Model-Fusion-Based Online Glucose Concentration Predictions in People with Type 1 Diabetes

Recent advances in the precision control strategy of artificial pancreas

The scientific diagnosis and treatment of patients with diabetes require frequent blood glucose testing and insulin delivery to normoglycemia. Therefore, an artificial pancreas with a continuous blood glucose (BG) monitoring function is an urgent research target in the medical industry. The problem of closed-loop algorithmic control of the BG with a time delay is a key and difficult issue that needs to be overcome in the development of an artificial pancreas. Firstly, the composition, structure, and control characteristics of the artificial pancreas are introduced. Subsequently, the research progress of artificial pancreas control algorithms is reviewed, and the characteristics, advantages, and disadvantages of proportional-integral-differential control, model predictive control, and artificial intelligence control are compared and analyzed to determine whether they are suitable for the practical application of the artificial pancreas. Additionally, key advancements in areas such as blood glucose data monitoring, adaptive models, wearable devices, and fully automated artificial pancreas systems are also reviewed. Finally, this review highlights that meal prediction, control safety, integration, streamlining the optimization of control algorithms, constant temperature preservation of insulin, and dual-hormone artificial pancreas are issues that require further attention in the future.

After-meal blood glucose level prediction for type-2 diabetic patients

Type 2 Diabetes, a metabolic disorder disease, is becoming a fast growing health crisis worldwide. It reduces the quality of life, and increases mortality and health care costs unless managed well. After-meal blood glucose level measure is considered as one of the most fundamental and well-recognized steps in managing Type 2 diabetes as it guides a user to make better plans of their diet and thus control the diabetes well. In this paper, we propose a data-driven approach to predict the 2 h after meal blood glucose level from the previous discrete blood glucose readings, meal, exercise, medication, & profile information of Type 2 diabetes patients. To the best of our knowledge, this is the first attempt to use discrete blood glucose readings for 2 h after meal blood glucose level prediction using data-driven models. In this study, we have collected data from five prediabetic and diabetic patients in free living conditions for six months. We have presented comparative experimental study using different popular machine learning models including support vector regression, random forest, and extreme gradient boosting, and two deep layer techniques: multilayer perceptron, and convolutional neural network. We present also the impact of different features in blood glucose level prediction, where we observe that meal has some modest and medication has a good influence on blood glucose level.

Robust positive control of tumour growth using angiogenic inhibition

In practice, many physical systems, including physiological ones, can be considered whose input can take only positive quantities. However, most of the conventional control methods do not support the positivity of the main input data to the system. Furthermore, the parameters of these systems, similar to other non-linear systems, are either not accurately identified or may change over time. Therefore, it is reasonable to design a controller that is robust against system uncertainties. A robust positive-input control method is proposed for the automatic treatment of targeted anti-angiogenic therapy implementing a recently published tumour growth model based on experiments conducted on mouse models. The backstepping (BS) approach is applied to design the positive input controller using sensory data of tumour volume as feedback. Unlike previous studies, the proposed controller only requires the measurement of tumour volume and does not require the measurement of inhibitor level. The exponential stability of the controlled system is proved mathematically using the Lyapunov theorem. As a result, the convergence rate of the tumour volume can be controlled, which is an important issue in cancer treatment. Moreover, the robustness of the system against parametric uncertainties is verified mathematically using the Lyapunov theorem. The real-time simulation results-based (OPAL-RT) and comparisons with previous studies confirm the theoretical findings and effectiveness of the proposed method.

Positive input observer-based controller design for blood glucose regulation for type 1 diabetic patients: A backstepping approach

In practice, there are many physical systems that can have only positive inputs, such as physiological systems. Most conventional control methods cannot ensure that the main system input is positive. A positive input observer-based controller is designed for an intravenous glucose tolerance test model of type 1 diabetes mellitus (T1DM). The backstepping (BS) approach is employed to design the feedback controller for artificial pancreas (AP) systems, based on the Extended Bergman's Minimal Model (EBMM). The EBMM represents the T1DM in terms of the blood glucose concentration (BGC), insulin concentration, and plasma level and the disturbance of insulin during medication due to either meal intake or burning sugar by doing some physical exercise. The insulin concentration and plasma level are estimated using observers, and these estimations are applied as feedback to the controller. The asymptotic stability of the observer-based controller is proved using the Lyapunov theorem. Moreover, it is proved that the system is bounded input-bounded output (BIBO) stable in the presence of uncertainties generated by uncertain parameters and external disturbance. For realistic situations, we consider only the BGC to be available for measurement and additionally inter-and intra-patient variability of system parameters is considered.

