Sex disparities in deep learning estimation of ejection fraction from cardiac magnetic resonance imaging
Open Access
- 23 January 2026
- journal article
- research article
- Published by Springer Nature in npj Digital Medicine
- Vol. 9 (1)
Abstract
The advent of artificial intelligence in cardiovascular imaging holds immense potential for earlier diagnoses, precision medicine, and improved disease management. However, the presence of sex-based disparities and strategies to mitigate biases in deep learning models for cardiac imaging remain understudied. In this study, we analyzed algorithmic bias in a foundation model that was pretrained on cardiac magnetic resonance imaging and radiology reports from multiple institutes and finetuned to estimate ejection fraction (EF) on the UK Biobank dataset. The model performed significantly worse in EF estimation for females than males in the diagnosis of reduced EF. Algorithmic fairness did not improve despite masking of protected attributes in radiology reports and data resampling, although explicit input of sex in model finetuning may improve EF estimation in some cases. The underdiagnosis of reduced EF among females holds critical implications for the exacerbation of existing sex-based disparities in cardiovascular health. We advise caution in the development of models for cardiovascular imaging to avoid such pitfalls.Keywords
Funding Information
- National Institutes of Health (1R01HL157235-01A1)
- National Institutes of Health (1R01HL157235-01A1)
- National Institutes of Health (1R01HL157235-01A1)
- National Institutes of Health (1R01HL157235-01A1)
- National Institutes of Health (1R01HL157235-01A1)
- National Institutes of Health (1R01HL157235-01A1)
- National Institutes of Health (1R01HL157235-01A1)
- National Institutes of Health (1R01HL157235-01A1)
- National Institutes of Health (1R01HL157235-01A1)
This publication has 39 references indexed in Scilit:
- An intentional approach to managing bias in general purpose embedding modelsThe Lancet Digital Health, 2024
- An information theoretic approach to reducing algorithmic bias for machine learningNeurocomputing, 2022
- Fairness in Cardiac MR Image Analysis: An Investigation of Bias Due to Data Imbalance in Deep Learning Based Segmentation2021
- The Lancet women and cardiovascular disease Commission: reducing the global burden by 2030The Lancet, 2021
- Addressing bias: artificial intelligence in cardiovascular medicineThe Lancet Digital Health, 2020
- Sex differences in cardiac magnetic resonance features in patients with hypertrophic cardiomyopathyThe International Journal of Cardiovascular Imaging, 2020
- Fully-automated left ventricular mass and volume MRI analysis in the UK Biobank population cohort: evaluation of initial resultsThe International Journal of Cardiovascular Imaging, 2017
- Artificial Intelligence in Precision Cardiovascular MedicineJACC, 2017
- Consideration of Sex Differences in Medicine to Improve Health Care and Patient OutcomesJAMA, 2016
- Importance of sex and gender in atherosclerosis and cardiovascular diseaseAtherosclerosis, 2015