Gender Bias in AI's Perception of Cardiovascular Risk

Margaux Achtari; Adil Salihu; Olivier Muller; Emmanuel Abbé; Carole Clair; Joëlle Schwarz; Stephane Fournier

doi:10.2196/54242

Gender Bias in AI's Perception of Cardiovascular Risk

J Med Internet Res. 2024 Oct 22:26:e54242. doi: 10.2196/54242.

Authors

Margaux Achtari^#¹, Adil Salihu^#², Olivier Muller², Emmanuel Abbé³, Carole Clair¹, Joëlle Schwarz¹, Stephane Fournier²

Affiliations

¹ Health and Gender Unit, University Center for Primary Care and Public Health (Unisanté), University of Lausanne, Lausanne, Switzerland.
² Department of Cardiology, Lausanne University Hospital and University of Lausanne, Lausanne, Switzerland.
³ Institute of Mathematics and School of Computer and Communication Sciences, EPFL, Lausanne, Switzerland.

^# Contributed equally.

PMID: 39437384
PMCID: PMC11538872
DOI: 10.2196/54242

Abstract

The study investigated gender bias in GPT-4's assessment of coronary artery disease risk by presenting identical clinical vignettes of men and women with and without psychiatric comorbidities. Results suggest that psychiatric conditions may influence GPT-4's coronary artery disease risk assessment among men and women.

Keywords: AI; CAD; artery; artificial intelligence; cardiovascular; chatbot: health care; coronary; coronary artery disease; gender; gender bias; gender equity; men: women; risk.

©Margaux Achtari, Adil Salihu, Olivier Muller, Emmanuel Abbé, Carole Clair, Joëlle Schwarz, Stephane Fournier. Originally published in the Journal of Medical Internet Research (https://www.jmir.org), 22.10.2024.

MeSH terms

Adult
Artificial Intelligence
Cardiovascular Diseases / psychology
Coronary Artery Disease / psychology
Female
Heart Disease Risk Factors
Humans
Male
Middle Aged
Risk Assessment / methods
Sexism* / psychology