AI-Enabled ECG Analysis Improves Diagnostic Accuracy and Reduces False STEMI Activations

Abstract

BACKGROUND: Timely reperfusion is critical in reducing mortality in ST-segment elevation myocardial infarction (STEMI). Although electrocardiography-guided cardiac catheterization laboratory (CCL) activation on the basis of first medical contact recognition improves system-level response, diagnostic uncertainty, particularly in atypical presentations, contributes to false positive activations (FPAs) and reperfusion delays. OBJECTIVES: The aim of this study was to evaluate the diagnostic performance and operational impact of artificial intelligence (AI)-based electrocardiographic (ECG) analysis in real-world STEMI triage across a multicenter U.S. registry. METHODS: A total of 1,032 patients with suspected STEMI who triggered emergent CCL activation at 3 geographically diverse percutaneous coronary intervention centers (January 2020 to May 2024) were retrospectively analyzed. Index electrocardiograms underwent standard triage and blinded retrospective AI ECG analysis (Queen of Hearts, PMcardio) trained to detect acute coronary occlusion and benign mimics. The reference standard was an angiographically confirmed culprit lesion with positive enzymes. Diagnostic accuracy, subgroup analyses, and FPA reclassification were compared. RESULTS: Of 1,032 emergent CCL activations, 601 (58.2%) had confirmed STEMI. The AI ECG model outperformed standard triage, demonstrating higher index ECG sensitivity (553 of 601 [92.0%; 95% CI: 89.7%-94.1%] vs 427 of 601 [71.0%; 95% CI: 67.4%-74.6%]), reducing FPA rates (34 of 431 [7.9%; 95% CI: 6.4%-9.6%] vs 180 of 431 [41.8%; 95% CI: 38.9%-44.7%]), and improving specificity (431 of 531 [81.0%; 95% CI: 77.2%-84.5%] vs 154 of 531 [29.0%; 95% CI: 24.8%-33.4%]) (P < 0.001 for all). The AI ECG model's area under the receiver-operating characteristic curve was 0.94 (95% CI: 0.92-0.95), maintaining consistent performance across clinically challenging subgroups (eg, atrial fibrillation, bundle branch block, STEMI equivalents). The AI ECG model reclassified 277 of 306 (91%) biomarker-negative FPAs correctly. CONCLUSIONS: AI-based ECG analysis significantly improved STEMI detection, reduced FPAs, and enhanced the recognition of nonconventional presentations. This supports integration of AI-based ECG analysis into acute chest pain pathways.

Ähnliche Arbeiten