Hybrid Control Policy for Artificial Pancreas via Ensemble Deep Reinforcement Learning.

Journal: IEEE transactions on bio-medical engineering
PMID:

Abstract

OBJECTIVE: The artificial pancreas (AP) shows promise for closed-loop glucose control in type 1 diabetes mellitus (T1DM). However, designing effective control policies for the AP remains challenging due to complex physiological processes, delayed insulin response, and inaccurate glucose measurements. While model predictive control (MPC) offers safety and stability through the dynamic model and safety constraints, it lacks individualization and is adversely affected by unannounced meals. Conversely, deep reinforcement learning (DRL) provides personalized and adaptive strategies but struggles with distribution shifts and substantial data requirements.

Authors

  • Wenzhou Lv
  • Tianyu Wu
  • Luolin Xiong
  • Liang Wu
    Clinical and Research Center of AIDS, Beijing Ditan Hospital, Capital Medical University, Beijing, China.
  • Jian Zhou
    CTIQ, Canon Medical Research USA, Inc., Vernon Hills, 60061, USA.
  • Yang Tang
    School of Science, Jiangsu University, Zhenjiang, China.
  • Feng Qian
    Department of Neurosurgery, Anhui No. 2 Provincial People's Hospital, Hefei, Anhui, China.