Adversarial Debiasing for Equitable and Fair Detection of Acute Coronary Syndrome using 12-Lead ECG

View Full Paper

Ask AI

Bookmark

Authors

Discussion

Machine learning enhances diagnostic accuracy for acute coronary syndrome, mitigating racial disparities in detection.

After using adversarial debiasing, the sensitivity gap between Black and non-Black populations reduced significantly, from 9.8% to 1.3%.
The study achieved ROC scores of 0.810 and 0.817, indicating high effectiveness in diagnosing acute coronary syndrome.
Machine learning models, including a random forest classifier, were tested using multiple strategies to improve diagnostic fairness.
The findings suggest adversarial debiasing can be a valuable approach for enhancing equitable healthcare across diverse populations.

Ji et al. (2025) studied this question.

View Full Paper

Ask AI

Bookmark

View Full Paper

Ask AI

Bookmark

Authors

Machine learning enhances diagnostic accuracy for acute coronary syndrome, mitigating racial disparities in detection.

After using adversarial debiasing, the sensitivity gap between Black and non-Black populations reduced significantly, from 9.8% to 1.3%.
The study achieved ROC scores of 0.810 and 0.817, indicating high effectiveness in diagnosing acute coronary syndrome.
Machine learning models, including a random forest classifier, were tested using multiple strategies to improve diagnostic fairness.
The findings suggest adversarial debiasing can be a valuable approach for enhancing equitable healthcare across diverse populations.

Ji et al. (2025) studied this question.

View Full Paper

Ask AI

Bookmark