Controlling blood glucose variability under uncertainty usingreinforcement learning and Gaussian processes

MARIANO DE PAULA; LUIS AVILA; ERNESTO MARTÍNEZ

APPLIED SOFT COMPUTING

ELSEVIER SCIENCE BV

Lugar: Amsterdam; Año: 2015 vol. 35 p. 310 - 332

1568-4946

tAutomated control of blood glucose (BG) concentration with a fully automated artificial pancreas will certainly improve the quality of life for insulin-dependent patients. Closed-loop insulin delivery is challenging due to inter- and intra-patient variability, errors in glucose sensors and delays in insulin absorption. Responding to the varying activity levels seen in outpatients, with unpredictable and unre-ported food intake, and providing the necessary personalized control for individuals is a challenging task for existing control algorithms. A novel approach for controlling glycemic variability using simulation-based learning is presented. A policy iteration algorithm that combines reinforcement learning with Gaussian process approximation is proposed. To account for multiple sources of uncertainty, a control policy is learned off-line using an Ito stochastic model of the glucose-insulin dynamics. For safety and performance, only relevant data are sampled through Bayesian active learning. Results obtained demon-strate that a generic policy is both safe and efficient for controlling subject-specific variability due to a patient?s lifestyle and its distinctive metabolic response.