Adaptive basal insulin recommender system based on Kalman filter for type 1 diabetes

Abstract

Type 1 diabetes mellitus is a chronic disease that requires those affected to self-administer insulin to control their blood glucose level. However, the estimation of the correct insulin dosage is not easy due to the complexity of glucose metabolism, which usually leads to blood glucose levels far from the optimal. This paper presents an adaptive and personalised basal insulin recommender system based on Kalman filter theory that can be used with or without continuous glucose monitoring systems. The proposed approach is tested with the UVa/PADOVA simulator with eleven virtual adult subjects. It has been tested in combination with two different bolus calculators, and the performance achieved has been compared with that obtained with the default basal doses of the simulator, which can be assumed as optimal. The achieved results demonstrate that the proposed system rapidly converges to the optimal basal dose, and it can be used with adaptive bolus calculators without the risk of instability.

Application of Artificial Intelligence Techniques for the Estimation of Basal Insulin in Patients with Type I Diabetes

“…Currently, different models have been proposed to predict the basal insulin dose using algorithms and artificial intelligence techniques [ 10 – 18 ]. Torrent-Fontbona proposes a system that calculates boluses with case-based reasoning and that in combination with Kalman filtering for baseline estimation reaches a time in the range of 83.87 + 1.35 [ 10 , 11 ]. Meanwhile, Cappon et al [ 12 ] use a NN to calculate insulin bolus with a reduction in the blood glucose risk index of 0.37, 0.23, and 0.20 versus the standard methods Scheiner, Pettus, and Edelman, respectively.…”

“…In this regard, clinical decision support systems based on artificial intelligence techniques could be useful as a strategy to close the care gaps [ 5 – 9 ]. Currently, different models have been proposed to estimate the basal insulin dose using artificial intelligence algorithms and techniques [ 10 – 18 ]. These models have shown good results in improving the time in the range of glycemic control [ 10 – 13 ].…”

“…Currently, different models have been proposed to estimate the basal insulin dose using artificial intelligence algorithms and techniques [ 10 – 18 ]. These models have shown good results in improving the time in the range of glycemic control [ 10 – 13 ]. Consequently, in this study, we aimed to evaluate different artificial intelligence models calculating basal insulin doses and estimates which could be better.…”

Generation of Virtual Patient Populations That Represent Real Type 1 Diabetes Cohorts

“…The main challenges for BG regulation in T1D are the disturbances in terms of meals, exercise, stress, and variability (inter-patient and intra-patient). The UVa/Padova simulator allows the incorporation of different meal scenarios for the virtual patient (VP) population, allowing researchers to analyze the effectiveness of a control algorithm [16][17][18][19][20][21][22], validate optimization and adaptation strategies for insulin delivery [23][24][25][26], develop disturbance detection algorithms for meals [27][28][29] and exercise [30], develop methods for mitigating the risks of hypoglycemia [31,32], and integrate machine learning algorithms into conventional diabetes therapy and bolus calculator for the treatment of T1D patients [33][34][35]. In the literature, the meal scenarios used for testing BG regulation effectiveness are based on typical values considering three meals per day [36][37][38][39][40][41][42][43][44][45][46][47].…”

A Classification System for Diabetic Patients with Machine Learning Techniques

“…It is well known that diabetes and cancer both are the most chronic diseases which have a composite relationship as when the glucose level of human body increase up to the divergent level then it leads to diabetes (Kalaiselvi and Nasira, 2014). So for finding the classification accurately in this dataset, some of the recommender system has been proposed based on adaptive and personalized basal insulin on Kalman filter theory (Torrent-Fontbona, 2018). The proposed algorithm may use with or without continuous glucose monitoring systems.…”