Wyniki wyszukiwania - BazTech

1

Robustness of closed-loop glucose control systems

Wyciślok Artur, Śmieja Jarosław

Archives of Control Sciences

|

2023

|

Vol. 33, No. 3

681--705

EN

The main purpose of this work is to provide an extensive, simulation-based comparison of robustness of PID and MPC algorithms in control of blood glucose levels in patients with type 1 diabetes and thus answer the question of their safety. Cohort testing, with 1000 simulated, randomized patients allowed to analyze specific control quality indicators, such as number of hypoglycemic events, and length of hypo- and hyperglycemia periods. Results show that both algorithms provide a reasonable safety level, taking into account natural changes of patients’ physiological parameters. At the same time, we point out drawbacks of each solution, as well as general problems arising in close-loop control of blood glucose level.

2

Blood glucose prediction model for type 1 diabetes based on artificial neural network with time-domain features

Alfian Ganjar, Syafrudin Muhammad, Anshari Muhammad, Benes Filip, Atmaji Fransiskus Tatas Dwi, Fahrurrozi Imam, Hidayatullah Ahmad Fathan, Rhee Jongtae

Biocybernetics and Biomedical Engineering

|

2020

|

Vol. 40, no. 4

1586--1599

EN

Predicting future blood glucose (BG) levels for diabetic patients will help them avoid potentially critical health issues. We demonstrate the use of machine learning models to predict future blood glucose levels given a history of blood glucose values as the single input parameter. We propose an Artificial Neural Network (ANN) model with time-domain attributes to predict blood glucose levels 15, 30, 45 and 60 min in the future. Initially, the model's features are selected based on the previous 30 min of BG measurements before a trained model is generated for each patient. These features are combined with time-domain attributes to give additional inputs to the proposed ANN. The prediction model was tested on 12 patients with Type 1 diabetes (T1D) and the results were compared with other data-driven models including the Support Vector Regression (SVR), K-Nearest Neighbor (KNN), C4.5 Decision Tree (DT), Random Forest (RF), Adaptive Boosting (AdaBoost) and eXtreme Gradient Boosting (XGBoost) models. Our results show that the proposed BG prediction model that is based on an ANN outperformed all other models with an average Root Mean Square Error (RMSE) of 2.82, 6.31, 10.65 and 15.33 mg/dL for Prediction Horizons (PHs) of 15, 30, 45 and 60 min, respectively. Our testing showed that combining time-domain attributes into the input data resulted in enhanced performance of majority of prediction models. The implementation of proposed prediction model allows patients to obtain future blood glucose levels, so that the preventive alerts can be generated before critical hypoglycemic/ hyperglycemic events occur.

3

In silico testing of optimized Fuzzy P+D controller for artificial pancreas

Soylu S., Danisman K.

Biocybernetics and Biomedical Engineering

|

2018

|

Vol. 38, no. 2

399--408

EN

Background and objectives: Despite therapeutic advances, a complete cure has not been found yet for patients with type 1 diabetes (T1D). Artificial pancreas (AP) is a promising approach to cope with this disease. The controller part of the AP can compute the insulin infusion rate that keeps blood glucose concentration (BGC) in normoglycemic ranges. Most controllers rely on model-based controllers and use manual meal announcements or meal detection algorithms. For a fully automated AP, a controller only using the patient's BGC data is needed. Methods: An optimized Mamdani-type hybrid Fuzzy P+D controller was proposed. Using the University of Virginia/Padova Simulator, a 36 h scenario was tested in nine virtual adult patients. To take into account the effect of continuous glucose monitor noise, the scenario was repeated 25 times for each adult.The main outcomes were the percentage of time BGC levels in the euglycemic range, low blood glucose index (LBGI), and blood glucose risk index (BGRI), respectively. Results: The obtained BGC values were found to be in the euglycemic range for 82.6% of the time. Moreover, the BGC values were below 50 mg/dl, below 70 mg/dl and above 250 mg/dl for 0%, 0.35% and 0.74% of the time, respectively. The BGRI, LBGI, and high blood glucose index (HBGI) were also found as 3.75, 0.34 and 3.41, respectively. The proposed controller both increases the time the BGC levels in the euglycemic range and causes less hypoglycemia and hyperglycemia relative to the published techniques studied in a similar scenario and population.

4

Continuous blood glucose level prediction of Type 1 Diabetes based on Artificial Neural Network

Ben Ali J., Hamdi T., Fnaiech N., Di Costanzo V., Fnaiech F., Ginoux J. M.

