Key result
A deep learning model pretrained on 12-lead ECGs predicted myocardial injury from continuous single-lead ECGs with an AUROC of 0.760, exceeding the predictive performance of emergency department physicians.
Why the study?
Current chest pain risk stratification requires 12-lead ECGs and serial biomarkers, which are static and restricted to highly resourced settings, prompting investigation into continuous single-lead ECG and transfer learning.
Does a deep learning model using continuous single-lead ECG predict myocardial injury as accurately as 12-lead ECGs in ED patients with chest pain or shortness of breath?
Cohort (n=10,874)
No
Does a deep learning model using continuous single-lead ECG predict myocardial injury as accurately as 12-lead ECGs in ED patients with chest pain or shortness of breath?
Effect estimate: AUROC 0.760 (95% CI 0.721-0.799)
Deep learning models using continuous single-lead ECGs can predict myocardial injury as accurately as 12-lead ECGs, offering potential for wearable device applications in chest pain triage.
Supports single-lead ECG exploration for ED injury prediction; leaves open prospective validation before wearable triage adoption.
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.
No takes yet. Share an insight, caveat, or question.
Jin et al. (2022) conducted a cohort in Myocardial injury / Chest pain (n=10,874). Deep learning model using continuous single-lead ECG vs. Baseline clinical models and ED physicians was evaluated on Prediction of myocardial injury (AUROC) (AUROC 0.760, 95% CI 0.721-0.799). A deep learning model pretrained on 12-lead ECGs predicted myocardial injury from continuous single-lead ECGs with an AUROC of 0.760, exceeding the predictive performance of emergency department physicians.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: