Prediction of blood glucose level of type 1 diabetics using response surface methodology and data mining

Abstract

In order to improve the accuracy of predicting blood glucose levels, it is necessary to obtain details about the lifestyle and to optimize the input variables dependent on diabetics. In this study, using four subjects who are type 1 diabetics, the fasting blood glucose level (FBG), metabolic rate, food intake, and physical condition are recorded for more than 5 months as a preliminary study. Then, using data mining, an estimation model of FBG is obtained, and subsequently, the trend in fluctuations in the next morning's glucose level is predicted. The subject's physical condition is self-assessed on a scale from positive (1) to negative (5), and the values are set as the physical condition variable. By adding the physical condition variable to the input variables for the data mining, the accuracy of the FBG prediction is improved. In order to determine more appropriate input variables from the biological information reflecting on the subject's glucose metabolism, response surface methodology (RSM) is employed. As a result, using the variables exhibiting positive correlations with the FBG in the RSM, the accuracy of the FBG prediction improved. Conditions could be found such that the accuracy of the predicting trends in fluctuations in blood glucose level reached around 80%. The prediction method of the trend in fluctuations in the next morning's glucose levels might be useful to improve the quality of life of type 1 diabetics through insulin treatment, and to prevent hypoglycemia.

A robust sliding mode controller with internal model for closed-loop artificial pancreas

“…There are many different models for the glucoregulatory system (see for instance [4,9,12,16,30,36]) with different structures and degrees of complexity. In this study, the model developed by Hovorka et al [15,16] has been chosen to represent the diabetic patient (virtual subject).…”

Multi-objective blood glucose control for type 1 diabetes

“…Other models such as in [20] and [11] can also be used for the derivation of the controller and future work will involve designing controller for detailed physiological models [28,35]. Data mining based models have also been effectively used for blood glucose level predictions [37].…”

Statistical Hypoglycemia Prediction

“…[3][4][5][6][7] We instead focus on simple statistical methods using only CGM data to predict/detect hypoglycemia. These methods require minimal sensors and patient input, making them more robust and potentially easier to implement commercially.…”