scholarly journals Analysis and design process for predicting and controlling blood glucose in Type 1 diabetic patients

2021 ◽  
Vol 16 (4) ◽  
pp. 0-0
Keyword(s):  
Blood Glucose ◽  
Absolute Error ◽  
Psychological State ◽  
Diabetic Patients ◽  
Analysis And Design ◽  
Control Blood Glucose ◽  
Insulin Requirements ◽  
Energy Equations ◽  
And Control

Engineering smart software that can monitor, predict, and control blood glucose is critical to improving patients' quality of treatments with type 1 Diabetic Mellitus (T1DM). However, ensuring a reasonable glycemic level in diabetic patients is quite challenging, as many methods do not adequately capture the complexities involved in glycemic control. This problem introduces a new level of complexity and uncertainty to the patient's psychological state, thereby making this problem nonlinear and unobservable. In this paper, we formulated a mathematical model using carbohydrate counting, insulin requirements, and the Harris-Benedict energy equations to establish the framework for predicting and controlling blood glucose level regulation in T1DM. We implemented the framework and evaluated its performance using root mean square error (RMSE) and mean absolute error (MAE) on a case study. Our framework had less error rate in terms of RMSE and MAE, which indicates a better fit with reasonable accuracy.

scholarly journals Multi-step ahead predictive model for blood glucose concentrations of type-1 diabetic patients

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Syed Mohammed Arshad Zaidi ◽  
Varun Chandola ◽  
Muhanned Ibrahim ◽  
Bianca Romanski ◽  
Lucy D. Mastrandrea ◽  
...  
Keyword(s):  
Blood Glucose ◽  
Diabetes Management ◽  
Mean Squared Error ◽  
Absolute Error ◽  
Target Range ◽  
Percentage Error ◽  
Diabetic Patients ◽  
Average Percentage ◽  
Squared Error

AbstractContinuous monitoring of blood glucose (BG) levels is a key aspect of diabetes management. Patients with Type-1 diabetes (T1D) require an effective tool to monitor these levels in order to make appropriate decisions regarding insulin administration and food intake to keep BG levels in target range. Effectively and accurately predicting future BG levels at multi-time steps ahead benefits a patient with diabetes by helping them decrease the risks of extremes in BG including hypo- and hyperglycemia. In this study, we present a novel multi-component deep learning model that predicts the BG levels in a multi-step look ahead fashion. The model is evaluated both quantitatively and qualitatively on actual blood glucose data for 97 patients. For the prediction horizon (PH) of 30 mins, the average values for root mean squared error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE), and normalized mean squared error (NRMSE) are $$23.22 \pm 6.39$$ 23.22 ± 6.39 mg/dL, 16.77 ± 4.87 mg/dL, $$12.84 \pm 3.68$$ 12.84 ± 3.68 and $$0.08 \pm 0.01$$ 0.08 ± 0.01 respectively. When Clarke and Parkes error grid analyses were performed comparing predicted BG with actual BG, the results showed average percentage of points in Zone A of $$80.17 \pm 9.20$$ 80.17 ± 9.20 and $$84.81 \pm 6.11,$$ 84.81 ± 6.11 , respectively. We offer this tool as a mechanism to enhance the predictive capabilities of algorithms for patients with T1D.

scholarly journals Multi-Step ahead Predictive Model for Blood Glucose Concentrations of Type-1 Diabetic Patients

2021 ◽  
Author(s):  
Syed Mohammed Arshad Zaidi ◽  
Varun Chandola ◽  
Muhanned Ibrahim ◽  
Bianca Romanski ◽  
Lucy D. Mastrandrea ◽  
...  
Keyword(s):  
Blood Glucose ◽  
Diabetes Management ◽  
Mean Squared Error ◽  
Absolute Error ◽  
Target Range ◽  
Percentage Error ◽  
Diabetic Patients ◽  
Average Percentage ◽  
Squared Error

Abstract Continuous monitoring of blood glucose (BG) levels is a key aspect of diabetes management. Patients with Type-1 diabetes (T1D) require an effective tool to monitor these levels in order to make appropriate decisions regarding insulin administrationand food intake to keep BG levels in target range. Effectively and accurately predicting future BG levels at multi-time stepsahead benefits a patient with diabetes by helping them decrease the risks of extremes in BG including hypo- and hyperglycemia.In this study, we present a novel multi-component deep learning model BG-Predict that predicts the BG levels in a multi-steplook ahead fashion. The model is evaluated both quantitatively and qualitatively on actual blood glucose data for 97 patients.For the prediction horizon (PH) of 30 minutes, the average values for root mean squared error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE), andnormalized mean squared error (NRMSE) are 20.82±4.97 mg/dL, 15.04±3.70 mg/dL, 11.63±2.78 and 0.06±0.01 respectively. When Clarke and Parkes error grid analyses were performedcomparing predicted BG with actual BG, the results showed average percentage of points in Zone A of 83.88±6.84 and 87.44±4.97, respectively. We offer this tool as a mechanism to enhance the predictive capabilities of algorithms for patients with T1D.

Blood glucose control algorithms for type 1 diabetic patients: A methodological review

2013 ◽  
Vol 8 (2) ◽  
pp. 107-119 ◽  
Author(s):  
Katrin Lunze ◽  
Tarunraj Singh ◽  
Marian Walter ◽  
Mathias D. Brendel ◽  
Steffen Leonhardt
Keyword(s):  
Blood Glucose ◽  
Glucose Control ◽  
Blood Glucose Control ◽  
Control Algorithms ◽  
Diabetic Patients ◽  
Methodological Review ◽  
Type 1 Diabetic Patients

Higher Order Sliding Mode Control for Blood Glucose Regulation of Type 1 Diabetic Patients

2018 ◽  
Vol 7 (1) ◽  
pp. 65-84 ◽  
Author(s):  
Mounir Djouima ◽  
Ahmad Taher Azar ◽  
Saïd Drid ◽  
Driss Mehdi
Keyword(s):  
Blood Glucose ◽  
Sliding Mode Control ◽  
Blood Glucose Level ◽  
Glucose Level ◽  
Sliding Mode ◽  
Higher Order ◽  
Control Technique ◽  
Diabetic Patients ◽  
Mode Control

Type 1 diabetes mellitus (T1DM) treatment depends on the delivery of exogenous insulin to obtain near normal glucose levels. This article proposes a method for blood glucose level regulation in type 1 diabetics. The control strategy is based on comparing the first order sliding mode control (FOSMC) with a higher order SMC based on the super twisting control algorithm. The higher order sliding mode is used to overcome chattering, which can induce some undesirable and harmful phenomena for human health. In order to test the controller in silico experiments, Bergman's minimal model is used for studying the dynamic behavior of the glucose and insulin inside human body. Simulation results are presented to validate the effectiveness and the good performance of this control technique. The obtained results clearly reveal improved performance of the proposed higher order SMC in regulating the blood glucose level within the normal glycemic range in terms of accuracy and robustness.

Sign in / Sign up

Export Citation Format

Share Document