Deep transfer learning: a novel glucose prediction framework for new subjects with type 2 diabetes

Blood glucose (BG) prediction is an effective approach to avoid hyper- and hypoglycemia, and achieve intelligent glucose management for patients with type 1 or serious type 2 diabetes. Recent studies have tended to adopt deep learning networks to obtain improved prediction models and more accurate prediction results, which have often required significant quantities of historical continuous glucose-monitoring (CGM) data. However, for new patients with limited historical dataset, it becomes difficult to establish an acceptable deep learning network for glucose prediction. Consequently, the goal of this study was to design a novel prediction framework with instance-based and network-based deep transfer learning for cross-subject glucose prediction based on segmented CGM time series. Taking the effects of biodiversity into consideration, dynamic time warping (DTW) was applied to determine the proper source domain dataset that shared the greatest degree of similarity for new subjects. After that, a network-based deep transfer learning method was designed with cross-domain dataset to obtain a personalized model combined with improved generalization capability. In a case study, the clinical dataset demonstrated that, with additional segmented dataset from other subjects, the proposed deep transfer learning framework achieved more accurate glucose predictions for new subjects with type 2 diabetes.

GLYFE: review and benchmark of personalized glucose predictive models in type 1 diabetes

Due to the sensitive nature of diabetes-related data, preventing them from being easily shared between studies, and the wide discrepancies in their data processing pipeline, progress in the field of glucose prediction is hard to assess. To address this issue, we introduce GLYFE (GLYcemia Forecasting Evaluation), a benchmark of machine learning-based glucose predictive models. We present the accuracy and clinical acceptability of nine different models coming from the literature, from standard autoregressive to more complex neural network-based models. These results are obtained on two different datasets, namely UVA/Padova Type 1 Diabetes Metabolic Simulator (T1DMS) and Ohio Type-1 Diabetes Mellitus (OhioT1DM), featuring artificial and real type 1 diabetic patients respectively. By providing extensive details about the data flow as well as by providing the whole source code of the benchmarking process, we ensure the reproducibility of the results and the usability of the benchmark by the community. Those results serve as a basis of comparison for future studies. In a field where data are hard to obtain, and where the comparison of results from different studies is often irrelevant, GLYFE gives the opportunity of gathering researchers around a standardized common environment.

Prior Informed Regularization of Recursively Updated Latent-Variables-Based Models with Missing Observations

Many data-driven modeling techniques identify locally valid, linear representations of time-varying or nonlinear systems, and thus the model parameters must be adaptively updated as the operating conditions of the system vary, though the model identification typically does not consider prior knowledge. In this work, we propose a new regularized partial least squares (rPLS) algorithm that incorporates prior knowledge in the model identification and can handle missing data in the independent covariates. This latent variable (LV) based modeling technique consists of three steps. First, a LV-based model is developed on the historical time series data. In the second step, the missing observations in the new incomplete data sample are estimated. Finally, the future values of the outputs are predicted as a linear combination of estimated scores and loadings. The model is recursively updated as new data are obtained from the system. The performance of the proposed rPLS and rPLS with exogenous inputs (rPLSX) algorithms are evaluated by modeling variations in glucose concentration (GC) of people with Type 1 diabetes (T1D) in response to meals and physical activities for prediction windows up to one hour, or 12 sampling instances, into the future. The proposed rPLS family of GC prediction models are evaluated with both in-silico and clinical experiment data and compared with the performance of recursive time series and kernel-based models. The root mean squared error (RMSE) with simulated subjects in the multivariable T1D simulator where physical activity effects are incorporated in GC variations are 2.52 and 5.81 mg/dL for 30 and 60 mins ahead predictions (respectively) when information for all meals and physical activities are used, increasing to 2.70 and 6.54 mg/dL (respectively) when meals and activities occurred, but the information is with-held from the modeling algorithms. The RMSE is 10.45 and 14.48 mg/dL for clinical study with prediction horizons of 30 and 60 mins, respectively. The low RMSE values demonstrate the effectiveness of the proposed rPLS approach compared to the conventional recursive modeling algorithms.

