A safe-enhanced fully closed-loop artificial pancreas controller based on deep reinforcement learning.
Patients with type 1 diabetes and their physicians have long desired a fully closed-loop artificial pancreas (AP) system that can alleviate the burden of blood glucose regulation. Although deep reinforcement learning (DRL) methods theoretically enable adaptive insulin dosing control, they face numer...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2025-01-01
|
| Series: | PLoS ONE |
| Online Access: | https://doi.org/10.1371/journal.pone.0317662 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832540209358569472 |
|---|---|
| author | Yan Feng Zhao Jun Kit Chaw Mei Choo Ang Yiqi Tew Xiao Yang Shi Lin Liu Xiang Cheng |
| author_facet | Yan Feng Zhao Jun Kit Chaw Mei Choo Ang Yiqi Tew Xiao Yang Shi Lin Liu Xiang Cheng |
| author_sort | Yan Feng Zhao |
| collection | DOAJ |
| description | Patients with type 1 diabetes and their physicians have long desired a fully closed-loop artificial pancreas (AP) system that can alleviate the burden of blood glucose regulation. Although deep reinforcement learning (DRL) methods theoretically enable adaptive insulin dosing control, they face numerous challenges, including safety and training efficiency, which have hindered their clinical application. This paper proposes a safe and efficient adaptive insulin delivery controller based on DRL. It employed ten tricks to enhance the proximal policy optimization (PPO) algorithm, improving training efficiency. Additionally, a dual safety mechanism of 'proactive guidance + reactive correction' was introduced to reduce the risks of hyperglycemia and hypoglycemia and to prevent emergencies. Performance evaluations in the Simglucose simulator demonstrate that the proposed controller achieved an 87.45% time in range (TIR) median, superior to baseline methods, with a lower incidence of hypoglycemia, notably eliminating severe hypoglycemia and treatment failures. These encouraging results indicate that the DRL-based fully closed-loop AP controller has taken an essential step toward clinical implementation. |
| format | Article |
| id | doaj-art-c7560e38d880486e93dccc374a97a7f2 |
| institution | Kabale University |
| issn | 1932-6203 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj-art-c7560e38d880486e93dccc374a97a7f22025-02-05T05:32:06ZengPublic Library of Science (PLoS)PLoS ONE1932-62032025-01-01201e031766210.1371/journal.pone.0317662A safe-enhanced fully closed-loop artificial pancreas controller based on deep reinforcement learning.Yan Feng ZhaoJun Kit ChawMei Choo AngYiqi TewXiao Yang ShiLin LiuXiang ChengPatients with type 1 diabetes and their physicians have long desired a fully closed-loop artificial pancreas (AP) system that can alleviate the burden of blood glucose regulation. Although deep reinforcement learning (DRL) methods theoretically enable adaptive insulin dosing control, they face numerous challenges, including safety and training efficiency, which have hindered their clinical application. This paper proposes a safe and efficient adaptive insulin delivery controller based on DRL. It employed ten tricks to enhance the proximal policy optimization (PPO) algorithm, improving training efficiency. Additionally, a dual safety mechanism of 'proactive guidance + reactive correction' was introduced to reduce the risks of hyperglycemia and hypoglycemia and to prevent emergencies. Performance evaluations in the Simglucose simulator demonstrate that the proposed controller achieved an 87.45% time in range (TIR) median, superior to baseline methods, with a lower incidence of hypoglycemia, notably eliminating severe hypoglycemia and treatment failures. These encouraging results indicate that the DRL-based fully closed-loop AP controller has taken an essential step toward clinical implementation.https://doi.org/10.1371/journal.pone.0317662 |
| spellingShingle | Yan Feng Zhao Jun Kit Chaw Mei Choo Ang Yiqi Tew Xiao Yang Shi Lin Liu Xiang Cheng A safe-enhanced fully closed-loop artificial pancreas controller based on deep reinforcement learning. PLoS ONE |
| title | A safe-enhanced fully closed-loop artificial pancreas controller based on deep reinforcement learning. |
| title_full | A safe-enhanced fully closed-loop artificial pancreas controller based on deep reinforcement learning. |
| title_fullStr | A safe-enhanced fully closed-loop artificial pancreas controller based on deep reinforcement learning. |
| title_full_unstemmed | A safe-enhanced fully closed-loop artificial pancreas controller based on deep reinforcement learning. |
| title_short | A safe-enhanced fully closed-loop artificial pancreas controller based on deep reinforcement learning. |
| title_sort | safe enhanced fully closed loop artificial pancreas controller based on deep reinforcement learning |
| url | https://doi.org/10.1371/journal.pone.0317662 |
| work_keys_str_mv | AT yanfengzhao asafeenhancedfullyclosedloopartificialpancreascontrollerbasedondeepreinforcementlearning AT junkitchaw asafeenhancedfullyclosedloopartificialpancreascontrollerbasedondeepreinforcementlearning AT meichooang asafeenhancedfullyclosedloopartificialpancreascontrollerbasedondeepreinforcementlearning AT yiqitew asafeenhancedfullyclosedloopartificialpancreascontrollerbasedondeepreinforcementlearning AT xiaoyangshi asafeenhancedfullyclosedloopartificialpancreascontrollerbasedondeepreinforcementlearning AT linliu asafeenhancedfullyclosedloopartificialpancreascontrollerbasedondeepreinforcementlearning AT xiangcheng asafeenhancedfullyclosedloopartificialpancreascontrollerbasedondeepreinforcementlearning AT yanfengzhao safeenhancedfullyclosedloopartificialpancreascontrollerbasedondeepreinforcementlearning AT junkitchaw safeenhancedfullyclosedloopartificialpancreascontrollerbasedondeepreinforcementlearning AT meichooang safeenhancedfullyclosedloopartificialpancreascontrollerbasedondeepreinforcementlearning AT yiqitew safeenhancedfullyclosedloopartificialpancreascontrollerbasedondeepreinforcementlearning AT xiaoyangshi safeenhancedfullyclosedloopartificialpancreascontrollerbasedondeepreinforcementlearning AT linliu safeenhancedfullyclosedloopartificialpancreascontrollerbasedondeepreinforcementlearning AT xiangcheng safeenhancedfullyclosedloopartificialpancreascontrollerbasedondeepreinforcementlearning |