Comparative assessment of glucose prediction models for patients with type 1 diabetes mellitus applying sensors for glucose and physical activity monitoring

A data-driven personalized approach to predict blood glucose levels in type-1 diabetes patients exercising in free-living conditions

OBJECTIVE

The development of new technologies has generated vast amount of data that can be analyzed to better understand and predict the glycemic behavior of people living with type 1 diabetes. This paper aims to assess whether a data-driven approach can accurately and safely predict blood glucose levels in patients with type 1 diabetes exercising in free-living conditions.

METHODS

Multiple machine learning (XGBoost, Random Forest) and deep learning (LSTM, CNN-LSTM, Dual-encoder with Attention layer) regression models were considered. Each deep-learning model was implemented twice: first, as a personalized model trained solely on the target patient's data, and second, as a fine-tuned model of a population-based training model. The datasets used for training and testing the models were derived from the Type 1 Diabetes Exercise Initiative (T1DEXI). A total of 79 patients in T1DEXI met our inclusion criteria. Our models used various features related to continuous glucose monitoring, insulin pumps, carbohydrate intake, exercise (intensity and duration), and physical activity-related information (steps and heart rate). This data was available for four weeks for each of the 79 included patients. Three prediction horizons (10, 20, and 30 min) were tested and analyzed.

RESULTS

For each patient, there always exists either a machine learning or a deep learning model that conveniently predicts BGLs for up to 30 min. The best performing model differs from one patient to another. When considering the best performing model for each patient, the median and the mean Root Mean Squared Error (RMSE) values (across the 79 patients) for predictions made 10 min ahead were 6.99 mg/dL and 7.46 mg/dL, respectively. For predictions made 30 min ahead, the median and mean RMSE values were 16.85 mg/dL and 17.74 mg/dL, respectively. The majority of the predictions output by the best model of each patient fell within the clinically safe zones A and B of the Clarke Error Grid (CEG), with almost no predictions falling into the unsafe zone E. The most challenging patient to predict 30 min ahead achieved an RMSE value of 32.31 mg/dL (with the corresponding best performing model). The best-predicted patient had an RMSE value of 10.48 mg/dL. Predicting blood glucose levels was more difficult during and after exercise, resulting in higher RMSE values on average. Prediction errors during and after physical activity (two hours and four hours after) generally remained within the clinical safe zones of the CEG with less than 0.5% of predictions falling into the harmful zones D and E, regardless of the exercise category.

CONCLUSIONS

Data-driven approaches can accurately predict blood glucose levels in type 1 diabetes patients exercising in free-living conditions. The best-performing model varies across patients. Approaches in which a population-based model is initially trained and then fine-tuned for each individual patient generally achieve the best performance for the majority of patients. Some patients remain challenging to predict with no straightforward explanation of why a patient is more challenging to predict than another.

Platform for precise, personalised glucose forecasting through continuous glucose and physical activity monitoring and deep learning

Emerging research has demonstrated the advantage of continuous glucose monitoring for use in artificial pancreas and diabetes management in general. Recent studies demonstrate that glucose level forecasting using deep learning can help avoid postprandial hyperglycemia (≥ 180 mg/dL) or hypoglycemia (≤70 mg/dL) from delayed or increased insulin dosing in artificial pancreas. In this paper, a novel hybrid deep learning framework with integration of content-based attention learning is presented, to effectively predict the glucose measurements with prediction horizons (PH) = 15, 30 and, 60 minutes for T1D and T2D patients based on past data. We also present a complete cloud-based system and mobile app used for collecting CGM sensor, physical activity data, CHO values and insulin measurements to perform glucose forecasts using the proposed model running on Cloud. This model was validated using clinical data of individual with Type 1 diabetes (OhioT1DM) and individual with Type 2 diabetes. The mean absolute relative difference (MARD) was 12.33±3.15, 7.14±1.76% for PH=60 and, 30 min respectively on OhioT1DM clinical Dataset. The root mean squared error (RMSE) was 29.41±5.92 mg/dL and 17.19±3.22 mg/dL and the mean absolute error (MAE) was 21.96±4.67 mg/dL and 12.58±2.34 mg/dL for PH=60 and, 30 min respectively on the same clinical dataset. It was observed that inclusion of physical activity leads to improved glucose forecasting accuracy. Furthermore, all these results were obtained by training the model on only 8 days of clinical data of a single patient, followed by testing on clinical data on the following days. The results indicate that training on a single patient data may lead to better personalisation and better glucose forecasting results compared to existing works.

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.

A Machine Learning Web App to Predict Diabetic Blood Glucose Based on a Basic Noninvasive Health Checkup, Sociodemographic Characteristics, and Dietary Information: Case Study

BACKGROUND

Over the past few decades, diabetes has become a serious public health concern worldwide, particularly in Bangladesh. The advancement of artificial intelligence can be reaped in the prediction of blood glucose levels for better health management. However, the practical validity of machine learning (ML) techniques for predicting health parameters using data from low- and middle-income countries, such as Bangladesh, is very low. Specifically, Bangladesh lacks research using ML techniques to predict blood glucose levels based on basic noninvasive clinical measurements and dietary and sociodemographic information.