Blood glucose concentration prediction based on VMD-KELM-AdaBoost

The time series of blood glucose concentration in diabetic patients are time-varying, nonlinear, and non-stationary. In order to improve the accuracy of blood glucose prediction, a multi-scale combination short-term blood glucose prediction model was constructed by combining the variational mode decomposition (VMD) method, the kernel extreme learning machine (KELM), and the AdaBoost algorithm (VMD-ELM-AdaBoost). Firstly, the blood glucose concentration series were decomposed into a set of intrinsic modal functions (IMFs) with different scales by the VMD method. On this basis, the KELM neural network and AdaBoost algorithm are combined to predict each IMF component. Finally, the cumulative blood glucose concentration prediction value is obtained by accumulating the KELM-AdaBoost prediction results of each IMF. The time series of measured blood glucose concentration were used for experimental analysis; the experimental results show that the proposed VMD-KELM-AdaBoost method has higher prediction accuracy compared with the classical prediction models such as ELM, KELM, SVM, and LSTM. The proposed VMD-KELM-AdaBoost model can still achieve high prediction accuracy 60 min in advance (the mean values of RMSE, MAPE, and CC are about 10.1422, 4.8629%, and 0.8737 respectively); in Clarke error mesh analysis, the proportion of falling into A region is about 95.7%; the sensitivity and false alarm rate of early alarm of hypoglycemia were 94.8% and 7.7%, respectively. Graphical abstract We have proposed a new prediction model. In the first part, for reducing thenon-stationarity, the data of blood glucose concentration was decomposed as a series ofIMF by VMD. In the second part, a prediction model based KELM and Adaboost wasestablished. In the third part, the KELM-Adaboost model was used to predict each IMF,and the predicted values of all IMFS were superimposed to obtain the final predictionresult of blood glucose concentration.

Data-based algorithms and models using diabetics real data for blood glucose and hypoglycaemia prediction - A systematic literature review

BACKGROUND AND AIM

Hypoglycaemia prediction play an important role in diabetes management being able to reduce the number of dangerous situations. Thus, it is relevant to present a systematic review on the currently available prediction algorithms and models for hypoglycaemia (or hypoglycemia in US English) prediction.

METHODS

This study aims to systematically review the literature on data-based algorithms and models using diabetics real data for hypoglycaemia prediction. Five electronic databases were screened for studies published from January 2014 to June 2020: ScienceDirect, IEEE Xplore, ACM Digital Library, SCOPUS, and PubMed.

RESULTS

Sixty-three eligible studies were retrieved that met the inclusion criteria. The review identifies the current trend in this topic: most of the studies perform short-term predictions (82.5%). Also, the review pinpoints the inputs and shows that information fusion is relevant for hypoglycaemia prediction. Regarding data-based models (80.9%) and hybrid models (19.1%) different predictive techniques are used: Artificial neural network (22.2%), ensemble learning (27.0%), supervised learning (20.6%), statistic/probabilistic (7.9%), autoregressive (7.9%), evolutionary (6.4%), deep learning (4.8%) and adaptative filter (3.2%). Artificial Neural networks and hybrid models show better results.

CONCLUSIONS

The data-based models for blood glucose and hypoglycaemia prediction should be able to provide a good balance between the applicability and performance, integrating complementary data from different sources or from different models. This review identifies trends and possible opportunities for research in this topic.

