Title:
強化学習に基づくインスリンの評価
Document Type and Number:
Japanese Patent JP7019127
Kind Code:
B2
Abstract:
The optimal insulin to be delivered by an insulin infusion pump is determined by using a reinforcement learning algorithm aiming to the personalized glucose regulation. The algorithm optimizes the daily basal insulin rate and insulin: carbohydrate ratio for each patient, on the basis of his/her measured glucose profile. The proposed algorithm is able to learn in real-time patient-specific characteristics captured in the daily glucose profile and provide individualized insulin treatment. An automatic and personalized tuning method contributes in the optimisation of the algorithm's performance.
Inventors:
Mougia Kako, Stavroller
Dascalaki, Eleni
Dream, peter
Dascalaki, Eleni
Dream, peter
Application Number:
JP2019523199A
Publication Date:
February 15, 2022
Filing Date:
July 14, 2017
Export Citation:
Assignee:
Univerzite Bern
International Classes:
A61M1/00; G16H20/10; A61M5/168; A61M5/172; G06N20/00
Domestic Patent References:
| JP2014204998A |
Foreign References:
| US20150100038 |
Other References:
Elena Daskalaki, 外2名,"Personalized Tuning of a Reinforcement Learning Control Algorithm for Glucose Regulation",35th Annual International Conference of the IEEE EMBS,2013年07月03日,pp.3487-3490
Elena Daskalaki, 外2名,"Personalized Tuning of a Reinforcement Learning Control Algorithm for Glucose Regulation",35th Annual International Conference of the IEEE EMBS,2013年07月03日,pp.3487-3490
Elena Daskalaki, 外2名,"Personalized Tuning of a Reinforcement Learning Control Algorithm for Glucose Regulation",35th Annual International Conference of the IEEE EMBS,2013年07月03日,pp.3487-3490
Attorney, Agent or Firm:
Katsuyuki Ninomiya