Indian pediatrics
July 15, 2026 · via Europe PMC
Comparative Interpretation of Pediatric Electrocardiograms by Large Language Models and a Pediatrician.
Saraç U, Paydaş AB, Çeliktaş Z, Kuyucuoğlu T, Şap F, Baysal T, Oflaz MB.
AI summary — for doctors, generated from the abstract only
A pediatrician interpreted pediatric ECGs more accurately than ChatGPT, Copilot or Gemini, so general LLMs should not be used independently.
What was studied
Single-centre comparison of one pediatrician and three LLMs interpreting 178 children's ECGs zero-shot against an expert consensus diagnosis.
Key findings
- Accuracy was 78.7% for the pediatrician, 71.9% ChatGPT, 66.9% Copilot and 50.0% Gemini.
- AUCs were 0.79, 0.70, 0.63 and 0.54 respectively.
- Gemini had a 39.9% false negative rate and Copilot a 24.7% false positive rate.
Clinical relevance
Missed pathological rhythms by AI could be dangerous, so these tools are unsuitable for unsupervised ECG reading in children.
Who should care
Limitations
Single centre, one pediatrician as comparator and zero-shot prompting of general-purpose models, so results may not generalise.
Use LLMs, if at all, only as supervised adjuncts and rely on expert ECG interpretation.
This is an AI-generated summary of the published abstract, not a clinical recommendation. It may not reflect the full text or subsequent updates — verify against the original source before acting on it.
Abstract
Objective
Large language models (LLMs) have been explored for clinical applications, yet their reliability in pediatric electrocardiogram (ECG) interpretation remains unclear. We compared the diagnostic accuracy of three general-purpose artificial intelligence (AI) systems-ChatGPT, Gemini, and Copilot-with that of a pediatrician and characterized error patterns across the platforms.
Methods
A total of 178 children (median age 108 months) underwent standard 12-lead ECG recording at a single center between January 2024 and July 2025. One pediatrician and three LLMs interpreted each ECG using a zero-shot design; responses were compared against a definitive diagnosis established through expert consensus. Rhythms were classified as physiological or pathological, with subgroup analysis for rhythms calling for emergency intervention.
Results
The pediatrician achieved the highest accuracy (78.7%), followed by ChatGPT (71.9%), Copilot (66.9%), and Gemini (50.0%). Area under the receiver operating characteristic (ROC) curve confirmed pediatrician superiority (0.79) over ChatGPT (0.70), Copilot (0.63), and Gemini (0.54). Agreement with definitive diagnosis was moderate for the pediatrician (κ = 0.566) and ChatGPT (κ = 0.410), but weak or nonsignificant for Copilot and Gemini. Error profiles differed markedly; Gemini showed a high false negative rate (39.9%), while Copilot showed a high false positive rate (24.7%).
Conclusions
The clinician outperformed the LLMs in pediatric ECG interpretation. Diagnostic accuracy varied markedly across the models, with reliability limits particularly evident in high-risk rhythms. In their current form, these systems may serve as supplementary tools under expert oversight rather than independent decision-makers.
DOI
10.1007/s13312-026-00396-3
PMID
42455258
Research metadata (titles, abstracts, authors, publication dates) is sourced from Europe PMC, which aggregates content from PubMed/MEDLINE, PubMed Central, and other providers under the U.S. National Library of Medicine (NLM/NCBI). NLM does not claim copyright on abstracts; the original journal publishers or authors may hold rights to the full articles. AI-generated summaries are derived only from the abstract, never the full text, and are always labeled as AI-generated.
Want more like this?
Browse more from the feed. A free account unlocks the full feed, saving and communities.
Back to the research feed