An Actor-Critic based controller for glucose regulation in type 1 diabetes

By Elena Daskalaki, Peter Diem, Stavroula G. Mougiakakou. 2013

49 citations recorded by the source corpus.

Subfields: Endocrinology, Diabetes and Metabolism, Molecular Biology, Surgery

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Endocrinology, Diabetes and Metabolism

In Molecular Biology

In Surgery

Citations in the corpus

Reinforcement Learning in Healthcare: A Survey (2019, neutral): “tatic behaviors of the Actor component. The authors then proposed using daily updates of the average basal rate (BR) and the insulin-to-carbohydrate (IC) ratio in order to optimize glucose regulation [117], and using estimation of information transfer (IT) from insulin to glucose for automatic and p”
A Batch, Off-Policy, Actor-Critic Algorithm for Optimizing the Average Reward (2016, methodology): “These algorithms have been used in health, for example for on-policy, online glucose regulation in Type 1 diabetes (Daskalaki et al., 2013).”
A Dual Mode Adaptive Basal-Bolus Advisor Based on Reinforcement Learning (2019, methodology): “As in [14], thePe in this work consists of three parts: the linear deterministic control action Pa , the supervisory control action Ps, and the exploratory part N(0, σ), which could be presented as Gaussian noise with zero mean and standard deviation σ.”
On-line policy learning and adaptation for real-time personalization of an artificial pancreas (2015, methodology): “Non-parametric models are true data models suitable to work with erratic glucose–insulin dynamics (Daskalaki et al., 2013, 2012), which makes them a powerful tool for adaptive control by reducing the problem of model bias, which frequently occurs when deterministic models are used.”
Artificial Intelligence for Diabetes Management and Decision Support: Literature Review (2018, methodology): “Daskalaki et al presented an adaptive, patient-specific BG control strategy based on the Actor-Critic learning approach and tested their approach on 28 virtual T1D patients (adults, adolescents, and children) [26].”
Model-Free Machine Learning in Biomedicine: Feasibility Study in Type 1 Diabetes (2016, methodology): “The weights ah and al are used for scaling the hypo- and hyperglycaemia components and are chosen as ah = 1 and al = 10 [35].”