Biocybernetics and Biomedical Engineering

|

2018

|

Vol. 38, no. 4

828--840

EN

Recent technological advancements in diabetes technologies, such as Continuous Glucose Monitoring (CGM) systems, provide reliable sources to blood glucose data. Following its development, a new challenging area in the field of artificial intelligence has been opened and an accurate prediction method of blood glucose levels has been targeted by scientific researchers. This article proposes a new method based on Artificial Neural Networks (ANN) for blood glucose level prediction of Type 1 Diabetes (T1D) using only CGMdata as inputs. To show the efficiency of our method and to validate our ANN, real CGM data of 13 patients were investigated. The accuracy of the strategy is discussed based on some statistical criteria such as the Root Mean Square Error (RMSE) and the Mean Absolute Percentage Error (MAPE). The obtained averages of RMSE are 6.43 mg/dL, 7.45 mg/dL, 8.13 mg/dL and 9.03 mg/dL for Prediction Horizon (PH) respectively 15 min, 30 min, 45 min and 60 min and the average of MAPE was 3.87% for PH = 15 min, knowing that the smaller is the RMSE and MAPE, the more accurate is the prediction. Experimental results show that the proposed ANN is accurate, adaptive, and very encouraging for a clinical implementation. Furthermore, while other studies have only focused on the prediction accuracy of blood glucose, this work aims to improve the quality of life of T1D patients by using only CGM data as inputs and by limiting human intervention.

5

Accurate prediction of continuous blood glucose based on support vector regression and differential evolution algorithm

Hamdi T., Ben Ali J., Di Costanzo V., Fnaiech F., Moreau E., Ginoux J. M.

Biocybernetics and Biomedical Engineering

|

2018

|

Vol. 38, no. 2

362--372

EN

Type 1 diabetes (T1D) is a chronic disease requiring patients to know their blood glucose values in order to ensure blood glucose levels as close to normal as possible. Hence, the ability to predict blood glucose levels is of a great interest for clinical researchers. In this sense, the literature is rich with several solutions that can predict blood glucose levels. Unfortunately, these methods require the patient to specific their daily activities: meal intake, insulin injection and emotional factors, which can be error prone. To reduce this burden on the patent, this work proposes to use only continuous glucose monitoring (CGM) data to predict blood glucose levels independently of other factors. To support this, support vector regression (SVR) and differential evolution (DE) algorithms were investigated. The proposed method is validated using real CGM data of 12 patients. The obtained average of root mean square error (RMSE) was 9.44, 10.78, 11.82 and 12.95 mg/dL for prediction horizon (PH) respectively equal to 15, 30, 45 and 60 min. The results of the present study and comparison with some previous works show that the proposed method holds promise. The SVR based on DE algorithm achieved high prediction accuracy while being robustness, automatic, and requiring no human intervention.

6

Treatment of patients with type 1 diabetes – Insulin pumps or multiple injections?

Krzymien J., Rachuta M., Kozlowska I., Ladyzynski P., Foltynski P.

Biocybernetics and Biomedical Engineering

|

2016

|

Vol. 36, no. 1

1--8

EN

In theory, the continuous subcutaneous insulin infusion (CSII) has a few advantages over the multiple daily insulin injections (MDI) that should lead to improved glycemic control and lower risk of hypoglycemia. In practice, both treatment regimens allow for adequate control of glycemia. The objective of this review is to discuss the most important factors contributing to this situation. We made a comprehensive evidence-based review of the factors affecting effectiveness of CSII and MDI, with a special attention to algorithms for insulin dose adjustments and the automatic bolus calculators. Regardless of the treatment regimen that is used a few different interdependent factors influence the final result of the intensive insulin therapy. These factors comprise: patients' education, attitude, emotional stability and compliance, and careful analysis of the treatment results by a physician establishing the appropriate rate of basal insulin infusion or the basal dose of insulin and adjusting insulin doses to: the meals, the planned physical activity and the actual and target glucose levels. Our study implies that good glycemic control in patients with type 1 diabetes requires not only a thorough patient education and complying with medical recommendations, but also an individual determination of therapy goals and ways of achieving them. That is why, regardless of the treatment method that is applied, it is the choice of appropriate algorithms and adjusting them to the patient's way of life what allow for achieving pre-specified therapeutic goals. Technical means such as automatic bolus calculators might supplement but they cannot replace patients education and compliance.