Background: Mitral valve prolapse (MVP) is a common valvulopathy, with a subset of MVP patients developing sudden cardiac death or cardiac arrest. Complex ventricular ectopy (ComVE) represents a marker of arrhythmic risk that is associated with myocardial fibrosis and increased mortality in MVP. We hypothesize that an ECG-based machine-learning model can identify MVP with ComVE and/or myocardial fibrosis on cardiac magnetic resonance (CMR) imaging.
Methods: A deep convolutional neural network (CNN) was trained to detect ComVE using 6,916 12-lead ECGs from 569 MVP patients evaluated at the University of California San Francisco (UCSF) between 2012 and 2020. A separate CNN was also trained to detect late gadolinium enhancement (LGE) using 87 ECGs from MVP patients with contrast CMR.
Results: The prevalence of ComVE was 160/569 or 28% (20 patients or 3% had cardiac arrest or sudden cardiac death). The area under the curve (AUC) of the CNN to detect ComVE was 0.81 (95% CI, 0.78-0.84). AUC remained high even after excluding patients with moderate-severe mitral regurgitation (MR) [0.80 (95% CI, 0.77-0.83)], or with bileaflet MVP [0.81 (95% CI, 0.76-0.85)]. The top ECG segments able to discriminate ComVE vs no ComVE were related to ventricular depolarization and repolarization (early-mid ST and QRS fromV1, V3, and III). LGE in the papillary muscles or basal inferolateral wall was present in 21 (24%) of 87 patients with available CMR. The AUC for detection of LGE was 0.75 (95% CI, 0.68-0.82).
Conclusions: Standard 12-lead ECGs analyzed with machine learning can detect MVP at risk for ventricular arrhythmias and fibrosis and can identify novel ECG correlates of arrhythmic risk regardless of leaflet involvement or mitral regurgitation severity. ECG-based CNNs may help select those MVP patients requiring closer follow-up and/or a CMR.