EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

High-Throughput Deep Learning Detection of Mitral Regurgitation

Amey Vrudhula iD, Grant Duffy, Milos Vukadinovic iD, David Liang iD, Susan Cheng iD, David Ouyang iD

Circulation · 17.09.2024 · 150 (12) · 923-933

DOI: 10.1161/circulationaha.124.069047 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Circulation, erschienen am 17.09.2024. Verfasst von Amey Vrudhula und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Cardiology, Smidt Heart Institute (A.V., G.D., M.V., S.C.), Cedars-Sinai Medical Center, Los Angeles, CA. Hauptthemen laut MEDLINE: Mitral Valve Insufficiency, Deep Learning. Die Arbeit wurde bisher 78-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: NHLBI NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BACKGROUND: Diagnosis of mitral regurgitation (MR) requires careful evaluation by echocardiography with Doppler imaging. This study presents the development and validation of a fully automated deep learning pipeline for identifying apical 4-chamber view videos with color Doppler echocardiography and detecting clinically significant (moderate or severe) MR from transthoracic echocardiograms. METHODS: A total of 58 614 transthoracic echocardiograms (2 587 538 videos) from Cedars-Sinai Medical Center were used to develop and test an automated pipeline to identify apical 4-chamber view videos with color Doppler across the mitral valve and then assess MR severity. The model was tested internally on a test set of 1800 studies (80 833 videos) from Cedars-Sinai Medical Center and externally evaluated in a geographically distinct cohort of 915 studies (46 890 videos) from Stanford Healthcare. RESULTS: In the held-out Cedars-Sinai Medical Center test set, the view classifier demonstrated an area under the curve (AUC) of 0.998 (0.998–0.999) and correctly identified 3452 of 3539 echocardiography videos as having color Doppler information across the mitral valve (sensitivity of 0.975 [0.968–0.982] and specificity of 0.999 [0.999–0.999] compared with manually curated videos). In the external test cohort from Stanford Healthcare, the view classifier correctly identified 1051 of 1055 manually curated videos with color Doppler information across the mitral valve (sensitivity of 0.996 [0.990–1.000] and specificity of 0.999 [0.999–0.999]). In the Cedars-Sinai Medical Center test cohort, MR moderate or greater in severity was detected with an AUC of 0.916 (0.899–0.932) and severe MR was detected with an AUC of 0.934 (0.913–0.953). In the Stanford Healthcare test cohort, the model detected MR moderate or greater in severity with an AUC of 0.951 (0.924–0.973) and severe MR with an AUC of 0.969 (0.946–0.987). CONCLUSIONS: In this study, a novel automated pipeline for identifying clinically significant MR from full transthoracic echocardiography studies demonstrated excellent performance across large numbers of studies and across multiple institutions. Such an approach has the potential for automated screening and surveillance of MR.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Mitral Valve InsufficiencyDeep LearningHumansEchocardiography, Doppler, ColorFemaleMaleMitral ValveMiddle AgedEchocardiographyAgedSeverity of Illness Index

Stichwörter der Autor:innen

artificial intelligencedeep learningechocardiographymitral valve insufficiency

Autor:innen und Institutionen

  • Department of Cardiology, Smidt Heart Institute (A.V., G.D., M.V., S.C.), Cedars-Sinai Medical Center, Los Angeles, CA.
  • Icahn School of Medicine at Mt Sinai, New York, NY (A.V.).
  • Department of Bioengineering, University of California Los Angeles (M.V.).
  • Department of Medicine, Division of Cardiology, Stanford University, Palo Alto, CA (D.L.).
  • Division of Artificial Intelligence in Medicine (D.O.), Cedars-Sinai Medical Center, Los Angeles, CA.

ORCID-Profile: Amey Vrudhula, Milos Vukadinovic, David Liang, Susan Cheng, David Ouyang

Förderung

  • NHLBI NIH HHS

Zitieren

APA

Vrudhula, A., Duffy, G., Vukadinovic, M., Liang, D., Cheng, S., & Ouyang, D. (2024). High-Throughput Deep Learning Detection of Mitral Regurgitation. Circulation, 150(12), 923-933. https://doi.org/10.1161/circulationaha.124.069047

Vancouver

Vrudhula A, Duffy G, Vukadinovic M, Liang D, Cheng S, Ouyang D. High-Throughput Deep Learning Detection of Mitral Regurgitation. Circulation. 2024;150(12):923-933. doi:10.1161/circulationaha.124.069047

BibTeX
@article{Vrudhula2024,
  author = {Vrudhula, Amey and Duffy, Grant and Vukadinovic, Milos and Liang, David and Cheng, Susan and Ouyang, David},
  title = {High-Throughput Deep Learning Detection of Mitral Regurgitation},
  journal = {Circulation},
  year = {2024},
  volume = {150},
  number = {12},
  pages = {923--933},
  doi = {10.1161/circulationaha.124.069047}
}
Kostenlos starten →