Evaluation of Federated Learning Using Standardized EHR Data in Japan.

Journal: Studies in health technology and informatics
Published Date: Aug 7, 2025

Abstract

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.

Authors

  • Koutarou Matsumoto
    Saiseikai Kumamoto Hospital, Kumamoto, Japan.
  • Saori Tou
    Department of Health Care Administration and Management, Graduate School of Medical Sciences, Kyushu University.
  • Yuta Nakamura
    Division of Radiology and Biomedical Engineering, Graduate School of Medicine, The University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, Tokyo, 113-8655, Japan. yutanakamura-tky@umin.ac.jp.
  • Asato Hashinokuchi
    Department of Thoracic Surgery, Kyushu University Hospital.
  • Fumihiko Kinoshita
    Department of Thoracic Surgery, Kyushu University Hospital.
  • Hideki Nakaguma
    Saiseikai Kumamoto Hospital, Kumamoto Japan.
  • Yukio Kozuma
    Institute for Medical Information Research and Analysis, Saiseikai Kumamoto Hospital.
  • Rui Sugeta
    Institute for Medical Information Research and Analysis, Saiseikai Kumamoto Hospital.
  • Yi-Ju Tseng
    Department of Laboratory Medicine, Chang Gung Memorial Hospital at Linkou, Taoyuan City, Taiwan.
  • Yasunobu Nohara
    Medical Information Center, Kyushu University Hospital, Fukuoka, Japan.
  • Takanori Yamashita
    Medical Information Center, Kyushu University Hospital, Fukuoka Japan. Electronic address: t-yama@med.kyushu-u.ac.jp.
  • Yoshifumi Wakata
    Kyushu University Hospital, Fukuoka, Japan.
  • Tomoyoshi Takenaka
    Department of Thoracic Surgery, Kyushu University Hospital.
  • Kazunori Iwatani
    Division of Respiratory Surgery, Saiseikai Kumamoto Hospital.
  • Hidehisa Soejima
    Saiseikai Kumamoto Hospital, Kumamoto Japan.
  • Naoki Nakashima
    Medical Information Center, Kyushu University Hospital, Fukuoka, Japan.
  • Masahiro Kamouchi
    Department of Health Care Administration and Management, Graduate School of Medical Sciences Kyushu University Fukuoka Japan.

Keywords

External Resources

Popular Topics
Recent Journals