Performance of AI models in ECG interpretation and risk stratification for major adverse cardiac events in the emergency department
Technology and Health Care · 18.11.2026
DOI: 10.1177/09287329261509123 ↗Kurz gefasst
Fachartikel in der Zeitschrift Technology and Health Care, online erschienen am 18.11.2026. Verfasst von Halil İbrahim Doru und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Emergency Medicine, Erzurum Horasan State Hospital, Erzurum, Turkey. Die Arbeit nennt 16 Literaturangaben.
Abstract (Originalsprache)
Background
Artificial intelligence (AI) may support electrocardiogram (ECG) interpretation and risk stratification in emergency departments, but its clinical utility remains uncertain.
Objective
To evaluate the performance of ChatGPT and Gemini in ECG interpretation and risk stratification for major adverse cardiac events (MACE).
Methods
In 89 prospective ED patients presenting with chest pain or palpitations, ECGs evaluated by AI models and emergency specialists were compared against cardiologist consensus. Cohen's kappa assessed agreement; diagnostic metrics were calculated for MACE risk stratification, and McNemar's test compared paired positive-call frequencies between the models.
Results
Emergency specialists showed high agreement with cardiologists (κ = 0.689–0.874), whereas ChatGPT (κ = 0.386) and Gemini (κ = 0.224) demonstrated lower agreement. McNemar testing revealed Gemini had a significantly higher positive-call tendency for ischemic features (ST elevation, ST depression, T-wave inversion; p < 0.05) than ChatGPT. For 30-day MACE risk stratification (n = 27, 30.3%), ChatGPT (96.3% sensitivity, 85.4% accuracy) and Gemini (92.6% sensitivity, 79.8% accuracy) showed numerically higher performance for ChatGPT; the proportion of positive MACE risk calls did not differ significantly between models (McNemar's exact test, p = 0.55).
Conclusion
In this single-center pilot cohort (n = 89), both AI models showed high sensitivity in an exploratory MACE risk-stratification analysis, with no significant difference in positive-call frequency; equivalence cannot be inferred. Both showed lower agreement with cardiologists than emergency specialists. These preliminary findings do not support rule-out use and, at most, suggest a supplementary decision-support role, requiring further multi-center validation.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Emergency Medicine, Erzurum Horasan State Hospital, Erzurum, Turkey.
- Department of Emergency Medicine, Erzurum Regional Training and Research Hospital, Erzurum, Turkey.
- Faculty of Education, Department of Computer Education and Instructional Technology, Dokuz Eylül University, Izmir, Turkey.
- Department of Cardiology, Erzurum Regional Training and Research Hospital, Erzurum, Turkey.
ORCID-Profile: Halil İbrahim Doru
Zitieren
APA
Doru, H. İ., Arslan, Ş., Can, N. O., Arslan, K., Aydınyılmaz, F., Oflaz, A. O., Odacı, A., & Şenol, A. (2026). Performance of AI models in ECG interpretation and risk stratification for major adverse cardiac events in the emergency department. Technology and Health Care. https://doi.org/10.1177/09287329261509123
Vancouver
Doru Hİ, Arslan Ş, Can NO, Arslan K, Aydınyılmaz F, Oflaz AO, et al. Performance of AI models in ECG interpretation and risk stratification for major adverse cardiac events in the emergency department. Technology and Health Care. 2026. doi:10.1177/09287329261509123
BibTeX
@article{Doru2026,
author = {Doru, Halil İbrahim and Arslan, Şenol and Can, Nazım Onur and Arslan, Kürşat and Aydınyılmaz, Faruk and Oflaz, Abdullah Onur and Odacı, Abdulkadir and Şenol, Ahmet},
title = {Performance of AI models in ECG interpretation and risk stratification for major adverse cardiac events in the emergency department},
journal = {Technology and Health Care},
year = {2026},
doi = {10.1177/09287329261509123}
}
EUVIMED