Lead Investigator: Yongwen Zhou, The Third Affiliated Hospital of SYSU
Title of Proposal Research: Reinforcement learning for personlized automated insulin delivery system among type 1 diabetes
Vivli Data Request: 10492
Funding Source: None
Potential Conflicts of Interest: None
Summary of the Proposed Research:
Calculating mealtime and appropriate adjustments during exercise do poses a significant challenges for individuals with type 1 diabetes. Currently, automated insulin delivery systems, integrating with continuous glucose monitoring, insulin pumps and algorithm had been demonstrated to improve glycemic outcomes and quality of life. However, the current widely used version were hybrid – require meal announcement and exercise for most time to achieve the more optimal control, which burdensome children, adolescents and some young adults who relatively have more challenges in adherence and diabetes management by themselves. Therefore, our study aimed to use the reinforcement learning agent to train the applied data (glucose data, insulin data, exercise and meal announcement data), employ a nerual network and mimic and enhance the algorithm process. The findings will provide a referenced strategy for us to further optimize our investigational algorithm that is under process for validation.
Requested Studies:
Type 1 Diabetes EXercise Initiative Pediatric Study (T1DexiP): The Effect of Exercise on Glycemic Control in Youth with Type 1 Diabetes
Data Contributor: Jaeb Center for Health Research Foundation, Inc.
Study ID: T1-DEXIP
Sponsor ID: T1-DEXIP
Type 1 Diabetes EXercise Initiative: The Effect of Exercise on Glycemic Control in Type 1 Diabetes Study
Data Contributor: Jaeb Center for Health Research Foundation, Inc.
Study ID: T1-DEXI
Sponsor ID: T1-DEXI