Improving blood glucose level predictability using machine learning

This study was designed to improve blood glucose level predictability and future hypoglycemic and hyperglycemic event alerts through a novel patient-specific supervised-machine-learning (SML) analysis of glucose level based on a continuous-glucose-monitoring system (CGM) that needs no human intervention, and minimises false-positive alerts. The CGM data over 7 to 50 non-consecutive days from 11 type-1 diabetic patients aged 18 to 39 with a mean HbA1C of 7.5% ± 1.2% were analysed using four SML models. The algorithm was constructed to choose the best-fit model for each patient. Several statistical parameters were calculated to aggregate the magnitudes of the prediction errors. The personalised solutions provided by the algorithm were effective in predicting glucose levels 30 minutes after the last measurement. The average root-mean-square-error was 20.48 mg/dL and the average absolute-mean-error was 15.36 mg/dL when the best-fit model was selected for each patient. Using the best-fit-model, the true-positive-hypoglycemia-prediction-rate was 64%, whereas the false-positive- rate was 4.0%, and the false-negative-rate was 0.015%. Similar results were found even when only CGM samples below 70 were considered. The true-positive-hyperglycemia-prediction-rate was 61%. State-of-the-art SML tools are effective in predicting the glucose level values of patients with type-1diabetes and notifying these patients of future hypoglycemic and hyperglycemic events, thus improving glycemic control. The algorithm can be used to improve the calculation of the basal insulin rate and bolus insulin, and suitable for a closed loop "artificial pancreas" system. The algorithm provides a personalised medical solution that can successfully identify the best-fit method for each patient.

A Real-Time Continuous Glucose Monitoring-Based Algorithm to Trigger Hypotreatments to Prevent/Mitigate Hypoglycemic Events

Background: The standard treatment for hypoglycemia recommended by the American Diabetes Association (ADA) suggests patients with diabetes to take small amounts of carbohydrates, the so-called hypotreatments (HTs), as soon as blood glucose concentration goes below 70 mg/dL. However, prevention, or at least mitigation, of hypoglycemic events could be achieved by triggering HTs ahead of time thanks to the use of the predictive capabilities of suitable real-time algorithms fed by continuous glucose monitoring (CGM) sensor data. Materials and Methods: The algorithm proposed in this article to trigger HTs for preventing forthcoming hypoglycemic events is based on the computation of the "dynamic risk", there is a nonlinear function combining current glycemia with its rate-of-change, both provided by CGM. A comparison of performance of the proposed algorithm against the ADA guidelines is made, in silico, on datasets of 100 virtual patients undergoing a single-meal experiment, with induced postmeal hypoglycemia, generated by the UVA/Padova type 1 diabetes simulator. Results: On noise-free CGM data, the proposed algorithm reduces the time spent in hypoglycemia, on median [25th-75th percentiles] from 36 [29-43] to 0 [0-11] min (P < 0.0001), with a concomitant decrease of the post-treatment rebound (PTR) in glucose concentration, on median [25th-75th percentiles] from 136 [121-148] to 121 [116-127] mg/dL (P < 0.0001). On noisy CGM data, there is still a reduction of both time spent in hypoglycemia from 41 [28-49] min to 25 [0-41] min (P < 0.0001) and PTR from 174 [146-189] mg/dL to 137 [123-151] mg/dL (P < 0.0001). Conclusions: The potentiality of the new algorithm in generating preventive HTs, which can allow significant reduction of hypoglycemia without concomitant increase of hyperglycemia, suggests its further development and test in silico, for example, simulating both insulin pump and multiple-daily-injection therapies.

Short-term prediction of glucose in type 1 diabetes using kernel adaptive filters

This study aims at presenting a nonlinear, recursive, multivariate prediction model of the subcutaneous glucose concentration in type 1 diabetes. Nonlinear regression is performed in a reproducing kernel Hilbert space, by either the fixed budget quantized kernel least mean square (QKLMS-FB) or the approximate linear dependency kernel recursive least-squares (KRLS-ALD) algorithm, such that a sparse model structure is accomplished. A multivariate feature set (i.e., subcutaneous glucose, food carbohydrates, insulin regime and physical activity) is used and its influence on short-term glucose prediction is investigated. The method is evaluated using data from 15 patients with type 1 diabetes in free-living conditions. In the case when all the input variables are considered: (i) the average root mean squared error (RMSE) of QKLMS-FB increases from 13.1 mg dL^-1 (mean absolute percentage error (MAPE) 6.6%) for a 15-min prediction horizon (PH) to 37.7 mg dL^-1 (MAPE 20.8%) for a 60-min PH and (ii) the RMSE of KRLS-ALD, being predictably lower, increases from 10.5 mg dL^-1 (MAPE 5.2%) for a 15-min PH to 31.8 mg dL^-1 (MAPE 18.0%) for a 60-min PH. Multivariate data improve systematically both the regularity and the time lag of the predictions, reducing the errors in critical glucose value regions for a PH ≥ 30 min. Graphical abstract ᅟ.