Literature DB >> 35994003

Transfer learning enables prediction of myocardial injury from continuous single-lead electrocardiography.

Boyang Tom Jin1, Raj Palleti1, Siyu Shi2, Andrew Y Ng1, James V Quinn3, Pranav Rajpurkar4, David Kim3.   

Abstract

OBJECTIVE: Chest pain is common, and current risk-stratification methods, requiring 12-lead electrocardiograms (ECGs) and serial biomarker assays, are static and restricted to highly resourced settings. Our objective was to predict myocardial injury using continuous single-lead ECG waveforms similar to those obtained from wearable devices and to evaluate the potential of transfer learning from labeled 12-lead ECGs to improve these predictions.
METHODS: We studied 10 874 Emergency Department (ED) patients who received continuous ECG monitoring and troponin testing from 2020 to 2021. We defined myocardial injury as newly elevated troponin in patients with chest pain or shortness of breath. We developed deep learning models of myocardial injury using continuous lead II ECG from bedside monitors as well as conventional 12-lead ECGs from triage. We pretrained single-lead models on a pre-existing corpus of labeled 12-lead ECGs. We compared model predictions to those of ED physicians.
RESULTS: A transfer learning strategy, whereby models for continuous single-lead ECGs were first pretrained on 12-lead ECGs from a separate cohort, predicted myocardial injury as accurately as models using patients' own 12-lead ECGs: area under the receiver operating characteristic curve 0.760 (95% confidence interval [CI], 0.721-0.799) and area under the precision-recall curve 0.321 (95% CI, 0.251-0.397). Models demonstrated a high negative predictive value for myocardial injury among patients with chest pain or shortness of breath, exceeding the predictive performance of ED physicians, while attending to known stigmata of myocardial injury.
CONCLUSIONS: Deep learning models pretrained on labeled 12-lead ECGs can predict myocardial injury from noisy, continuous monitor data early in a patient's presentation. The utility of continuous single-lead ECG in the risk stratification of chest pain has implications for wearable devices and preclinical settings, where external validation of the approach is needed.
© The Author(s) 2022. Published by Oxford University Press on behalf of the American Medical Informatics Association. All rights reserved. For permissions, please email: journals.permissions@oup.com.

Entities:  

Keywords:  acute coronary syndrome; deep learning; electrocardiography; transfer learning

Mesh:

Substances:

Year:  2022        PMID: 35994003      PMCID: PMC9552286          DOI: 10.1093/jamia/ocac135

Source DB:  PubMed          Journal:  J Am Med Inform Assoc        ISSN: 1067-5027            Impact factor:   7.942


  40 in total

1.  Noninvasive Cardiac Testing vs Clinical Evaluation Alone in Acute Chest Pain: A Secondary Analysis of the ROMICAT-II Randomized Clinical Trial.

Authors:  Samuel W Reinhardt; Chien-Jung Lin; Eric Novak; David L Brown
Journal:  JAMA Intern Med       Date:  2018-02-01       Impact factor: 21.873

2.  Chest pain in general practice or in the hospital emergency department: is it the same?

Authors:  F Buntinx; D Knockaert; R Bruyninckx; N de Blaey; M Aerts; J A Knottnerus; H Delooz
Journal:  Fam Pract       Date:  2001-12       Impact factor: 2.267

3.  Chest pain in the emergency room: value of the HEART score.

Authors:  A J Six; B E Backus; J C Kelder
Journal:  Neth Heart J       Date:  2008-06       Impact factor: 2.380

4.  Detection of STEMI Using Prehospital Serial 12-Lead Electrocardiograms.

Authors:  Alain Tanguay; Johann Lebon; Lorraine Lau; Denise Hébert; François Bégin
Journal:  Prehosp Emerg Care       Date:  2018-01-16       Impact factor: 3.077

5.  Accuracy of Physicians' Electrocardiogram Interpretations: A Systematic Review and Meta-analysis.

Authors:  David A Cook; So-Young Oh; Martin V Pusic
Journal:  JAMA Intern Med       Date:  2020-11-01       Impact factor: 21.873

6.  A Methodological Appraisal of the HEART Score and Its Variants.

Authors:  Steven M Green; David L Schriger
Journal:  Ann Emerg Med       Date:  2021-04-29       Impact factor: 5.721

7.  PTB-XL, a large publicly available electrocardiography dataset.

Authors:  Patrick Wagner; Nils Strodthoff; Ralf-Dieter Bousseljot; Dieter Kreiseler; Fatima I Lunze; Wojciech Samek; Tobias Schaeffter
Journal:  Sci Data       Date:  2020-05-25       Impact factor: 6.444

8.  Artificial intelligence to predict needs for urgent revascularization from 12-leads electrocardiography in emergency patients.

Authors:  Shinichi Goto; Mai Kimura; Yoshinori Katsumata; Shinya Goto; Takashi Kamatani; Genki Ichihara; Seien Ko; Junichi Sasaki; Keiichi Fukuda; Motoaki Sano
Journal:  PLoS One       Date:  2019-01-09       Impact factor: 3.240

Review 9.  Array programming with NumPy.

Authors:  Charles R Harris; K Jarrod Millman; Stéfan J van der Walt; Ralf Gommers; Pauli Virtanen; David Cournapeau; Eric Wieser; Julian Taylor; Sebastian Berg; Nathaniel J Smith; Robert Kern; Matti Picus; Stephan Hoyer; Marten H van Kerkwijk; Matthew Brett; Allan Haldane; Jaime Fernández Del Río; Mark Wiebe; Pearu Peterson; Pierre Gérard-Marchant; Kevin Sheppard; Tyler Reddy; Warren Weckesser; Hameer Abbasi; Christoph Gohlke; Travis E Oliphant
Journal:  Nature       Date:  2020-09-16       Impact factor: 49.962

10.  Classification of 12-lead ECGs: the PhysioNet/Computing in Cardiology Challenge 2020.

Authors:  Erick A Perez Alday; Annie Gu; Amit J Shah; Chad Robichaux; An-Kwok Ian Wong; Chengyu Liu; Feifei Liu; Ali Bahrami Rad; Andoni Elola; Salman Seyedi; Qiao Li; Ashish Sharma; Gari D Clifford; Matthew A Reyna
Journal:  Physiol Meas       Date:  2021-01-01       Impact factor: 2.833

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.