Related Experiment Video
Updated: Aug 15, 2026
Inverse Probability of Treatment Weighting (Propensity Score) using the Military Health System Data Repository and National Death Index
Published on: January 8, 2020
Algorithmic fairness in machine-learning models for determining the progression or recurrence of cardiovascular
Imeth Illamperuma1, Bhavya Gandhi2, Ronin Offman2
1Department of Medicine, McMaster University, Hamilton, ON L8S 4L8, Canada.
Insights
Algorithmic fairness in machine learning (ML) models for secondary cardiovascular disease (CVD) prevention is under-researched. Limited studies show fairness challenges driven by data and structural factors, not just algorithms.
Area of Science:
- Cardiovascular Disease Research
- Machine Learning Applications
- Health Equity
Background:
- Machine learning (ML) models are increasingly used to predict cardiovascular disease (CVD) outcomes.
- Ensuring algorithmic fairness across racial subgroups is critical for equitable healthcare.
- Current research on fairness in secondary CVD prevention ML models is limited.
Purpose of the Study:
- To review how algorithmic fairness is measured, operationalized, and reported in ML models for secondary CVD prevention.
- To identify gaps in the literature regarding fairness in ML models for racialized populations experiencing CVD.
Main Methods:
- A scoping review following PRISMA-ScR guidelines.
- Systematic searches of OVID MEDLINE, EMBASE, Scopus, and CENTRAL databases.
- Inclusion of studies evaluating fairness in ML models for secondary cardiovascular outcomes.
Main Results:
- Only three retrospective cohort studies met inclusion criteria, using US electronic health record data.
- One study implemented fairness-aware development, showing 5%-12% improvement in equity metrics with minor trade-offs.
- Other studies assessed fairness post hoc, with limited success in mitigating subgroup performance disparities.
Conclusions:
- Evidence on algorithmic fairness in ML for secondary CVD outcomes is sparse.
- Fairness limitations often stem from upstream data and structural factors, not solely algorithmic design.
- Improved reporting and integrated fairness approaches are needed for equitable clinical deployment.
Objective:
To examine how algorithmic fairness is measured, operationalized, and reported in machine learning (ML) models designed to predict or support secondary prevention of cardiovascular disease (CVD) outcomes including progression, recurrence, readmission, and post-index mortality in racialized populations.
Materials And Methods:
This scoping review was conducted in accordance with PRISMA-ScR guidelines and registered with the Open Science Framework (OSF registration: https://doi.org/10.17605/OSF.IO/9W67V). Systematic searches of OVID MEDLINE, EMBASE, Scopus, and CENTRAL were performed to identify studies evaluating fairness in ML models applied to secondary cardiovascular outcomes.
Results:
Of 2669 records screened, three retrospective cohort studies met inclusion criteria. All studies used large-scale electronic health record data from the United States and evaluated model performance across racial subgroups. Only one study implemented fairness-aware model development, reporting improvements of approximately 5%-12% in equity-related metrics, accompanied by modest trade-offs in calibration and sensitivity. The remaining studies assessed fairness post hoc and demonstrated limited ability to mitigate subgroup performance differences.
Discussion:
Most full-text studies excluded during screening addressed fairness in predicting primary CVD incidence rather than secondary outcomes, highlighting a substantial gap in the literature. Across included studies, observed fairness limitations appeared to be driven largely by upstream structural and data-generating factors such as representation, care patterns, and documentation rather than algorithmic design alone.
Conclusion:
Evidence on algorithmic fairness in ML models for secondary cardiovascular outcomes remains sparse. Improved reporting of subgroup performance, missingness, and calibration, alongside integration of fairness throughout model development, is necessary before equitable clinical deployment.
Study Registration:
Open Science Framework: https://doi.org/10.17605/OSF.IO/9W67V.