Enhancing Antidiabetic Drug Selection Using Transformers: Machine-Learning Model Development
The proposed model demonstrates the feasibility of accurately predicting the next prescribed drugs. This model, trained from the past prescriptions of endocrinologists, has the potential to provide information that can assist nonspecialists in making diabetes-treatment decisions. Future studies will focus on incorporating important factors such as prescription contraindications and constraints to enhance safety, as well as leveraging large-scale clinical data across multiple hospitals to improve the generalizability of the model.
Authors
- Tomohisa Seki (ORCID: https://orcid.org/0000-0002-4281-135X)
- Hisashi Kurasawa (ORCID: https://orcid.org/0000-0001-7599-6277)
- Eri Nakahara (ORCID: https://orcid.org/0000-0002-0199-3249)
- Nagisa Shiomi
- Akinori Fujino (ORCID: https://orcid.org/0000-0003-3377-3539)
- Kazuhiko Ohe (ORCID: https://orcid.org/0000-0002-4296-9536)
- Kayo Waki (ORCID: https://orcid.org/0000-0003-0046-2523)
- Hiroshi Nakashima (ORCID: https://orcid.org/0000-0001-6269-1386)
Institutions
- NTT (Japan) (JP)
- University of Tokyo Hospital (JP)
Publication Details
- Journal
- JMIR Medical Informatics
- Published
- 2025-06-02
- DOI
- https://doi.org/10.2196/67748
- Primary Topic
- Machine Learning in Healthcare
- Type
- article
- Field-Weighted Citation Impact
- 0.00