In silico evaluation of pramlintide dosing algorithms in artificial pancreas systems
Pramlintide's capability to delay gastric emptying has motivated its use in artificial pancreas systems, accompanying insulin as a control action. Due to the scarcity of pramlintide simulation models in the literature, in silico testing of insulin-plus-pramlintide strategies is not widely used. This work incorporates a recent pramlintide pharmacokinetics/pharmacodynamics model into the T1DM UVA/Padova simulator to adjust and validate four insulin-plus-pramlintide control algorithms. The proposals are based on an existing insulin controller and administer pramlintide either as independent boluses or as a ratio of the insulin infusion. The results of the insulin-pramlintide algorithms are compared against their insulin-alone counterparts, showing an improvement in the time in range between 3.00\% and 10.53\%, consistent with results reported in clinical trials in the literature. Future work will focus on individualizing the pramlintide model to the patients' characteristics and evaluating the implemented strategies under more challenging scenarios.
Code (0)
등록된 구현이 없습니다.
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
An AI-enabled dual-hormone model predictive control algorithm that delivers insulin and pramlintide
Current closed-loop insulin delivery algorithms need to be informed of carbohydrate intake disturbances. This can be a burden on people using these systems. Pramlintide is a hormone that delays gastric emptying, which en…
Model Predictive ControlAn Explainable Deep Reinforcement Learning Model for Warfarin Maintenance Dosing Using Policy Distillation and Action Forging
Deep Reinforcement Learning is an effective tool for drug dosing for chronic condition management. However, the final protocol is generally a black box without any justification for its prescribed doses. This paper addre…
Deep Reinforcement LearningManagementFlexible Blood Glucose Control: Offline Reinforcement Learning from Human Feedback
Reinforcement learning (RL) has demonstrated success in automating insulin dosing in simulated type 1 diabetes (T1D) patients but is currently unable to incorporate patient expertise and preference. This work introduces …
Offline RLReinforcement Learning (RL)Are Large Language Models Dynamic Treatment Planners? An In Silico Study from a Prior Knowledge Injection Angle
Reinforcement learning (RL)-based dynamic treatment regimes (DTRs) hold promise for automating complex clinical decision-making, yet their practical deployment remains hindered by the intensive engineering required to in…
Reinforcement LearningPrompt EngineeringClinical KnowledgeOptimizing Warfarin Dosing using Deep Reinforcement Learning
Warfarin is a widely used anticoagulant, and has a narrow therapeutic range. Dosing of warfarin should be individualized, since slight overdosing or underdosing can have catastrophic or even fatal consequences. Despite m…
Deep Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)