The use of reinforcement learning algorithms to meet the challenges of an artificial pancreas

By M. Bothe, Luke Dickens, Katrin Reichel, A. Tellmann, B. Ellger, M. Westphal, Aldo A. Faisal. 2013

131 citations recorded by the source corpus.

Subfields: Endocrinology, Diabetes and Metabolism, 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 Surgery

Citations in the corpus

Optimal medication dosing from suboptimal clinical examples: A deep reinforcement learning approach (2016, methodology): “Application of RL to design of clinical trials and adjustment of clinical treatments have been previously suggested in the literature [15], [16], [17].”
On-line policy learning and adaptation for real-time personalization of an artificial pancreas (2015, background): “Model-based RL is a promising alternative to develop adaptive personalization techniques to control blood glucose since RL algorithms can quantitatively predict and measure the performance of selected actions (Bothe et al., 2013; Daskalaki, Diem, & Mougiakakou, 2013).”
Deep Reinforcement Learning for Closed-Loop Blood Glucose Control (2020, background): “Despite its successes, RL has yet to be fully explored as a solution for a closed-loop AP system (Bothe et al., 2013).”
Artificial intelligence, bias and clinical safety (2019, unknown): “…in medicine, but one can imagine a future where ‘closed loop’ applications, such as subcutaneous insulin pumps driven by information from wearable sensors, 33 or automated ventilator control driven by physiological monitoring data in intensive care, 34 are directly controlled by AI algorithms.”
Artificial Intelligence in Surgery: Promises and Perils (2018, methodology): “One can conceptualize reinforcement learning as the computer science equivalent of operant conditioning(9) and is useful for automated tuning of predictions or actions, such as controlling an artificial pancreas system to fine-tune the measurement and delivery of insulin to diabetic patients.(10) ML”
Artificial Intelligence for Diabetes Management and Decision Support: Literature Review (2018, methodology): “Another AI method that has been increasingly adopted in the area of control algorithms is the so-called reinforcement algorithm [25].”
Model-Free Machine Learning in Biomedicine: Feasibility Study in Type 1 Diabetes (2016, background): “The advantages of ML and RL illustrate a promising path towards the resolution of the AP challenges, as has been recently recognised and reported [32], [33].”
The Actor Search Tree Critic (ASTC) for Off-Policy POMDP Learning in Medical Decision Making (2018, methodology): “Automatic treatment optimisation based on reinforcement learning has been explored in simulated patients for HIV therapy [4] using fitted-Q iteration, dynamic insulin dosage in diabetes using model-based reinforcement learning [5], and anaesthesia depth control using actor-critic [6].”
Control of Blood Glucose for Type-1 Diabetes by Using Reinforcement Learning with Feedforward Algorithm (2018, background): “Recently, together with the development of artificial intelligence and machine learning, reinforcement learning (RL) has emerged as a data-driven method to control unknown nonlinear systems [6, 7] and has been used as a long-termmanagement tool for chronic diseases [8, 9].”