Challenging common bolus advisor for self-monitoring type-I diabetes patients using Reinforcement Learning - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2020

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

Résumé

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.
Fichier principal
Vignette du fichier
2020-LLPAB-DSHealth.pdf (1010.24 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03161776 , version 1 (08-03-2021)

Licence

Paternité

Identifiants

  • HAL Id : hal-03161776 , version 1

Citer

Frédéric Logé, Erwan 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. ⟨hal-03161776⟩
31 Consultations
147 Téléchargements

Partager

Gmail Facebook X LinkedIn More