EUVIMEDEUVIMED entdecken
Open Access

Deep Learning Algorithms to Detect Murmurs Associated With Structural Heart Disease

John Prince iD, John Maidens iD, Spencer Kieu, Caroline Currie iD, Daniel Barbosa, Cody Hitchcock, Adam Saltman iD, Kambiz Norozi iD, Philipp Wiesner, Nicholas Slamon iD, Erica Del Grippo, Deepak Padmanabhan iD und 4 weitere

Journal of the American Heart Association · 17.10.2023 · 12 (20)

DOI: 10.1161/jaha.123.030377 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of the American Heart Association, erschienen am 17.10.2023. Verfasst von John Prince und 15 weiteren Autor:innen. Beteiligte Einrichtung: Eko Devices, Inc. Oakland CA USA. Hauptthemen laut MEDLINE: Deep Learning, Heart Diseases. Die Arbeit wurde bisher 46-mal zitiert (Crossref) und nennt 55 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NHLBI NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

The success of cardiac auscultation varies widely among medical professionals, which can lead to missed treatments for structural heart disease. Applying machine learning to cardiac auscultation could address this problem, but despite recent interest, few algorithms have been brought to clinical practice. We evaluated a novel suite of Food and Drug Administration‐cleared algorithms trained via deep learning on >15 000 heart sound recordings. Methods and Results We validated the algorithms on a data set of 2375 recordings from 615 unique subjects. This data set was collected in real clinical environments using commercially available digital stethoscopes, annotated by board‐certified cardiologists, and paired with echocardiograms as the gold standard. To model the algorithm in clinical practice, we compared its performance against 10 clinicians on a subset of the validation database. Our algorithm reliably detected structural murmurs with a sensitivity of 85.6% and specificity of 84.4%. When limiting the analysis to clearly audible murmurs in adults, performance improved to a sensitivity of 97.9% and specificity of 90.6%. The algorithm also reported timing within the cardiac cycle, differentiating between systolic and diastolic murmurs. Despite optimizing acoustics for the clinicians, the algorithm substantially outperformed the clinicians (average clinician accuracy, 77.9%; algorithm accuracy, 84.7%.)

Conclusions

The algorithms accurately identified murmurs associated with structural heart disease. Our results illustrate a marked contrast between the consistency of the algorithm and the substantial interobserver variability of clinicians. Our results suggest that adopting machine learning algorithms into clinical practice could improve the detection of structural heart disease to facilitate patient care.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningHeart DiseasesAdultHumansHeart MurmursHeart AuscultationAlgorithms

Stichwörter der Autor:innen

auscultationdeep learningdigital stethoscopesheart sound classificationmurmur classificationstructural heart disease

Autor:innen und Institutionen

  • Eko Devices, Inc. Oakland CA USA.
  • Department of Pediatrics, Pediatric Cardiology Western University London ON Canada.
  • Department of Pediatric Cardiology and Intensive Care Medicine Hannover Medical School Hannover Germany.
  • Children Health Research Institute London ON Canada.
  • Cox Medical Center Springfield MO USA.
  • Nemours Children's Hospital, Delaware Wilmington DE USA.

ORCID-Profile: John Prince, John Maidens, Caroline Currie, Adam Saltman, Kambiz Norozi, Nicholas Slamon, Deepak Padmanabhan, Anand Subramanian

Förderung

  • NHLBI NIH HHS

Zitieren

APA

Prince, J., Maidens, J., Kieu, S., Currie, C., Barbosa, D., Hitchcock, C., Saltman, A., Norozi, K., Wiesner, P., Slamon, N., Del Grippo, E., Padmanabhan, D., Subramanian, A., Manjunath, C., Chorba, J., & Venkatraman, S. (2023). Deep Learning Algorithms to Detect Murmurs Associated With Structural Heart Disease. Journal of the American Heart Association, 12(20). https://doi.org/10.1161/jaha.123.030377

Vancouver

Prince J, Maidens J, Kieu S, Currie C, Barbosa D, Hitchcock C, et al. Deep Learning Algorithms to Detect Murmurs Associated With Structural Heart Disease. Journal of the American Heart Association. 2023;12(20). doi:10.1161/jaha.123.030377

BibTeX
@article{Prince2023,
  author = {Prince, John and Maidens, John and Kieu, Spencer and Currie, Caroline and Barbosa, Daniel and Hitchcock, Cody and Saltman, Adam and Norozi, Kambiz and Wiesner, Philipp and Slamon, Nicholas and Del Grippo, Erica and Padmanabhan, Deepak and Subramanian, Anand and Manjunath, Cholenahalli and Chorba, John and Venkatraman, Subramaniam},
  title = {Deep Learning Algorithms to Detect Murmurs Associated With Structural Heart Disease},
  journal = {Journal of the American Heart Association},
  year = {2023},
  volume = {12},
  number = {20},
  doi = {10.1161/jaha.123.030377}
}
Kostenlos starten →