EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Creating a general-purpose generative model for healthcare data based on multiple clinical studies

Hiroshi Maruyama iD, Kotatsu Bito iD, Yuki Saito, Masanobu Hibi, Shun Katada, Aya Kawakami, Kenta Oono, Nontawat Charoenphakdee, Zhengyan Gao, Hideyoshi Igata, Masashi Yoshikawa, Yoshiaki Ota und 5 weitere

PLOS Digital Health · 05.11.2025 · 4 (11) · e0001059

DOI: 10.1371/journal.pdig.0001059 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS Digital Health, online erschienen am 05.11.2025. Verfasst von Hiroshi Maruyama und 16 weiteren Autor:innen. Beteiligte Einrichtung: Kao Corporation, Chuo-ku, Tokyo, Japan. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Kao Corporation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Data for healthcare applications are typically customized for specific purposes but are often difficult to access due to high costs and privacy concerns. Rather than prepare separate datasets for individual applications, we propose a novel approach: building a general-purpose generative model applicable to virtually any type of healthcare application. This generative model encompasses a broad range of human attributes, including age, sex, anthropometric measurements, blood components, physical performance metrics, and numerous healthcare-related questionnaire responses. To achieve this goal, we integrated the results of multiple clinical studies into a unified training dataset and developed a generative model to replicate its characteristics. The model can estimate missing attribute values from known attribute values and generate synthetic datasets for various applications. Our analysis confirmed that the model captures key statistical properties of the training dataset, including univariate distributions and bivariate relationships. We demonstrate the model’s practical utility through multiple real-world applications, illustrating its potential impact on predictive, preventive, and personalized medicine.

Autor:innen und Institutionen

  • Kao Corporation, Chuo-ku, Tokyo, Japan.
  • Preferred Networks Inc., Chiyoda-ku, Tokyo, Japan.
  • Research into Artifacts, Center for Engineering, The University of Tokyo, Bunkyo-ku, Tokyo, Japan.
  • Digital Business Creation, Kao Corporation, Chuo-ku, Tokyo, Japan.
  • Human Health Care Product Research Laboratories, Kao Corporation, Sumida-ku, Tokyo, Japan.

ORCID-Profile: Hiroshi Maruyama, Kotatsu Bito

Förderung

  • Kao Corporation

Zitieren

APA

Maruyama, H., Bito, K., Saito, Y., Hibi, M., Katada, S., Kawakami, A., Oono, K., Charoenphakdee, N., Gao, Z., Igata, H., Yoshikawa, M., Ota, Y., Okui, H., Akita, K., Yamaguchi, S., Sugawara, Y., & Maeda, S. I. (2025). Creating a general-purpose generative model for healthcare data based on multiple clinical studies. PLOS Digital Health, 4(11), e0001059. https://doi.org/10.1371/journal.pdig.0001059

Vancouver

Maruyama H, Bito K, Saito Y, Hibi M, Katada S, Kawakami A, et al. Creating a general-purpose generative model for healthcare data based on multiple clinical studies. PLOS Digital Health. 2025;4(11):e0001059. doi:10.1371/journal.pdig.0001059

BibTeX
@article{Maruyama2025,
  author = {Maruyama, Hiroshi and Bito, Kotatsu and Saito, Yuki and Hibi, Masanobu and Katada, Shun and Kawakami, Aya and Oono, Kenta and Charoenphakdee, Nontawat and Gao, Zhengyan and Igata, Hideyoshi and Yoshikawa, Masashi and Ota, Yoshiaki and Okui, Hiroki and Akita, Kei and Yamaguchi, Shoichiro and Sugawara, Yohei and Maeda, Shin-Ichi},
  title = {Creating a general-purpose generative model for healthcare data based on multiple clinical studies},
  journal = {PLOS Digital Health},
  year = {2025},
  volume = {4},
  number = {11},
  pages = {e0001059},
  doi = {10.1371/journal.pdig.0001059}
}
Kostenlos starten →