Large language models fail to reliably predict emergent catheterization laboratory activation from prehospital electrocardiograms.
Heart & lung · 2026-09-16 · Method & validation
Abstract
BACKGROUND: Rapid and accurate electrocardiogram (ECG) interpretation is essential for timely identification of ST-elevation myocardial infarction (STEMI) and activation of reperfusion pathways in emergency care. OBJECTIVES: To evaluate the diagnostic performance of multimodal LLMs in identifying prehospital ECGs warranting emergent catheterization laboratory activation. METHODS: We performed a retrospective analysis of 615 ECGs from 270 emergency medical service patient encounters (EMS) with concern for acute myocardial infarction. The reference standard was cardiology activation of the STEMI pathway for emergent angiography. LLM-based image interpretation (three models) and ECG machine algorithm interpretations were compared. Sensitivity, specificity, positive predictive value, negative predictive value, and overall accuracy were calculated. RESULTS: Gemini demonstrated the highest sensitivity (95.3%; 95% CI 91.7-97.3) but extremely poor specificity (9.4%), indicating a high false-positive rate. ChatGPT and Claude showed moderate sensitivity (68.1% and 67.2%) with limited specificity (42.3% and 46.5%). The ECG machine algorithm demonstrated more balanced performance, with sensitivity of 67.7% (95% CI 61.4-73.4) and higher specificity (64.2%) than all LLMs. CONCLUSIONS: Multimodal LLM interpretation of prehospital ECGs demonstrated clinically unreliable performance for identifying ECGs warranting emergent cardiac catheterization laboratory activation when benchmarked against real-world cardiology activation decisions. Although some models achieved high sensitivity, poor specificity resulted in excessive false-positive activation recommendations. These findings suggest that general-purpose LLMs are not appropriate for ECG-based catheterization laboratory activation decisions in time-sensitive cardiopulmonary care workflows.
Abstract © the authors or publisher, via PubMed. Reuse and removal
Tags
Decision support tools · ECG transmission
Related articles
- Derivation and validation of the Montreal prehospital ST-elevation myocardial infarction activation rule. (J Electrocardiol, 2020)
- An algorithm for identification of ST-elevation myocardial infarction patients by emergency medicine services. (Am J Emerg Med, 2013)
- The ECG as decision support in STEMI. (Dan Med J, 2012)
- Prehospital ECG Interpretation Methods for ST-Elevation MI Detection and Catheterization Laboratory Activation: A Systematic Review and Meta-Analysis. (Arch Acad Emerg Med, 2025)
- The Effect of Implementation of the American Heart Association Mission Lifeline PreAct Algorithm for Prehospital Cardiac Catheterization Laboratory Activation on the Rate of "False Positive" Activations. (Prehosp Disaster Med, 2020)
- Effect of prehospital 12-Lead electrocardiography on the emergent medical system for ST-Segment-Elevation myocardial infarction during the coronavirus disease 2019 (COVID-19) pandemic: results from the K-ACTIVE registry. (Cardiovasc Interv Ther, 2026)