1. Creating Fair Models of Atherosclerotic Cardiovascular Disease Risk
- Author
-
Fatima Rodriguez, Ben J. Marafino, Nigam H. Shah, Latha Palaniappan, Stephen R. Pfohl, Adrien Coulet, Stanford Center for BioMedical Informatics Research (BMIR), Stanford University, Knowledge representation, reasonning (ORPAILLEUR), Inria Nancy - Grand Est, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Department of Natural Language Processing & Knowledge Discovery (LORIA - NLPKD), Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS), Stanford School of Medicine [Stanford], Stanford Medicine, Stanford University-Stanford University, and Snowball Inria Associate Team
- Subjects
FOS: Computer and information sciences ,Computer Science - Machine Learning ,[INFO.INFO-DB]Computer Science [cs]/Databases [cs.DB] ,Actuarial science ,Atherosclerotic cardiovascular disease ,Computer science ,Machine Learning (stat.ML) ,030204 cardiovascular system & hematology ,Health records ,Machine Learning (cs.LG) ,[INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI] ,3. Good health ,03 medical and health sciences ,0302 clinical medicine ,Statistics - Machine Learning ,Cohort ,Risk stratification ,Leverage (statistics) ,Observational study ,030212 general & internal medicine ,[INFO.INFO-BI]Computer Science [cs]/Bioinformatics [q-bio.QM] - Abstract
International audience; 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 withinconsistent 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 reducedvariability 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 ofthese results in the context of the empirical trade-off between fairness and model performance.
- Published
- 2019
- Full Text
- View/download PDF