Development and Evaluation of a Deep Learning–Based Pulmonary Hypertension Screening Algorithm Using a Digital Stethoscope
Journal of the American Heart Association · 04.02.2025 · 14 (3)
DOI: 10.1161/jaha.124.036882 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of the American Heart Association, erschienen am 04.02.2025. Verfasst von Ling Guo und 9 weiteren Autor:innen. Beteiligte Einrichtung: Eko Health Inc. Emeryville CA USA. Hauptthemen laut MEDLINE: Deep Learning, Stethoscopes, Hypertension, Pulmonary, Algorithms. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.
Abstract (Originalsprache)
Background
Despite the poor outcomes related to the presence of pulmonary hypertension, it often goes undiagnosed in part because of low suspicion and screening tools not being easily accessible such as echocardiography. A new readily available screening tool to identify elevated pulmonary artery systolic pressures is needed to help with the prognosis and timely treatment of underlying causes such as heart failure or pulmonary vascular remodeling. We developed a deep learning–based method that uses phonocardiograms (PCGs) for the detection of elevated pulmonary artery systolic pressure, an indicator of pulmonary hypertension.
Methods
Approximately 6000 PCG recordings with the corresponding echocardiogram‐based estimated pulmonary artery systolic pressure values, as well as ≈169 000 PCG recordings without associated echocardiograms, were used for training a deep convolutional network to detect pulmonary artery systolic pressures ≥40 mm Hg in a semisupervised manner. Each 15‐second PCG, recorded using a digital stethoscope, was processed to generate 5‐second mel‐spectrograms. An additional labeled data set of 196 patients was used for testing. GradCAM++ was used to visualize high importance segments contributing to the network decision.
Results
An average area under the receiver operator characteristic curve of 0.79 was obtained across 5 cross‐validation folds. The testing data set gave a sensitivity of 0.71 and a specificity of 0.73, with pulmonic and left subclavicular locations having higher sensitivities. GradCAM++ technique highlighted physiologically meaningful PCG segments in example pulmonary hypertension recordings.
Conclusions
We demonstrated the feasibility of using digital stethoscopes in conjunction with deep learning algorithms as a low‐cost, noninvasive, and easily accessible screening tool for early detection of pulmonary hypertension.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Eko Health Inc. Emeryville CA USA.
- Warren Alpert Medical School Brown University Providence RI USA.
- Brown University Helath Cardiovascular Institute Providence RI USA.
- University of California, San Francisco, Heart & Vascular San Francisco CA USA.
- VA Providence Healthcare System Providence RI USA.
ORCID-Profile: Ling Guo, Nivedita Khobragade, Suleman Ilyas, Preston N Nicely, Caroline Currie, Gaurav Choudhary
Zitieren
APA
Guo, L., Khobragade, N., Kieu, S., Ilyas, S., Nicely, P. N., Asiedu, E. K., Lima, F. V., Currie, C., Lastowski, E., & Choudhary, G. (2025). Development and Evaluation of a Deep Learning–Based Pulmonary Hypertension Screening Algorithm Using a Digital Stethoscope. Journal of the American Heart Association, 14(3). https://doi.org/10.1161/jaha.124.036882
Vancouver
Guo L, Khobragade N, Kieu S, Ilyas S, Nicely PN, Asiedu EK, et al. Development and Evaluation of a Deep Learning–Based Pulmonary Hypertension Screening Algorithm Using a Digital Stethoscope. Journal of the American Heart Association. 2025;14(3). doi:10.1161/jaha.124.036882
BibTeX
@article{Guo2025,
author = {Guo, Ling and Khobragade, Nivedita and Kieu, Spencer and Ilyas, Suleman and Nicely, Preston N and Asiedu, Emmanuel K and Lima, Fabio V and Currie, Caroline and Lastowski, Emileigh and Choudhary, Gaurav},
title = {Development and Evaluation of a Deep Learning–Based Pulmonary Hypertension Screening Algorithm Using a Digital Stethoscope},
journal = {Journal of the American Heart Association},
year = {2025},
volume = {14},
number = {3},
doi = {10.1161/jaha.124.036882}
}
EUVIMED