EUVIMEDEUVIMED entdecken
Multizentrische Studie

Detection of Hypertrophic Cardiomyopathy on Electrocardiogram Using Artificial Intelligence

James M Hillis iD, Bernardo C Bizzo iD, Sarah F Mercaldo iD, Ankita Ghatak iD, Ashley L MacDonald, Madeleine A Halle, Alexander S Schultz, Eric L'Italien iD, Victor Tam, Nicole K Bart iD, Filipe A Moura iD, Amine Awad und 12 weitere

Circulation: Heart Failure · 2025

DOI: 10.1161/circheartfailure.124.012667 ↗

Kurz gefasst

Multizentrische Studie in der Zeitschrift Circulation: Heart Failure, 2025. Verfasst von James M Hillis und 23 weiteren Autor:innen. Beteiligte Einrichtung: Mass General Brigham AI, Boston, MA (J.M.H., B.C.B., S.F.M., A.G., A.L.M.D., M.A.H., A.S.S., E.L.I., V.T., K.J.D., B.M.S.). Hauptthemen laut MEDLINE: Cardiomyopathy, Hypertrophic, Electrocardiography, Artificial Intelligence, Deep Learning. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 19 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BACKGROUND: Hypertrophic cardiomyopathy (HCM) is associated with significant morbidity and mortality, including sudden cardiac death in the young. Its prevalence is estimated to be 1 in 500, although many people are undiagnosed. The ability to screen electrocardiograms for its presence could improve detection and enable earlier diagnosis. This study evaluated the accuracy of an artificial intelligence device (Viz HCM) in detecting HCM based on a 12-lead electrocardiogram. METHODS: The device was previously trained using deep learning and provides a binary outcome (HCM suspected or not suspected). This study included 293 HCM-positive and 2912 HCM-negative cases, which were selected from 3 hospitals based on chart review incorporating billing diagnostic codes, cardiac imaging, and electrocardiogram features. The device produced an output for 291 (99.3%) HCM-positive and 2905 (99.8%) HCM-negative cases. RESULTS: The device identified HCM with sensitivity of 68.4% (95% CI, 62.8–73.5%), specificity of 99.1% (95% CI, 98.7–99.4%), and area under the curve of 0.975 (95% CI, 0.965–0.982). With assumed population prevalence of 0.002 (1 in 500), the positive predictive value was 13.7% (95% CI, 10.1–19.9%) and the negative predictive value was 99.9% (95% CI, 99.9–99.9%). The device demonstrated broadly consistent performance across demographic and technical subgroups. CONCLUSIONS: The device identified HCM based on a 12-lead electrocardiogram with good performance. Coupled with clinical expertise, it has the potential to augment HCM detection and diagnosis.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Cardiomyopathy, HypertrophicElectrocardiographyArtificial IntelligenceDeep LearningHumansMaleFemaleMiddle AgedAdultPredictive Value of TestsAged

Stichwörter der Autor:innen

artificial intelligencecardiomyopathiesdeep learningelectrocardiography

Autor:innen und Institutionen

  • Mass General Brigham AI, Boston, MA (J.M.H., B.C.B., S.F.M., A.G., A.L.M.D., M.A.H., A.S.S., E.L.I., V.T., K.J.D., B.M.S.).
  • Department of Neurology (J.M.H., A.A., D.B.), Massachusetts General Hospital, Boston.
  • Harvard Medical School, Boston, MA (J.M.H., B.C.B., S.F.M., N.K.B., F.A.M., A.A., D.B., A.J.B., D.A.G., K.S.J., M.S.L., N.A.M., V.D.N., K.J.D., B.M.S., C.Y.H.).
  • Department of Radiology (B.C.B., S.F.M., K.J.D.), Massachusetts General Hospital, Boston.
  • Division of Cardiovascular Medicine (N.K.B., F.A.M., A.J.B., D.A.G., K.S.J., M.S.L., N.A.M., V.D.N., B.M.S., C.Y.H.), Brigham and Women's Hospital, Boston, MA.
  • Department of Neurology (A.A., D.B., D.T.), Brigham and Women's Hospital, Boston, MA.

ORCID-Profile: James M Hillis, Bernardo C Bizzo, Sarah F Mercaldo, Ankita Ghatak, Eric L'Italien, Nicole K Bart, Filipe A Moura, David Bargiela, Sarajune Dagen, Karola S Jering, Mathew S Lopes, Nicholas A Marston, Victor D Nauffal, Keith J Dreyer, Benjamin M Scirica, Carolyn Y Ho

Zitieren

APA

Hillis, J. M., Bizzo, B. C., Mercaldo, S. F., Ghatak, A., MacDonald, A. L., Halle, M. A., Schultz, A. S., L'Italien, E., Tam, V., Bart, N. K., Moura, F. A., Awad, A., Bargiela, D., Dagen, S., Toland, D., Blood, A. J., Gross, D. A., Jering, K. S., Lopes, M. S., …, & Ho, C. Y. (2025). Detection of Hypertrophic Cardiomyopathy on Electrocardiogram Using Artificial Intelligence. Circulation: Heart Failure. https://doi.org/10.1161/circheartfailure.124.012667

Vancouver

Hillis JM, Bizzo BC, Mercaldo SF, Ghatak A, MacDonald AL, Halle MA, et al. Detection of Hypertrophic Cardiomyopathy on Electrocardiogram Using Artificial Intelligence. Circulation: Heart Failure. 2025. doi:10.1161/circheartfailure.124.012667

BibTeX
@article{Hillis2025,
  author = {Hillis, James M and Bizzo, Bernardo C and Mercaldo, Sarah F and Ghatak, Ankita and MacDonald, Ashley L and Halle, Madeleine A and Schultz, Alexander S and L'Italien, Eric and Tam, Victor and Bart, Nicole K and Moura, Filipe A and Awad, Amine and Bargiela, David and Dagen, Sarajune and Toland, Danielle and Blood, Alexander J and Gross, David A and Jering, Karola S and Lopes, Mathew S and Marston, Nicholas A and Nauffal, Victor D and Dreyer, Keith J and Scirica, Benjamin M and Ho, Carolyn Y},
  title = {Detection of Hypertrophic Cardiomyopathy on Electrocardiogram Using Artificial Intelligence},
  journal = {Circulation: Heart Failure},
  year = {2025},
  doi = {10.1161/circheartfailure.124.012667}
}
Kostenlos starten →