EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Deep Learning‐Based Prediction Model for Cardiac Resynchronization Therapy Responders Using Electrocardiogram Data

Hitoshi Mori, Yuya Fujisaki, Syunta Higuchi, Masataka Narita, Daisuke Kawano iD, Kazuhisa Matsumoto iD, Wataru Sasaki iD, Tsukasa Naganuma, Naomichi Tanaka, Kazuhiko Kuinose, Haruka Yamazaki, Hiroki Yamazaki und 4 weitere

Journal of Cardiovascular Electrophysiology · 2026-01 · 37 (1) · 157-164

DOI: 10.1111/jce.70212 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Cardiovascular Electrophysiology, online erschienen am 02.12.2025. Verfasst von Hitoshi Mori und 15 weiteren Autor:innen. Beteiligte Einrichtung: Department of Cardiology, Saitama Medical University International Medical Center, Hidaka, Japan. Hauptthemen laut MEDLINE: Cardiac Resynchronization Therapy, Deep Learning, Electrocardiography, Heart Failure. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: This study received financial support from Abbott Medical Japan (grant number: AS2025A000019295)..

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Cardiac resynchronization therapy (CRT) is an established treatment for advanced heart failure, but approximately 30% of patients fail to respond. This study aimed to develop and evaluate deep learning models using preimplantation electrocardiogram (ECG) data to predict CRT response.

Methods

We conducted a retrospective analysis of 285 patients who underwent CRT implantations and completed a 6‐month follow‐up. Responders were defined as those exhibiting ≥ 15% left ventricular end‐systolic volume reduction. Three models were developed: ResNet‐18 model trained on ECG images, self‐supervised learning (SSL) enhanced ResNet‐18 model, and LightGBM model trained on time‐series ECG data. Model performance was evaluated using accuracy, positive predictive value (PPV), and negative predictive value (NPV), averaged across 10 random seeds. Model interpretability using Gradient‐weighted Class Activation Mapping (Grad‐CAM) was performed on 36 responder cases.

Results

The SSL + ResNet‐18 model demonstrated the most stable performance (accuracy 78.5% ± 5.5%) and PPV of 81.3%. The ResNet‐18 model achieved the highest PPV of 84.2% but had lower accuracy (74.1%) and larger variability. The LightGBM model exhibited the highest accuracy (79.4%) but the lowest PPV at 72.8%. Grad‐CAM showed that precordial leads were highlighted in 13 cases (36.1%), limb leads in 16 (44.4%), and both regions in 7 (19.4%), indicating heterogeneity in the model's focus and potential diversity in the electrical features contributing to CRT response prediction.

Conclusion

AI models using preimplantation ECG data, particularly those based on image inputs, can effectively predict CRT responders. This approach may enhance patient selection and support personalized therapy strategies in CRT management.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Cardiac Resynchronization TherapyDeep LearningElectrocardiographyHeart FailureDecision Support TechniquesSignal Processing, Computer-AssistedHumansFemaleRetrospective StudiesMalePredictive Value of TestsAgedTreatment OutcomeMiddle AgedTime FactorsVentricular Function, LeftReproducibility of ResultsRecovery of FunctionAction PotentialsClinical Decision-MakingHeart Rate

Stichwörter der Autor:innen

cardiac resynchronization therapydeep learningelectrocardiogramresponder

Autor:innen und Institutionen

  • Department of Cardiology, Saitama Medical University International Medical Center, Hidaka, Japan.
  • Sera, Inc, Meguro, Japan.
  • Department of Medical Engineer, Saitama Medical University International Medical Center, Hidaka, Japan.

ORCID-Profile: Daisuke Kawano, Kazuhisa Matsumoto, Wataru Sasaki, Ritsushi Kato

Förderung

  • This study received financial support from Abbott Medical Japan (grant number: AS2025A000019295).

Zitieren

APA

Mori, H., Fujisaki, Y., Higuchi, S., Narita, M., Kawano, D., Matsumoto, K., Sasaki, W., Naganuma, T., Tanaka, N., Kuinose, K., Yamazaki, H., Yamazaki, H., Yoshino, W., Takeda, T., Ikeda, Y., & Kato, R. (2026). Deep Learning‐Based Prediction Model for Cardiac Resynchronization Therapy Responders Using Electrocardiogram Data. Journal of Cardiovascular Electrophysiology, 37(1), 157-164. https://doi.org/10.1111/jce.70212

Vancouver

Mori H, Fujisaki Y, Higuchi S, Narita M, Kawano D, Matsumoto K, et al. Deep Learning‐Based Prediction Model for Cardiac Resynchronization Therapy Responders Using Electrocardiogram Data. Journal of Cardiovascular Electrophysiology. 2026;37(1):157-164. doi:10.1111/jce.70212

BibTeX
@article{Mori2026,
  author = {Mori, Hitoshi and Fujisaki, Yuya and Higuchi, Syunta and Narita, Masataka and Kawano, Daisuke and Matsumoto, Kazuhisa and Sasaki, Wataru and Naganuma, Tsukasa and Tanaka, Naomichi and Kuinose, Kazuhiko and Yamazaki, Haruka and Yamazaki, Hiroki and Yoshino, Wataru and Takeda, Toshiki and Ikeda, Yoshifumi and Kato, Ritsushi},
  title = {Deep Learning‐Based Prediction Model for Cardiac Resynchronization Therapy Responders Using Electrocardiogram Data},
  journal = {Journal of Cardiovascular Electrophysiology},
  year = {2026},
  volume = {37},
  number = {1},
  pages = {157--164},
  doi = {10.1111/jce.70212}
}
Kostenlos starten →