ArticleThe western journal of emergency medicine2026
Pilot Study Comparing Emergency Physician and Artificial Intelligence-supported Interpretations of Electrocardiograms.
Article in The western journal of emergency medicine, 2026. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Not yet cited in PubMed.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
0 citing papers in PubMed.
No citing paper in PubMed yet.
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
1 author.
Funding
No grant is acknowledged in the PubMed record.
Abstract
backgroundArtificial intelligence (AI) tools are increasingly being explored for medical applications; however, their effectiveness in emergency electrocardiogram (ECG) interpretation is under-investigated. In this pilot study we aimed to evaluate the diagnostic performance of AI interpretation of ECGs by comparing its results to those of an experienced emergency physician.
methodsWe sourced 20 ECG cases representing common critical conditions from publicly available academic repositories-ST-elevation myocardial infarction, non-ST-elevation myocardial infarction, atrial fibrillation, supraventricular tachycardia, ventricular tachycardia, third-degree atrioventricular block, left and right bundle branch block, hyperkalemia, Brugada syndrome, Wellens syndrome, fusion beats, and torsades de pointes.The AI tool ChatGPT-4 and an experienced emergency physician, who served as the reference (gold standard) interpreter, independently analyzed each case across five key parameters: rhythm and heart rate; cardiac axis; ST/T segment changes; preliminary diagnosis; and emergency management recommendation. Full concordance was defined as complete agreement across all five parameters.
resultsAgreement between AI and the emergency physician was observed in 18 of 20 cases (90%). The Cohen kappa was 0.80, indicating substantial chance-corrected agreement. Concordance by diagnostic category was as follows: myocardial infarction (6/6, 100%); arrhythmias including atrial fibrillation, supraventricular tachycardia, and ventricular tachycardia (6/6, 100%); conduction disorders (3/3, 100%); and hyperkalemia (1/1, 100%). Among the atypical or complex ECGs, concordance was 1/1 (100%) for Brugada syndrome, 1/1 (100%) for Wellens syndrome, 0/1 (0%) for fusion beats, and 0/1 (0%) for torsades de pointes. In the torsades case, ChatGPT did not recommend intravenous magnesium sulfate-the standard first-line treatment-despite recognizing the condition.
conclusionAn AI tool demonstrated moderate diagnostic concordance with one experienced emergency physician in interpreting some common ECG findings in the emergency setting. However, discrepancies, particularly in complex cases and critical management recommendations, highlight the need for larger scale investigations. Our findings from this pilot study do not support the independent use of AI for definitive ECG interpretation or emergency management decisions; it should serve as an adjunct tool that enhances rather than supplants human clinical judgment.
Indexed as
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.