Creating Fair Models of Atherosclerotic Cardiovascular Disease Risk

Stephen Pfohl, Ben Marafino, Adrien Coulet, Fatima Rodriguez, Latha Palaniappan, Nigam H. Shah
2019 Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society - AIES '19  
Guidelines for the management of atherosclerotic cardiovascular disease (ASCVD) recommend the use of risk stratification models to identify patients most likely to benefit from cholesterollowering 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
more » ... 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. CCS CONCEPTS • Applied computing → Health informatics.
doi:10.1145/3306618.3314278 dblp:conf/aies/PfohlMCRPS19 fatcat:xhccq7pgxbajbj5quh7tlruioq