUTING MACHINERY
DOI: 10.1145/3306618.3314278
Keywords
electronic health records; fairness; cardiovascular disease; adversarial learning; risk prediction; machine learning
Categories
Funding
- National Science Foundation [DGE-1656518]
- NLM [RO1 LM011369-06, T15 LM007033]
- Widen Horizons program of the IDEX Lorraine Universit6 d'Excellence [15-IDEX-0004]
- Inria
Ask authors/readers for more resources
Guidelines for the management of atherosclerotic cardiovascular disease (ASCVD) recommend the use of risk stratification models to identify patients most likely to benefit from cholesterol-lowering and other therapies. These models have differential performance across race and gender groups with inconsistent behavior across studies, potentially resulting in an inequitable distribution of beneficial therapy. In this work, we leverage adversarial learning and a large observational cohort extracted from electronic health records (EHRs) to develop a fair ASCVD risk prediction model with reduced variability in error rates across groups. We empirically demonstrate that our approach is capable of aligning the distribution of risk predictions conditioned on the outcome across several groups simultaneously for models built from high-dimensional EHR data. We also discuss the relevance of these results in the context of the empirical trade-off between fairness and model performance.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available