Algorithmic fairness in cardiovascular disease risk prediction: overcoming inequalities

• Published in: Open heart Vol. 10; no. 2; p. e002395
• Main Author: Varga, Tibor V
• Format: Journal Article
• Language: English
• Published: London British Cardiovascular Society 01.11.2023; BMJ Publishing Group LTD; BMJ Publishing Group
• Subjects: Algorithms; biomarkers; delivery of health care; Diabetes; epidemiology; ethics, medical; Ethnicity; Health disparities; Minority & ethnic groups; Precision medicine; Socioeconomic factors; Systematic review; Viewpoint; United Kingdom > UK; United States > US
• ISSN: 2053-3624; 2398-595X; 2053-3624
• DOI: 10.1136/openhrt-2023-002395

The main purpose of prognostic risk prediction models is to identify individuals who are at risk of disease, to enable early intervention. Current prognostic cardiovascular risk prediction models, such as the Systematic COronary Risk Evaluation (SCORE2) and the SCORE2-Older Persons (SCORE2-OP) models, which represent the clinically used gold standard in assessing patient risk for major cardiovascular events in the European Union (EU), generally overlook socioeconomic determinants, leading to disparities in risk prediction and resource allocation. A central recommendation of this article is the explicit inclusion of individual-level socioeconomic determinants of cardiovascular disease in risk prediction models. The question of whether prognostic risk prediction models can promote health equity remains to be answered through experimental research, potential clinical implementation and public health analysis. This paper introduces four distinct fairness concepts in cardiovascular disease prediction and their potential to narrow existing disparities in cardiometabolic health.