EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Evaluation of Federated Learning Using Standardized EHR Data in Japan

Koutarou Matsumoto, Saori Tou, Yuta Nakamura, Asato Hashinokuchi, Fumihiko Kinoshita, Hideki Nakaguma, Yukio Kozuma, Rui Sugeta, Yi-Ju Tseng, Yasunobu Nohara, Takanori Yamashita, Yoshifumi Wakata und 5 weitere

Studies in Health Technology and Informatics · 2025

DOI: 10.3233/shti250996 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Studies in Health Technology and Informatics, 2025. Verfasst von Koutarou Matsumoto und 16 weiteren Autor:innen. Beteiligte Einrichtung: Department of Health Care Administration and Management, Graduate School of Medical Sciences, Kyushu University. Hauptthemen laut MEDLINE: Electronic Health Records, Thoracic Surgery, Video-Assisted, Confidentiality, Information Dissemination. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This study addresses privacy concerns in multi-institutional data sharing by applying federated learning (FL) to develop a predictive model for prolonged air leaks (PAL) following video-assisted thoracoscopic surgery (VATS). Utilizing standardized electronic health record (EHR) data from two hospitals in Japan, we maintained a high discriminatory accuracy by exchanging only model parameters without sharing the underlying data, thereby ensuring patient privacy. These results suggest that FL can improve the accuracy of predictive models in healthcare while protecting data privacy. However, compared with models developed using centralized data, models built with FL tended to be more influenced by facilities with larger case volumes, indicating the need for further validation.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Electronic Health RecordsThoracic Surgery, Video-AssistedConfidentialityInformation DisseminationMachine LearningJapanHumansFederated Learning

Stichwörter der Autor:innen

Federated LearningMachine LearningProlonged Air LeakVideo-Assisted Thoracoscopic SurgeryePath System

Autor:innen und Institutionen

  • Department of Health Care Administration and Management, Graduate School of Medical Sciences, Kyushu University.
  • Biostatistics Center, Kurume University.
  • Institute for Medical Information Research and Analysis, Saiseikai Kumamoto Hospital.
  • Department of Thoracic Surgery, Kyushu University Hospital.
  • Department of Computer Science, National Yang Ming Chiao Tung University.
  • Big Data Science and Technology, Faculty of Advanced Science and Technology, Kumamoto University.

Zitieren

APA

Matsumoto, K., Tou, S., Nakamura, Y., Hashinokuchi, A., Kinoshita, F., Nakaguma, H., Kozuma, Y., Sugeta, R., Tseng, Y. J., Nohara, Y., Yamashita, T., Wakata, Y., Takenaka, T., Iwatani, K., Soejima, H., Nakashima, N., & Kamouchi, M. (2025). Evaluation of Federated Learning Using Standardized EHR Data in Japan. Studies in Health Technology and Informatics. https://doi.org/10.3233/shti250996

Vancouver

Matsumoto K, Tou S, Nakamura Y, Hashinokuchi A, Kinoshita F, Nakaguma H, et al. Evaluation of Federated Learning Using Standardized EHR Data in Japan. Studies in Health Technology and Informatics. 2025. doi:10.3233/shti250996

BibTeX
@article{Matsumoto2025,
  author = {Matsumoto, Koutarou and Tou, Saori and Nakamura, Yuta and Hashinokuchi, Asato and Kinoshita, Fumihiko and Nakaguma, Hideki and Kozuma, Yukio and Sugeta, Rui and Tseng, Yi-Ju and Nohara, Yasunobu and Yamashita, Takanori and Wakata, Yoshifumi and Takenaka, Tomoyoshi and Iwatani, Kazunori and Soejima, Hidehisa and Nakashima, Naoki and Kamouchi, Masahiro},
  title = {Evaluation of Federated Learning Using Standardized EHR Data in Japan},
  journal = {Studies in Health Technology and Informatics},
  year = {2025},
  doi = {10.3233/shti250996}
}
Kostenlos starten →