Publications by authors named "Sean A Abreau"
Article Synopsis
- Valvular heart disease, specifically aortic stenosis (AS), aortic regurgitation (AR), and mitral regurgitation (MR), is a significant but often underdiagnosed issue that deep learning analysis of electrocardiograms (ECGs) can potentially address.
- The study involved 77,163 patients and developed deep learning algorithms to accurately identify moderate to severe cases of AS, AR, and MR using ECG data, achieving good performance metrics, especially for AS (AU-ROC: 0.88).
- Results suggest that deep learning could be integrated into screening programs for valvular heart disease, showing high sensitivity and specificity, particularly at low disease prevalence rates.
Importance: Millions of clinicians rely daily on automated preliminary electrocardiogram (ECG) interpretation. Critical comparisons of machine learning-based automated analysis against clinically accepted standards of care are lacking.
Objective: To use readily available 12-lead ECG data to train and apply an explainability technique to a convolutional neural network (CNN) that achieves high performance against clinical standards of care.