Machine learning-based reproducible prediction of type 2 diabetes subtypes
The new ML model for predicting Ahlqvist's subtypes of type 2 diabetes has great potential for application in clinical practice and cohort studies because it can classify individuals with missing HOMA2 indices and predict glycaemic control, diabetic complications and treatment outcomes with long-term consistency by using readily available variables. Future studies are needed to assess whether our approach is applicable to research and/or clinical practice in multiethnic populations.
Authors
- Hideki Katagiri (ORCID: https://orcid.org/0000-0003-1093-3704)
- Akira Narita (ORCID: https://orcid.org/0000-0002-9076-0710)
- Kenichi Tanaka (ORCID: https://orcid.org/0000-0003-4655-9355)
- Eiryo Kawakami (ORCID: https://orcid.org/0000-0001-9955-4342)
- Yoshinori Shimajiri
- Junichiro James Kazama (ORCID: https://orcid.org/0000-0001-7710-2660)
- Hiroaki Masuzaki (ORCID: https://orcid.org/0000-0002-2445-1047)
- Takafumi Ojima (ORCID: https://orcid.org/0000-0003-1197-0574)
- Hayato Tanabe (ORCID: https://orcid.org/0000-0003-4576-8032)
- Masahiro Sato (ORCID: https://orcid.org/0000-0003-1334-2950)
- Haruka Saito (ORCID: https://orcid.org/0000-0002-0482-8126)
- Gen Tamiya (ORCID: https://orcid.org/0000-0002-0597-415X)
- Akimitsu Miyake (ORCID: https://orcid.org/0000-0001-8509-1412)
- Michio Shimabukuro (ORCID: https://orcid.org/0000-0001-7835-7665)
Institutions
- Fukushima Medical University (JP)
- Chiba University (JP)
- Tohoku University (JP)
- University of the Ryukyus (JP)
- RIKEN Center for Sustainable Resource Science (JP)
- Tohoku Medical Megabank Organization (JP)
- The University of Osaka (JP)
Publication Details
- Journal
- Diabetologia
- Published
- 2024-08-21
- DOI
- https://doi.org/10.1007/s00125-024-06248-8
- Citations
- 17
- Primary Topic
- Artificial Intelligence in Healthcare
- Type
- article
- Field-Weighted Citation Impact
- 12.03
Funders
- Japan Society for the Promotion of Science
- Japan Science and Technology Agency