Official journal of the Slovak Society of Cardiology,
Slovak Society of Hypertension and Slovak Association for Cardiac Arrhythmias

Cardiology Letters 2026, 35(3):146-154

Corrected QT interval assessment: artificial intelligence versus physician

Ján Šuba ml., Martin Dúbrava
LFUK a UN Bratislava, Nemocnica akad. L. Dérera, Limbová 5, 833 05 Bratislava, Slovenská republika

Background: Quantification of the corrected QT interval (QTc) is of major importance for risk stratification of torsades de pointes and arrhythmogenic sudden cardiac death, particularly when QTc exceeds 500 ms.

Aim: The aim of the study was to compare QTc interval assessment between the widely available multimodal AI assistant ChatGPT version 5.2 "Thinking", the specialized AI application PMcardio, automated ECG device measurement, and physician measurement.

Patients and Methods: The analysis included 115 anonymized 12-lead electrocardiograms from hospitalized patients. The mean age was 80.8 years, and 58.3% were women. Using a standardized methodology, QT and RR intervals were determined and the QTc interval was subsequently calculated using Bazett's formula. Agreement of the above methods with physician measurement was evaluated by Bland-Altman analysis.

Results: QTc interval was assessable in 105 recordings analyzed by ChatGPT, whereas all 115 recordings were assessable with PMcardio and physician measurement. ChatGPT showed the lowest agreement with the physician, with wide variability and evidence of proportional bias. PMcardio and the ECG device achieved substantially closer agreement with physician measurements.

Conclusion: A broadly available multimodal AI model demonstrated substantial variability in measurements and therefore cannot yet be considered sufficiently robust for independent QTc assessment in clinical practice. In contrast, specialized AI tools appear more promising. Physician measurement remains essential.

Keywords: artificial intelligence; electrocardiography; QT interval; QTc

Published: August 1, 2026  Show citation

ACS AIP APA ASA Harvard Chicago Chicago Notes IEEE ISO690 MLA NLM Turabian Vancouver
Šuba J, Dúbrava M. Corrected QT interval assessment: artificial intelligence versus physician. Cardiology Letters. 2026;35(3):146-154.
Share...
Download citation
  • BibTeX (.bib)
  • Bookends (.ris)
  • EasyBib (.ris)
  • EndNote (.enw)
  • EndNote 8 (.xml)
  • ISI WoS (.isi)
  • Medlars (.medlars)
  • Mendeley (.ris)
  • MODS (.xml)
  • Papers (.ris)
  • RefWorks (.txt)
  • RefManager (.ris)
  • RIS (.ris)
  • MS Word (.xml)
  • Zotero (.ris)
    • Open full article

    References

    1. Zhou J, Li H, Chen S, Chen Z, Han Z, Gao X. Large language models in biomedicine and healthcare. npj Artif Intell. 2025;1:44.
    2. AlSaad R, Abd-alrazaq A, Boughorbel S, Ahmed A, Renault MA, Damseh R, et al. Multimodal large language models in health care: applications, challenges, and future outlook. J Med Internet Res. 2024;26:e59505.
    3. Collins GS, Moons KGM, Dhiman P, Riley RD, Beam AL, Van Claster B, et al. TRIPOD+AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods. BMJ. 2024;385:e078378.
    4. Drew BJ, Ackerman MJ, Funk M, Gibler WB, Klingfield P, Menon V, et al. Prevention of torsade de pointes in hospital settings: a scientific statement from the American Heart Association and the American College of Cardiology Foundation. J Am Coll Cardiol. 2010;55:934-947.
    5. Yap YG, Camm AJ. Drug induced QT prolongation and torsades de pointes. Heart. 2003;89:1363-1372.
    6. Zeppenfeld K, Tfelt-Hansen J, de Riva M, Winkel BG, Behr ER, Blom NA, et al. 2022 ESC Guidelines for the management of patients with ventricular arrhythmias and the prevention of sudden cardiac death. Eur Heart J. 2022;43:3997-4126.
    7. Stallmann FW, Pipberger HV. Automatic recognition of electrocardiographic waves by digital computer. Circ Res. 1961;9:1138-1143.
    8. McLaughlin NB, Campbell RW, Murray A. Accuracy of four automatic QT measurement techniques in cardiac patients and healthy subjects. Heart. 1996;76:422-426.
    9. Schläpfer J, Wellens HJ. Computer-Interpreted Electrocardiograms: Benefits and Limitations. J Am Coll Cardiol. 2017;70:1183-1192.
    10. Palermi S, Vecchiato M, Ng FS, Attia Z, Cho Y, Anselmino M, et al. Artificial intelligence and the electrocardiogram: a modern renaissance. Eur J Intern Med. 2025;140:106329.
    11. Kim YR, Park SB, Lee SJ, Yang HJ. Artificial intelligence assisted QT interval measurement in 12-lead-ECGs. Europace. 2025;27(Suppl 1):euaf085.838.
    12. Plagwitz L, Doldi F, Magerfleisch J, Zotov M, Bickmann L, Heider D, et al. QTcNet: a deep learning model for direct heart rate corrected QT interval estimation. Europace. 2025;27:euaf274.
    13. Ansari RA, Bandyopadhyay S, Trivedi RK, Brennan KA, Liu X, Ganesan P, et al. Deep Learning-Based Continuous QT Monitoring to Identify High-Risk Prolongation Events After Class III Antiarrhythmic Initiation. Circulation. 2026;153:35-46.
    14. Zhu L, Mou W, Wu K, Lai Y, Lin A, Yang T, et al. Multimodal ChatGPT-4V for Electrocardiogram Interpretation: Promise and Limitations. J Med Internet Res. 2024;26:e54607.
    15. Çamkiran V, Tunç H, Achmar B, Ürker TS, Kutlu İ, Torun A. Artificial intelligence (ChatGPT) ready to evaluate ECG in real life? Not yet! Digit Health. 2025;11: 20552076251325279.

    This is an open access article distributed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (CC BY-NC 4.0), which permits non-comercial use, distribution, and reproduction in any medium, provided the original publication is properly cited. No use, distribution or reproduction is permitted which does not comply with these terms.


    Return to the content