ORIGINAL RESEARCH article
Front. Med.
Sec. Translational Medicine
Diagnostic Accuracy of ChatGPT for 12-Lead ECG-Based Localization of Ventricular Ectopic Foci Prior to Catheter Ablation
Provisionally accepted
- School of Medicine, Selcuk University, Konya, Türkiye
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
Background: Precise pre-procedural localisation of ventricular ectopic (VE) foci shortens mapping time, reduces fluoroscopy, and improves ablation success. Large language models such as ChatGPT offer instant, free-text clinical support, but their accuracy in ECG-based VE localisation is unknown. Methods: In this single-centre pilot diagnostic-accuracy study, 50 consecutive adults (43 ± 14 years; 58 % female) scheduled for first-time VE ablation were enrolled. ChatGPT served as the index test and invasive electroanatomical mapping during ablation served as the reference standard. A blinded electrophysiologist converted each index 12-lead ECG into a structured textual description of QRS morphology. ChatGPT-4o (temperature 0.2) was asked to assign one of five anatomic origins (RVOT, LVOT, papillary muscle, fascicular, epicardial). Predictions were compared with electro-anatomical mapping during catheter ablation; agreement was measured with Cohen's κ. Results: Electro-anatomical mapping identified 30 RVOT, 11 LVOT, 4 papillary, 1 fascicular, and 4 epicardial foci. ChatGPT correctly localised 17/50 cases (34 %), yielding an overall Cohen's κ of –0.02 (95 % CI –0.18 to 0.14). Sensitivity/specificity were 40 %/55 % for RVOT and 36 %/62 % for LVOT; no fascicular or epicardial origins were correctly predicted. Performance did not differ by the presence of structural heart disease (p = 0.43). Procedure duration and acute ablation success (96 %) were unaffected by ChatGPT accuracy. Conclusions: Freetext querying of ChatGPT failed to provide clinically meaningful VE localisation, performing no better than chance and markedly below published ECG-based algorithms. This likely reflects the model's lack of domain-specific training and its reliance on purely text-based reasoning without direct access to ECG signals. Current general-purpose language models should not be relied upon for procedural planning in VE ablation; future work must integrate multimodal training and domain-specific optimisation before LLMs can augment electrophysiology practice. Keywords: ChatGPT; ventricular ectopy; catheter ablation; electrocardiogram; artificial intelligence
Keywords: ChatGPT, Ventricular ectopy, Catheter Ablation, electrocardiogram, artificial intelligence
Received: 13 Aug 2025; Accepted: 15 Dec 2025.
Copyright: © 2025 Gurses, TEZCAN, Yalcın, Özalp, Tuncez and Özen. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence: Hüseyin TEZCAN
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.