Human vs Artificial Intelligence in Detecting Coronary Occlusions in ST-Elevation Myocardial Infarction: Retrospective Study
JMIR Cardio · 14.10.2026 · 10 · e88399-e88399
DOI: 10.2196/88399 ↗Kurz gefasst
Vergleichsstudie in der Zeitschrift JMIR Cardio, online erschienen am 14.10.2026. Verfasst von Aurelia Zimmerli und 12 weiteren Autor:innen. Beteiligte Einrichtung: Department of Cardiology, University Hospital of Lausanne, Rue du Bugnon 46, Lausanne, 1011, Switzerland, 41 795568205. Hauptthemen laut MEDLINE: Electrocardiography, ST Elevation Myocardial Infarction, Artificial Intelligence, Coronary Occlusion. Die Arbeit nennt 14 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.
Abstract (Originalsprache)
Background
Occlusion myocardial infarction (OMI) on the electrocardiogram (ECG) can present as ST-elevation myocardial infarction (STEMI), non-STEMI, ST depression, or other patterns (eg, de Winter T waves and hyperacute T waves), posing a diagnostic challenge. Even experienced physicians may overlook OMI on ECG, leading to delays in catheterization laboratory activation. Recently, smartphone apps using AI have been shown to exhibit promising accuracy in ECG interpretation in large datasets.
Objective
The objective of our study was to retrospectively compare the diagnostic performance of an AI-based application (PMCardio) with that of interventional cardiologists in interpreting nonpathognomonic ECGs that generated debates about diagnosis.
Methods
In total, 33 ECGs that were diagnostically challenging upon patient admission to the emergency department were included. A group of 3 interventional cardiologists, blinded to the final diagnosis, independently assessed whether the ECG suggested OMI requiring immediate invasive coronary angiography. The diagnostic performance of the cardiologists was compared to that of the AI application, using the results of coronary angiography as the gold standard and considering any lesion with ≥90% stenosis as positive.
Results
Of the 33 patients, 29 (88%) had a final diagnosis of cardiac origin for their chest pain, including 23 acute coronary syndromes, of which 13 (57%) were OMI. The 3 cardiologists achieved sensitivities of 62%, 85%, and 62%; negative predictive values (NPVs) of 74%, 83%, and 69%; specificities of 70%, 50%, and 55%; and positive predictive values (PPVs) of 57%, 52%, and 47%. Their overall misclassification rates were 33%, 36%, and 42%. In contrast, AI analysis demonstrated a sensitivity and NPV of 100%, a specificity of 60%, a PPV of 62%, and an overall misclassification rate of 24%.
Conclusions
In this retrospective study of challenging ECGs, an AI application demonstrated better diagnostic performance of OMI as compared to cardiologists. These findings highlight the potential of AI to enhance diagnostic accuracy and support clinical decision-making.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Cardiology, University Hospital of Lausanne, Rue du Bugnon 46, Lausanne, 1011, Switzerland, 41 795568205.
- Hirslanden Klinik Im Park, Zurich, Switzerland.
- Emergency Department, University Hospital of Lausanne, Lausanne, Switzerland.
Zitieren
APA
Zimmerli, A., Dupre, M., Liabot, Q., Sellah, C. Y., Meier, D., Salihu, A., Weerts, V., Rubimbura, V., Roux, O., Muller, O., Hugli, O., Carron, P. N., & Fournier, S. (2026). Human vs Artificial Intelligence in Detecting Coronary Occlusions in ST-Elevation Myocardial Infarction: Retrospective Study. JMIR Cardio, 10, e88399-e88399. https://doi.org/10.2196/88399
Vancouver
Zimmerli A, Dupre M, Liabot Q, Sellah CY, Meier D, Salihu A, et al. Human vs Artificial Intelligence in Detecting Coronary Occlusions in ST-Elevation Myocardial Infarction: Retrospective Study. JMIR Cardio. 2026;10:e88399-e88399. doi:10.2196/88399
BibTeX
@article{Zimmerli2026,
author = {Zimmerli, Aurelia and Dupre, Marion and Liabot, Quentin and Sellah, C-Yasmine and Meier, David and Salihu, Adil and Weerts, Victor and Rubimbura, Vladimir and Roux, Olivier and Muller, Olivier and Hugli, Olivier and Carron, Pierre-Nicolas and Fournier, Stephane},
title = {Human vs Artificial Intelligence in Detecting Coronary Occlusions in ST-Elevation Myocardial Infarction: Retrospective Study},
journal = {JMIR Cardio},
year = {2026},
volume = {10},
pages = {e88399--e88399},
doi = {10.2196/88399}
}
EUVIMED