Deep learning for algorithmic detection of pulmonary hypertension using a combined digital stethoscope and single-lead electrocardiogram

Abstract This SBIR Direct to Phase II project will develop a deep learning-based clinical decision support algorithm for screening and detecting pulmonary hypertension (PH) using phonocardiogram and electrocardiogram data recording using the Eko DUO Digital Stethoscopes. The screening tool will help to decrease the number of patients with pulmonary hypertension that remain undertreated simply because their condition is not diagnosed. The gold standard diagnostic for pulmonary hypertension is right heart catheterization which is costly, invasive, and requires specialized personnel.To address these challenges, Eko developed the DUO, a digital stethoscope in a handheld form factor with built-in single lead electrocardiogram. The DUO is designed to stream digitized phonocardiograms and electrocardiograms to a smartphone, tablet or personal computer. There, the signal can be analyzed with the decision support algorithm we developed as part of this project. The specific aims of this study are : (1) build a database of matched ECG/PCG recording labeled against right heart catheterization and echocardiograms, and (2) develop and clinically test a deep learning algorithm that can detect PH and stratify its severity. By integrating this deep learning algorithm into Eko’s mobile and cloud software platform, we anticipate this algorithm will enable more accurate screening for pulmonary hypertension in adult patients, leading to earlier diagnosis and better patient outcomes.