Interpretable Multihorizon Glucose Forecasting for Assessing Nutritional Information Impact in Type 1 Diabetes Management: Model Development and Validation Study
Carlos Gallardo-García, M Elena Hernando, David Subías, Mercedes Rigla, Gema García-Sáez, Andrew Coristine · 2026
Read Interpretable Multihorizon Glucose Forecasting for Assessing Nutritional Information Impact in Type 1 Diabetes Management: Model Development and Validation Study by Carlos Gallardo-García, M Elena Hernando, David Subías, Mercedes Rigla, Gema García-Sáez, Andrew Coristine (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/PMC13592460.txt.
Description
Carlos Gallardo-García and five colleagues build glucose forecasting models for type 1 diabetes that look past carbohydrate counts alone. Fat and protein also sway how blood sugar rises after a meal, yet most forecasters ignore them. Their models learned from sensor, insulin, and meal records of 351 adults, covering more than 15,000 meals. Forecasts ran up to four hours ahead, with built in tools to show which inputs drove each call.
Adding fat and protein sharpened early forecasts, cutting average error clearly. For later hours, splitting sugars from complex carbohydrates on top of fat and protein worked best. Attribution checks partly matched that split. The team cautions that the gains are modest and non causal, and that outside testing must come first.
Catalog record
| CREATOR | Carlos Gallardo-García, M Elena Hernando, David Subías, Mercedes Rigla, Gema García-Sáez, Andrew Coristine |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 52 KB |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |