Leveraging clinical epidemiology concepts to strengthen machine learning fairness evaluations

The increasing use of machine learning (ML) in clinical care makes fairness a central issue. Fairness, defined as the absence of disparities across individuals or subgroups, shares several parallels with concepts in clinical epidemiology. The objective was to apply clinical epidemiology frameworks to the evaluation of ML fairness, both to enhance understanding of these concepts and to strengthen fairness assessments.

This manuscript addresses: (1) the connection between clinical epidemiology bias terms and ML fairness concepts; (2) the relationship between diagnostic testing metrics and fairness criteria; (3) issues arising from multiple testing; and (4) strategies for fairness considerations leveraging clinical epidemiology principles.

Unfairness can arise at different stages: before model development, during model development and post-deployment. The root of unfairness can be conceptualized as a result of clinical epidemiology bias concepts, such as selection, measurement, model misspecification, cognitive and implementation bias. Common approaches to evaluating fairness involve comparing model performance metrics across 1 or more subgroups. Four widely used fairness criteria are independence, separation, sufficiency and predictive parity. They can be assessed using diagnostic testing metrics. Fairness evaluations are vulnerable to multiple testing issues, with subgroup analyses posing particular risks for spurious findings. Solutions can leverage established clinical epidemiology principles such as pre-specifying the analytic strategy.

Many parallels exist between ML fairness and clinical epidemiology, including the conceptualization of the root causes of unfairness, the articulation of fairness criteria, and considerations related to multiple testing. Methodologically sound fairness approaches can leverage well-established principles from clinical epidemiology.