Personalized Type 1 Diabetes Management: Reinforcement Learning–Based Insulin Dosing and Glucose Forecasting
Ernest M Taku, Vibhuti Gupta, Ashutosh Singhal, Sheyu Li · 2026
Read Personalized Type 1 Diabetes Management: Reinforcement Learning–Based Insulin Dosing and Glucose Forecasting by Ernest M Taku, Vibhuti Gupta, Ashutosh Singhal, Sheyu Li (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/pmc-13233011.txt.
Description
Ernest M Taku and colleagues published a 2026 study on personalizing insulin dosing for type 1 diabetes with reinforcement learning, a form of artificial intelligence that learns by trial and reward. Fixed insulin schedules struggle because glucose responds to meals, activity, stress, and the body's own rhythms. The team built a deep Q-network agent that adjusts dose suggestions from continuous glucose monitor data.
Training used the OhioT1DM dataset, covering eight weeks of glucose readings, insulin doses, and activity records for twelve people. The agent viewed the previous two hours of data and chose among small dose steps, earning rewards for keeping glucose between 70 and 180 milligrams per deciliter. The paper evaluates predicted against actual glucose traces, aiming at safer, more personal dosing support.
Catalog record
| CREATOR | Ernest M Taku, Vibhuti Gupta, Ashutosh Singhal, Sheyu Li |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 58 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |