Nigel J C Greenwood1, Jenny E Gunton2. 1. School of Mathematics and Physics, University of Queensland, Brisbane, Australia Neuromathix, NeuroTech Research Pty Ltd nigel@neuromathix.com. 2. Westmead Clinical School, University of Sydney, Sydney, Australia Diabetes and Transcription Factors Group, Garvan Institute of Medical Research, Darlinghurst, Australia St Vincent's Clinical School, Faculty of Medicine, University of New South Wales, Kensington, Australia Diabetes and Endocrinology, Westmead Hospital, Sydney, Australia.
Abstract
BACKGROUND: This study demonstrated the novel application of a "machine-intelligent" mathematical structure, combining differential game theory and Lyapunov-based control theory, to the artificial pancreas to handle dynamic uncertainties. METHODS: Realistic type 1 diabetes (T1D) models from the literature were combined into a composite system. Using a mixture of "black box" simulations and actual data from diabetic medical histories, realistic sets of diabetic time series were constructed for blood glucose (BG), interstitial fluid glucose, infused insulin, meal estimates, and sometimes plasma insulin assays. The problem of underdetermined parameters was side stepped by applying a variant of a genetic algorithm to partial information, whereby multiple candidate-personalized models were constructed and then rigorously tested using further data. These formed a "dynamic envelope" of trajectories in state space, where each trajectory was generated by a hypothesis on the hidden T1D system dynamics. This dynamic envelope was then culled to a reduced form to cover observed dynamic behavior. A machine-intelligent autonomous algorithm then implemented game theory to construct real-time insulin infusion strategies, based on the flow of these trajectories through state space and their interactions with hypoglycemic or near-hyperglycemic states. RESULTS: This technique was tested on 2 simulated participants over a total of fifty-five 24-hour days, with no hypoglycemic or hyperglycemic events, despite significant uncertainties from using actual diabetic meal histories with 10-minute warnings. In the main case studies, BG was steered within the desired target set for 99.8% of a 16-hour daily assessment period. Tests confirmed algorithm robustness for ±25% carbohydrate error. For over 99% of the overall 55-day simulation period, either formal controller stability was achieved to the desired target or else the trajectory was within the desired target. CONCLUSIONS: These results suggest that this is a stable, high-confidence way to generate closed-loop insulin infusion strategies.
BACKGROUND: This study demonstrated the novel application of a "machine-intelligent" mathematical structure, combining differential game theory and Lyapunov-based control theory, to the artificial pancreas to handle dynamic uncertainties. METHODS: Realistic type 1 diabetes (T1D) models from the literature were combined into a composite system. Using a mixture of "black box" simulations and actual data from diabetic medical histories, realistic sets of diabetic time series were constructed for blood glucose (BG), interstitial fluid glucose, infused insulin, meal estimates, and sometimes plasma insulin assays. The problem of underdetermined parameters was side stepped by applying a variant of a genetic algorithm to partial information, whereby multiple candidate-personalized models were constructed and then rigorously tested using further data. These formed a "dynamic envelope" of trajectories in state space, where each trajectory was generated by a hypothesis on the hidden T1D system dynamics. This dynamic envelope was then culled to a reduced form to cover observed dynamic behavior. A machine-intelligent autonomous algorithm then implemented game theory to construct real-time insulin infusion strategies, based on the flow of these trajectories through state space and their interactions with hypoglycemic or near-hyperglycemic states. RESULTS: This technique was tested on 2 simulated participants over a total of fifty-five 24-hour days, with no hypoglycemic or hyperglycemic events, despite significant uncertainties from using actual diabetic meal histories with 10-minute warnings. In the main case studies, BG was steered within the desired target set for 99.8% of a 16-hour daily assessment period. Tests confirmed algorithm robustness for ±25% carbohydrate error. For over 99% of the overall 55-day simulation period, either formal controller stability was achieved to the desired target or else the trajectory was within the desired target. CONCLUSIONS: These results suggest that this is a stable, high-confidence way to generate closed-loop insulin infusion strategies.
Authors: Teresa P Monsod; Daniel E Flanagan; Fran Rife; Rebecca Saenz; Sonia Caprio; Robert S Sherwin; William V Tamborlane Journal: Diabetes Care Date: 2002-05 Impact factor: 19.112
Authors: Stephen D Patek; B Wayne Bequette; Marc Breton; Bruce A Buckingham; Eyal Dassau; Francis J Doyle; John Lum; Lalo Magni; Howard Zisser Journal: J Diabetes Sci Technol Date: 2009-03-01
Authors: Lalo Magni; Davide M Raimondo; Luca Bossi; Chiara Dalla Man; Giuseppe De Nicolao; Boris Kovatchev; Claudio Cobelli Journal: J Diabetes Sci Technol Date: 2007-11
Authors: Ling Hinshaw; Chiara Dalla Man; Debashis K Nandy; Ahmed Saad; Adil E Bharucha; James A Levine; Robert A Rizza; Rita Basu; Rickey E Carter; Claudio Cobelli; Yogish C Kudva; Ananda Basu Journal: Diabetes Date: 2013-02-27 Impact factor: 9.461