Personalized glucose forecasting for people with type 1 diabetes using large language models
LLM-based models provided similar MAE values to state-of-the-art models but presented a reduced variability. The proposed personalized approach obtained the best results for short-term periods. Our work contributes to developing personalized glucose prediction models for enhancing glycemic control, reducing diabetes-related complications.
Authors
- David Chushig-Muzo (ORCID: https://orcid.org/0000-0001-5585-2305)
- Ana M. Wägner (ORCID: https://orcid.org/0000-0002-7663-9308)
- Conceição Granja (ORCID: https://orcid.org/0000-0002-3028-8899)
- Cristina Soguero-Ruíz (ORCID: https://orcid.org/0000-0001-5817-989X)
- Francisco J. Lara-Abelenda (ORCID: https://orcid.org/0000-0001-5565-8203)
- Pablo Peiro-Corbacho
Institutions
- Universidad de Las Palmas de Gran Canaria (ES)
- University Hospital of North Norway (NO)
- Universidad Rey Juan Carlos (ES)
Publication Details
- Journal
- Computer Methods and Programs in Biomedicine
- Published
- 2025-04-04
- DOI
- https://doi.org/10.1016/j.cmpb.2025.108737
- Citations
- 10
- Primary Topic
- Diabetes Management and Research
- Type
- article
- Field-Weighted Citation Impact
- 12.95
Funders
- European Commission
- Horizon 2020 Framework Programme
- Agencia Estatal de Investigación