A deep learning ECG model for identification and localization of occlusion myocardial infarction.

Clinical Snapshot

Key Findings

• P Value: Not reported

• Effect Size: C-statistic ≥0.95 for OMI detection, ≥0.87 for non-OMI infarctions

• Primary Outcome: Diagnostic accuracy for occlusion myocardial infarction detection

• Nnt Or Sensitivity: Sensitivity and specificity not reported; only C-statistics provided

• Confidence Interval: Not reported

Clinical Application

Requires integration with ECG systems and validation in local healthcare settings before implementation Relevant to Australian emergency departments and cardiology services; would need TGA approval as medical device software; aligns with RACGP guidelines for timely ACS management Emergency department patients with suspected acute coronary syndrome requiring ECG evaluation

Abstract

Rapid identification and localization of an acute coronary occlusion are vital to prevent myocardial damage, yet reliance on ST-segment ECG criteria misses many acute occlusion myocardial infarctions (OMI) and triggers unnecessary acute angiographies. Here, we present a trained and validated deep learning model using 540,372 emergency ECGs paired with definitive catheterization outcomes. The model has a C-statistic of ≥0.95 for OMI and ≥0.87 for non-OMI infarctions and can localize culprit lesions in the three main coronary branches, which can guide the angiographer. Performance is similar across age, sex, and ECG hardware subgroups. Obviating dependence on ST-elevations and troponins, this model for the identification and localization of OMI has the potential to shorten the time to reperfusion of an acute coronary occlusion and save resources. Because human oversight of OMI detection on the ECG is limited, randomized clinical trials with patient-relevant outcomes are warranted.