EUVIMEDEUVIMED entdecken
ValidierungsstudieOpen Access · CC BY 4.0

QTcNet: a deep learning model for direct heart rate corrected QT interval estimation

Lucas Plagwitz iD, Florian Doldi iD, Jannes Magerfleisch, Maxim Zotov iD, Lucas Bickmann iD, Dominik Heider iD, Julian Varghese iD, Lars Eckardt iD, Antonius Büscher iD

Europace · 2025

DOI: 10.1093/europace/euaf274 ↗

Kurz gefasst

Validierungsstudie in der Zeitschrift Europace, 2025. Verfasst von Lucas Plagwitz und 8 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Medical Informatics, University of Münster, Albert-Schweitzer-Campus 1/Building A11, Münster 48149, Germany. Hauptthemen laut MEDLINE: Deep Learning, Electrocardiography, Heart Rate, Signal Processing, Computer-Assisted. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Center for Clinical Research.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Aims

Automated QTc measurements from commercial ECG systems often diverge from expert readings. We developed QTcNet, a deep learning model trained and validated on multiple large ECG datasets to improve automated QTc measurement accuracy. Methods and results QTcNet employs a regression-based convolutional neural network architecture. It was trained on 120 300 algorithm-labelled ECGs (60 150 from an internal hospital cohort and 60 150 from the MIMIC-IV dataset) after correction for a vendor-specific +15 ms bias. Performance was evaluated against expert QTc measurements in three independent datasets: PTB Diagnostic ECG Database (n = 100 ECGs in validation set), QTcMS (n = 210), and ECGRDVQ (n = 5219). The effect of fine-tuning on cardiologist-annotated ECGs was tested in the PTB database (n = 449 in fine-tuning set). Model explainability analyses were performed with Integrated Gradient maps. QTcNet reduced cross-cohort mean absolute error (MAE) from 23.4 to 13.4 ms and root mean square error (RMSE) from 40.1 to 22.1 ms, almost halving large (>50 ms) outliers. Fine-tuning only reduced errors in the PTB dataset but did not improve cross-cohort performance. Integrated Gradient maps confirmed that the model concentrated on QRS onset and T wave offset, supporting physiological plausibility.

Conclusion

QTcNet, trained on large-scale algorithmically labelled data, consistently outperformed conventional algorithms across three independent, external validation datasets. Fine-tuning of QTcNet may adapt the model to the characteristics of specific cohorts but reduces external validity in other cohorts. We openly release the full model and code, along with a ready-to-use online implementation at https://qtcnet.uni-muenster.de, facilitating further research and community-driven improvement.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningElectrocardiographyHeart RateSignal Processing, Computer-AssistedHumansReproducibility of ResultsAlgorithmsDatabases, FactualAction PotentialsPredictive Value of TestsNeural Networks, Computer

Stichwörter der Autor:innen

12-lead ECGArtificial intelligenceDeep learningDeep regressionQT interval estimationQTc measurement

Autor:innen und Institutionen

  • Institute of Medical Informatics, University of Münster, Albert-Schweitzer-Campus 1/Building A11, Münster 48149, Germany.
  • Clinic for Cardiology II: Electrophysiology, University Hospital Münster, Albert-Schweitzer-Campus 1/Building A1, Münster 48149, Germany.
  • Institute of Medical Data Science, Otto-von-Guericke University Magdeburg, Leipziger Str. 44/Building 2, Magdeburg 39120, Germany.

ORCID-Profile: Lucas Plagwitz, Florian Doldi, Maxim Zotov, Lucas Bickmann, Dominik Heider, Julian Varghese, Lars Eckardt, Antonius Büscher

Förderung

  • Center for Clinical Research

Zitieren

APA

Plagwitz, L., Doldi, F., Magerfleisch, J., Zotov, M., Bickmann, L., Heider, D., Varghese, J., Eckardt, L., & Büscher, A. (2025). QTcNet: a deep learning model for direct heart rate corrected QT interval estimation. Europace. https://doi.org/10.1093/europace/euaf274

Vancouver

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. doi:10.1093/europace/euaf274

BibTeX
@article{Plagwitz2025,
  author = {Plagwitz, Lucas and Doldi, Florian and Magerfleisch, Jannes and Zotov, Maxim and Bickmann, Lucas and Heider, Dominik and Varghese, Julian and Eckardt, Lars and Büscher, Antonius},
  title = {QTcNet: a deep learning model for direct heart rate corrected QT interval estimation},
  journal = {Europace},
  year = {2025},
  doi = {10.1093/europace/euaf274}
}
Kostenlos starten →