Understanding algorithmic fairness for clinical prediction in terms of subgroup net benefit and health equity

TL;DR

This paper proposes a novel fairness assessment for clinical prediction models by expanding net benefit to evaluate health equity and distribution of benefits across subgroups, addressing limitations of traditional fairness paradigms.

Contribution

It introduces a subgroup net benefit framework to assess fairness in clinical models, emphasizing health equity and trade-offs with resource constraints.

Findings

Demonstrated approach with diabetes and lung cancer models

Highlighted trade-offs between health equity and healthcare objectives

Provided insights into model impact on health inequalities

Abstract

There are concerns about the fairness of clinical prediction models. 'Fair' models are defined as those for which their performance or predictions are not inappropriately influenced by protected attributes such as ethnicity, gender, or socio-economic status. Researchers have raised concerns that current algorithmic fairness paradigms enforce strict egalitarianism in healthcare, levelling down the performance of models in higher-performing subgroups instead of improving it in lower-performing ones. We propose assessing the fairness of a prediction model by expanding the concept of net benefit, using it to quantify and compare the clinical impact of a model in different subgroups. We use this to explore how a model distributes benefit across a population, its impact on health inequalities, and its role in the achievement of health equity. We show how resource constraints might introduce necessary trade-offs between health equity and other objectives of healthcare systems. We showcase our proposed approach with the development of two clinical prediction models: 1) a prognostic type 2 diabetes model used by clinicians to enrol patients into a preventive care lifestyle intervention programme, and 2) a lung cancer screening algorithm used to allocate diagnostic scans across the population. This approach helps modellers better understand if a model upholds health equity by considering its performance in a clinical and social context.