EUVIMEDEUVIMED entdecken
Multizentrische StudieOpen Access · CC BY 4.0

Proof-of-Concept Automated Framework for Intraoperative Transesophageal Echocardiography: View Classification and Biventricular Function Assessment

Trevor Chan, Shir Goldfinger, Rachel Hannah Grasfield, Vikram Eswar, David Barreto, John G Augoustides, Vivian Yan, Ronak M Shah, Alison M Pouch, Emily J MacKay

Journal of Cardiothoracic and Vascular Anesthesia · 2026

DOI: 10.1053/j.jvca.2026.01.036 ↗

Kurz gefasst

Multizentrische Studie in der Zeitschrift Journal of Cardiothoracic and Vascular Anesthesia, 2026. Verfasst von Trevor Chan und 9 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology, University of Pennsylvania, Philadelphia; Department of Bioengineering, University of Pennsylvania, Philadelphia. Hauptthemen laut MEDLINE: Echocardiography, Transesophageal, Monitoring, Intraoperative, Cardiac Surgical Procedures, Ventricular Function, Right. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NHLBI NIH HHS, NCATS NIH HHS, National Center for Advancing Translational Sciences.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

OBJECTIVE: To develop a proof-of-concept automated framework for integrated intraoperative transesophageal echocardiography (TEE) interpretation, encompassing view classification, left ventricular ejection fraction (LVEF) and right ventricular systolic function (RVSF) assessment, and tricuspid regurgitation (TR) grading. DESIGN: This cross-sectional study used TEE video clips and reports from patients undergoing cardiac surgery from 2018 to 2023. SETTING: Two hospitals within the University of Pennsylvania Healthcare System. PARTICIPANTS: Study participants were ≥18 years of age and undergoing any cardiac surgery in which an intraoperative TEE was performed. We used 6,900 intraoperative TEE studies from 6,016 unique patients. INTERVENTIONS: Receipt of intraoperative TEE examination during cardiac surgery. MEASUREMENTS AND MAIN RESULTS: The view classification model was trained on TEE clips from 1,432 studies, and the diagnostic model was trained on clips from 6,400 studies, for a total of more than 700,000 individual TEE clips for training. Performance was evaluated on 945 test clips from 8 studies for view classification and 500 studies for diagnostic prediction. No external testing was performed. The view classifier achieved 86% accuracy compared to the expert agreement top-1 weighted accuracy of 74%. The diagnostic model differentiated LVEF >55% versus ≤55% (area under the receiver operating characteristic curve [AUROC] = 0.86) and LVEF >30% versus ≤30% (AUROC = 0.95). Continuous LVEF prediction was assessed (Pearson r = 0.79, mean absolute error = 7.8). The model differentiated normal versus abnormal RVSF (AUROC = 0.82) and differentiated less-than-moderate versus moderate-or-greater right ventricular dysfunction (AUROC = 0.92). Additionally, the model differentiated no TR versus any TR (AUROC = 0.69) and differentiated less-than-moderate versus moderate-or-greater TR (AUROC = 0.79). CONCLUSIONS: This proof-of-concept automated approach showed encouraging results for view classification and quantification tasks, suggesting potential for further development toward intraoperative utility.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Echocardiography, TransesophagealMonitoring, IntraoperativeCardiac Surgical ProceduresVentricular Function, RightHumansCross-Sectional StudiesFemaleMaleProof of Concept StudyStroke VolumeMiddle AgedAged

Stichwörter der Autor:innen

cardiac surgerydeep learningechocardiographyperioperative medicine

Autor:innen und Institutionen

  • Department of Radiology, University of Pennsylvania, Philadelphia; Department of Bioengineering, University of Pennsylvania, Philadelphia.
  • Department of Radiology, University of Pennsylvania, Philadelphia; School of Arts and Sciences, University of Pennsylvania. Electronic address: shirg@sas.upenn.edu.
  • School of Medicine, Des Moines University, Des Moines, IA.
  • Department of Anaesthesiology and Critical Care,Perelman School of Medicine at the University of Pennsylvania, Philadelphia.
  • School of Medicine, Thomas Jefferson University, Philadelphia, PA.
  • Department of Anaesthesiology and Critical Care,Perelman School of Medicine at the University of Pennsylvania, Philadelphia; Penn's Cardiovascular Outcomes, Quality and Evaluative Research Center (CAVOQER),University of…

Förderung

  • NHLBI NIH HHS
  • NCATS NIH HHS
  • National Center for Advancing Translational Sciences
  • National Heart Lung and Blood Institute
  • National Institutes of Health
  • Institute for Translational Medicine and Therapeutics
  • University of Pennsylvania
  • National Science Foundation

Zitieren

APA

Chan, T., Goldfinger, S., Grasfield, R. H., Eswar, V., Barreto, D., Augoustides, J. G., Yan, V., Shah, R. M., Pouch, A. M., & MacKay, E. J. (2026). Proof-of-Concept Automated Framework for Intraoperative Transesophageal Echocardiography: View Classification and Biventricular Function Assessment. Journal of Cardiothoracic and Vascular Anesthesia. https://doi.org/10.1053/j.jvca.2026.01.036

Vancouver

Chan T, Goldfinger S, Grasfield RH, Eswar V, Barreto D, Augoustides JG, et al. Proof-of-Concept Automated Framework for Intraoperative Transesophageal Echocardiography: View Classification and Biventricular Function Assessment. Journal of Cardiothoracic and Vascular Anesthesia. 2026. doi:10.1053/j.jvca.2026.01.036

BibTeX
@article{Chan2026,
  author = {Chan, Trevor and Goldfinger, Shir and Grasfield, Rachel Hannah and Eswar, Vikram and Barreto, David and Augoustides, John G and Yan, Vivian and Shah, Ronak M and Pouch, Alison M and MacKay, Emily J},
  title = {Proof-of-Concept Automated Framework for Intraoperative Transesophageal Echocardiography: View Classification and Biventricular Function Assessment},
  journal = {Journal of Cardiothoracic and Vascular Anesthesia},
  year = {2026},
  doi = {10.1053/j.jvca.2026.01.036}
}
Kostenlos starten →