Creating Fair Models of Atherosclerotic Cardiovascular Disease Risk
This work addresses inequitable therapy distribution in healthcare for patients with ASCVD, representing an incremental improvement in fairness for domain-specific risk models.
The authors tackled the problem of unfair performance across race and gender groups in atherosclerotic cardiovascular disease (ASCVD) risk prediction models by developing a fair model using adversarial learning and electronic health records, achieving reduced variability in error rates across groups.
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.