AI-Enabled ECG Analysis Improves Diagnostic Accuracy and Reduces False STEMI Activations
JACC: Cardiovascular Interventions · 2026-01 · 19 (2) · 145-156
DOI: 10.1016/j.jcin.2025.10.018 ↗Kurz gefasst
Multizentrische Studie in der Zeitschrift JACC: Cardiovascular Interventions, 2026-01. Verfasst von Robert Herman und 18 weiteren Autor:innen. Beteiligte Einrichtung: Cardiovascular Center Aalst, AZORG Hospital, Aalst, Belgium; Powerful Medical, Bratislava, Slovakia. Electronic address: robi.herman@gmail.com. Hauptthemen laut MEDLINE: ST Elevation Myocardial Infarction, Electrocardiography, Percutaneous Coronary Intervention, Artificial Intelligence. Die Arbeit wurde bisher 45-mal zitiert (Crossref) und nennt 24 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: OpenAI, University of Naples Federico II.
Abstract (Originalsprache)
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.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Cardiovascular Center Aalst, AZORG Hospital, Aalst, Belgium; Powerful Medical, Bratislava, Slovakia. Electronic address: robi.herman@gmail.com.
- Department of Emergency Medicine, University of California, Davis, Davis, California, USA.
- Department of Emergency Medicine, Beth Israel Deaconess Medical Center, Boston, Massachusetts, USA.
- Department of Emergency Medicine, McGovern Medical School, University of Texas Health Science Center at Houston, and Memorial Hermann Hospital, Texas Medical Center, Houston, Texas, USA.
- Division of Cardiology, Department of Medicine, Weatherhead PET Imaging Center, McGovern Medical School, University of Texas Health Science Center, and Memorial Hermann Hospital, Houston, Texas, USA.
- Powerful Medical, Bratislava, Slovakia.
Förderung
- OpenAI
- University of Naples Federico II
Zitieren
APA
Herman, R., Mumma, B. E., Hoyne, J. D., Cooper, B. L., Johnson, N. P., Kisova, T., Demolder, A., Rafajdus, A., Iring, A., Palus, T., Belmonte, M., Barbato, E., Baron, S. J., Hatala, R., Smith, S. W., Meyers, H. P., Sharkey, S. W., Bartunek, J., & Henry, T. D. (2026). AI-Enabled ECG Analysis Improves Diagnostic Accuracy and Reduces False STEMI Activations. JACC: Cardiovascular Interventions, 19(2), 145-156. https://doi.org/10.1016/j.jcin.2025.10.018
Vancouver
Herman R, Mumma BE, Hoyne JD, Cooper BL, Johnson NP, Kisova T, et al. AI-Enabled ECG Analysis Improves Diagnostic Accuracy and Reduces False STEMI Activations. JACC: Cardiovascular Interventions. 2026;19(2):145-156. doi:10.1016/j.jcin.2025.10.018
BibTeX
@article{Herman2026,
author = {Herman, Robert and Mumma, Bryn E and Hoyne, Jake D and Cooper, Benjamin L and Johnson, Nils P and Kisova, Timea and Demolder, Anthony and Rafajdus, Adam and Iring, Andrej and Palus, Timotej and Belmonte, Marta and Barbato, Emanuele and Baron, Suzanne J and Hatala, Robert and Smith, Stephen W and Meyers, H Pendell and Sharkey, Scott W and Bartunek, Jozef and Henry, Timothy D},
title = {AI-Enabled ECG Analysis Improves Diagnostic Accuracy and Reduces False STEMI Activations},
journal = {JACC: Cardiovascular Interventions},
year = {2026},
volume = {19},
number = {2},
pages = {145--156},
doi = {10.1016/j.jcin.2025.10.018}
}
EUVIMED