Abstract. Estimation of future glucose concentration is important for diabetes management. To develop a model predictive control (MPC) system that measures the glucose concentration and automatically inject the amount of insulin needed to keep the glucose level within its normal range, the accuracy of the predicted glucose level and the longer prediction time are major factors affecting the performance of the control system. The predicted glucose values can be used for early hypoglycemic/hyperglycemic alarms for adjustment of insulin injections or insulin infusion rates of manual or automated pumps. Recent developments in continuous glucose monitoring (CGM) devices open new opportunities for glycemia management of diabetic patients. In this article a new technique, which uses a recurrent neural network (RNN) and data obtained from CGM device, is proposed to predict the future values of the glucose concentration for prediction horizons (PH) of 15, 30, 45, 60 minutes. The results of the proposed technique is evaluated and compared relative to that obtained from a feed forward neural network prediction model (NNM). Our results indicate that, the RNN is better in prediction than the NNM for the relatively long prediction horizons.

Current insulin therapy for patients with type 1 diabetes often results in high variability in blood glucose concentration and may cause hyper-and hypoglycemic episodes. Closing the glucose control loop with a fully automated control system improves the quality of life for insulin-dependent patients. This paper presents a nonlinear model predictive control technique for glucose regulation in type 1 diabetic patients. The proposed technique uses a neural network as a nonlinear model for prediction of future glucose values and a fuzzy logic controller (FLC) to determine the insulin dose required to regulate the blood glucose level, especially after unmeasured meals. In the proposed technique, to avoid errors of meal estimation, the patient is not required to enter any data such as the meal time and size which was, in previous systems, necessary to determine the insulin bolus. The use of neural networks in predicting future glucose levels helps the proposed control strategy to handle delays associated with insulin absorption and time-lag between subcutaneous glucose readings and the plasma glucose level. The FLC uses the predicted glucose values to determine the required insulin bolus. A feed forward neural network (FFNN) and a recurrent neural network (RNN) are tested and evaluated as nonlinear glucose prediction models. Simulation results for three meal challenges are demonstrated. our results indicate that, the use of a neural network as a predictor along with a FL controller can decrease the postprandial glucose concentration, avoids hyper glycemia, and dynamically responds to glycemic challenges. The simulation results also indicate that, the use of a RNN in glucose prediction gives better results than the use of a FFNN. The RNN provides much better prediction performance than the FFNN especially at longer prediction horizons.

No abstract

Type-1 diabetes is a disease characterized by high blood-glucose level. Using a fully automated closed loop control system improves the quality of life for type1 diabetic patients. In this paper, a scalable closed loop blood glucose regulation system which is tuned to each patient is presented. This control system doesn't need any data entry from the patient. A recurrent neural network (RNN) is used as a nonlinear pred ictor and a fuzzy logic controller (FLC) is used to determine the insulin dosage which is required to regulate the blood glucose level. The insulin infusion is restricted by calculation of insulin on board (IOB) wh ich avoids overdosing of insulin. The performance of the proposed NMPC is evaluated by applying fu ll day meal regime to each patient. The evaluation includes testing in relation to specific life style condition, i.e. fasting, postprandial, fault meal estimat ion, and exercise as a metabolic disturbance. Our simu lation results indicate that, the use of a RNN along with a FLC can decrease the postprandial glucose concentration. The proposed controller can be used in fasting and can avoid severe hypo or hyper-glycemia during fasting. It can also decrease the postprandial g lucose concentration and can dynamically respond to different glycemic challenges. Fig.6: the controlled glucose of patient #1 using the proposed control system for (a) fasting (no meals), (b) scheduled meals, (c) 50% increasing in a meal, (d) 10% increasing in a meal, (e) 10% decreasing a meal, (f) 5% increasing the sensitivity, (g) 40% increasing the sensitivity(increasing the sensitivity). Fig.7: T he controlled glucose for patient #2 using the proposed control system for (a) fasting (no meals), (b) scheduled meals, (c) 50% increasing in the second meal, (d) 10% increasing in the second meal, (e) 10% decreasing in the second meal, (f) 5% increasing in the sensitivity, (g) 40% increasing in the sensitivity

No abstract