EUVIMEDEUVIMED entdecken
Multizentrische StudieKlinische Studie

Artificial Intelligence Software for Detecting Paroxysmal Atrial Fibrillation from Sinus Rhythm Monitor ECG: Development and Clinical Trial

Yuichi Tamura iD, Tomohiro Takata, Hirohisa Taniguchi, Ryo Takemura, Mineki Takechi, Rika Takeyasu, Eiichi Watanabe, Hirotaka Yada, Yudai Tamura, Jin Iwasawa, Tadahiro Taniguchi, Satoshi Ogawa

Advances in Therapy · 2026-02 · 43 (2) · 834-847

DOI: 10.1007/s12325-025-03461-8 ↗

Kurz gefasst

Multizentrische Studie in der Zeitschrift Advances in Therapy, online erschienen am 27.12.2025. Verfasst von Yuichi Tamura und 11 weiteren Autor:innen. Beteiligte Einrichtung: Department of Cardiology, International University of Health and Welfare Mita Hospital, 1-4-3 Mita, Minato-ku, Tokyo, 108-8329, Japan. tamura.u1@gmai…. Hauptthemen laut MEDLINE: Atrial Fibrillation, Electrocardiography, Ambulatory, Artificial Intelligence, Software. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 18 Literaturangaben. Gefördert von: Japan Agency for Medical Research and Development.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

INTRODUCTION: Detecting paroxysmal atrial fibrillation (pAF) from sinus rhythm could enable earlier intervention and stroke prevention. We developed a deep-learning Holter electrocardiograph (ECG) algorithm and prospectively evaluated its patient-level performance against 7-day AF outcomes. METHODS: We curated 20,000 30-s sinus rhythm blocks (125 Hz) from Holter ECG data of patients with and without pAF, trained convolutional models with tenfold cross-validation, and assessed a separate validation set (n = 54; 27 pAF, 27 controls) to select the operating threshold. A multicenter prospective study then evaluated the algorithm using ten consecutive 30-s sinus rhythm blocks per patient with a 4/10 positive rule; patients with pAF underwent concurrent 7-day patch monitoring to anchor outcomes. RESULTS: Cross-validation during development yielded mean sensitivity 84.2% and specificity 66.2%; the best tuned model achieved 84.9% sensitivity and 69.9% specificity on the separate set. In the clinical trial, among 24 patients with AF documented within 7 days and 20 controls, the device showed sensitivity 91.7% (95% confidence interval (CI) 73.0-99.0) and specificity 65.0% (40.8-84.6). No device-related adverse events occurred. CONCLUSION: An artificial intelligence (AI) analyzing short sinus rhythm Holter segments can identify patients who develop pAF within 7 days, supporting use as a triage tool for intensified rhythm monitoring. TRIAL REGISTRATION: UMIN-CTR UMIN000047182.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Atrial FibrillationElectrocardiography, AmbulatoryArtificial IntelligenceSoftwareDeep LearningHumansFemaleMaleProspective StudiesMiddle AgedAgedAlgorithmsSensitivity and Specificity

Stichwörter der Autor:innen

Artificial intelligenceAtrial fibrillation screeningConvolutional neural networkDeep learningElectrocardiographyHolter monitoringMedical device softwareParoxysmal atrial fibrillation

Autor:innen und Institutionen

  • Department of Cardiology, International University of Health and Welfare Mita Hospital, 1-4-3 Mita, Minato-ku, Tokyo, 108-8329, Japan. tamura.u1@gmail.com.
  • Cardio Intelligence Inc., Minato-ku, Tokyo, Japan. tamura.u1@gmail.com.
  • Pulmonary Hypertension Center, International University of Health and Welfare Mita Hospital, Minato-ku, Tokyo, Japan. tamura.u1@gmail.com.
  • Cardio Intelligence Inc., Minato-ku, Tokyo, Japan.
  • Department of Cardiology, International University of Health and Welfare Mita Hospital, 1-4-3 Mita, Minato-ku, Tokyo, 108-8329, Japan.
  • Clinical and Translational Research Center, Keio University Hospital, Shinjuku-ku, Tokyo, Japan.

ORCID-Profile: Yuichi Tamura

Förderung

  • Japan Agency for Medical Research and Development

Zitieren

APA

Tamura, Y., Takata, T., Taniguchi, H., Takemura, R., Takechi, M., Takeyasu, R., Watanabe, E., Yada, H., Tamura, Y., Iwasawa, J., Taniguchi, T., & Ogawa, S. (2026). Artificial Intelligence Software for Detecting Paroxysmal Atrial Fibrillation from Sinus Rhythm Monitor ECG: Development and Clinical Trial. Advances in Therapy, 43(2), 834-847. https://doi.org/10.1007/s12325-025-03461-8

Vancouver

Tamura Y, Takata T, Taniguchi H, Takemura R, Takechi M, Takeyasu R, et al. Artificial Intelligence Software for Detecting Paroxysmal Atrial Fibrillation from Sinus Rhythm Monitor ECG: Development and Clinical Trial. Advances in Therapy. 2026;43(2):834-847. doi:10.1007/s12325-025-03461-8

BibTeX
@article{Tamura2026,
  author = {Tamura, Yuichi and Takata, Tomohiro and Taniguchi, Hirohisa and Takemura, Ryo and Takechi, Mineki and Takeyasu, Rika and Watanabe, Eiichi and Yada, Hirotaka and Tamura, Yudai and Iwasawa, Jin and Taniguchi, Tadahiro and Ogawa, Satoshi},
  title = {Artificial Intelligence Software for Detecting Paroxysmal Atrial Fibrillation from Sinus Rhythm Monitor ECG: Development and Clinical Trial},
  journal = {Advances in Therapy},
  year = {2026},
  volume = {43},
  number = {2},
  pages = {834--847},
  doi = {10.1007/s12325-025-03461-8}
}
Kostenlos starten →