Deep learning-based strain echocardiography adds prognostic value in heart failure with reduced ejection fraction
European Heart Journal - Imaging Methods and Practice

Abstract
Echocardiographic global longitudinal strain (GLS) and mechanical dispersion (MD) improve risk prediction in heart failure (HF). To facilitate clinical implementation, we aimed to develop a deep learning (DL)-based method for fast, fully automated GLS and MD and validate its ability to predict ventricular arrhythmia (VA) and all-cause mortality.
This prospective observational study included 568 patients (73 ± 13 years, 67% male) with first diagnosis of HF and reduced ejection fraction (HFrEF). A DL-based method was designed to measure echocardiographic GLS and MD. The median follow-up was 4.8 years (interquartile range: 2.9, 6.1 years). VA occurred in 49 patients (9%), while 118 patients (21%) died. The optimal cut-off values for GLS and MD were 9% and 70 ms. Patients with both impaired GLS and increased MD were at high risk of VA [hazard ratio (HR) 6.98, 95% confidence interval (CI): 3.23–15.1] compared to those with either impaired GLS or increased MD alone [HR 2.84 (95% CI: 1.38–5.86),
A novel DL-based method for fully automated GLS and MD was feasible, fast, and predicted VA in patients with HFrEF. Combining GLS and MD provided potential incremental prognostic value beyond GLS, MD, or EF alone. This approach may enhance workflow and facilitate arrhythmic risk stratification. Further studies are needed to determine whether it can improve selection of patients for ICD therapy.
NCT02286908 at
Contributors

Andreas Østvik
Author

Daniela Melichova
Author

John Nyberg
Author

Thuy Mi Nguyen
Author

Ivar M Salte
Author

Øyvind O Salvesen
Author

Havard Dalen
Author

Lasse Lovstakken
Author

Harald Brunvand
Author

Kristina H Haugaa
Author





