Skip to Main content Skip to Navigation
Conference papers

Challenging common bolus advisor for self-monitoring type-I diabetes patients using Reinforcement Learning

Abstract : Patients with diabetes who are self-monitoring have to decide right before each meal how much insulin they should take. A standard bolus advisor exists, but has never actually been proven to be optimal in any sense. We challenged this rule applying Reinforcement Learning techniques on data simulated with T1DM, an FDA-approved simulator developped by [3] modeling the gluco-insulin interaction. Results show that the optimal bolus rule is fairly different from the standard bolus advisor, and if followed can actually avoid hypoglycemia episodes.
Document type :
Conference papers
Complete list of metadata

https://hal.inria.fr/hal-03161776
Contributor : Erwan Le Pennec <>
Submitted on : Monday, March 8, 2021 - 9:33:08 AM
Last modification on : Tuesday, March 9, 2021 - 3:29:20 AM

File

2020-LLPAB-DSHealth.pdf
Files produced by the author(s)

Identifiers

Collections

Citation

Frédéric Logé, Erwann Le Pennec, Habiboulaye Amadou-Boubacar. Challenging common bolus advisor for self-monitoring type-I diabetes patients using Reinforcement Learning. DSHeath, 2020, San Diego, United States. ⟨10.1145/nnnnnnn.nnnnnnn⟩. ⟨hal-03161776⟩

Share

Metrics

Record views

25

Files downloads

110