OBJECTIVE

To formulate strategies for public health planning and the control of diabetes, this study aimed to develop a personalized ML model that predicts the blood glucose level of urban corporate workers in Bangladesh.

METHODS

Based on the basic noninvasive health checkup test results, dietary information, and sociodemographic characteristics of 271 employees of the Bangladeshi Grameen Bank complex, 5 well-known ML models, namely, linear regression, boosted decision tree regression, neural network, decision forest regression, and Bayesian linear regression, were used to predict blood glucose levels. Continuous blood glucose data were used in this study to train the model, which then used the trained data to predict new blood glucose values.

RESULTS

Boosted decision tree regression demonstrated the greatest predictive performance of all evaluated models (root mean squared error=2.30). This means that, on average, our model's predicted blood glucose level deviated from the actual blood glucose level by around 2.30 mg/dL. The mean blood glucose value of the population studied was 128.02 mg/dL (SD 56.92), indicating a borderline result for the majority of the samples (normal value: 140 mg/dL). This suggests that the individuals should be monitoring their blood glucose levels regularly.

CONCLUSIONS

This ML-enabled web application for blood glucose prediction helps individuals to self-monitor their health condition. The application was developed with communities in remote areas of low- and middle-income countries, such as Bangladesh, in mind. These areas typically lack health facilities and have an insufficient number of qualified doctors and nurses. The web-based application is a simple, practical, and effective solution that can be adopted by the community. Use of the web application can save money on medical expenses, time, and health management expenses. The created system also aids in achieving the Sustainable Development Goals, particularly in ensuring that everyone in the community enjoys good health and well-being and lowering total morbidity and mortality.

Wearable sensor platforms for real-time monitoring and early warning of metabolic disorders in humans

Nowadays, the prevalence of metabolic syndromes (MSs) has attracted increasing concerns as it is closely related to overweight and obesity, physical inactivity and overconsumption of energy, making the diagnosis and real-time monitoring of the physiological range essential and necessary for avoiding illness due to defects in the human body such as higher risk of cardiovascular disease, diabetes, stroke and diseases related to artery walls. However, the current sensing techniques are inconvenient and do not continuously monitor the health status of humans. Alternatively, the use of recent wearable device technology is a preferable method for the prevention of these diseases. This can enable the monitoring of the health status of humans in different health domains, including environment and structure. The use wearable devices with the purpose of facilitating rapid treatment and real-time monitoring can decrease the prevalence of MS and long-time monitor the health status of patients. This review highlights the recent advances in wearable sensors toward continuous monitoring of blood pressure and blood glucose, and further details the monitoring of abnormal obesity, triglycerides and HDL. We also discuss the challenges and future prospective of monitoring MS in humans.

Minimally invasive electrochemical continuous glucose monitoring sensors: Recent progress and perspective

Diabetes and its complications are seriously threatening the health and well-being of hundreds of millions of people. Glucose levels are essential indicators of the health conditions of diabetics. Over the past decade, concerted efforts in various fields have led to significant advances in glucose monitoring technology. In particular, the rapid development of continuous glucose monitoring (CGM) based on electrochemical sensing principles has great potential to overcome the limitations of self-monitoring blood glucose (SMBG) in continuously tracking glucose trends, evaluating diabetes treatment options, and improving the quality of life of diabetics. However, the applications of minimally invasive electrochemical CGM sensors are still limited owing to the following aspects: i) invasiveness, ii) short lifespan, iii) biocompatibility, and iv) calibration and prediction. In recent years, the performance of minimally invasive electrochemical CGM systems (CGMSs) has been significantly improved owing to breakthrough developments in new materials and key technologies. In this review, we summarize the history of commercial CGMSs, the development of sensing principles, and the research progress of minimally invasive electrochemical CGM sensors in reducing the invasiveness of implanted probes, maintaining enzyme activity, and improving the biocompatibility of the sensor interface. In addition, this review also introduces calibration algorithms and prediction algorithms applied to CGMSs and describes the application of machine learning algorithms for glucose prediction.

Deep Multitask Learning by Stacked Long Short-Term Memory for Predicting Personalized Blood Glucose Concentration

The adverse glycemic events triggered by the inaccurate insulin infusion in Type I diabetes (T1D) can lead to fatal complications. Predicting blood glucose concentration (BGC) based on clinical health records is critical for control algorithms in the artificial pancreas (AP) and aiding in medical decision support. This paper presents a novel deep learning (DL) model incorporating multitask learning (MTL) for personalized blood glucose prediction. The network architecture consists of shared and clustered hidden layers. Two layers of stacked long short-term memory (LSTM) form the shared hidden layers that learn generalized features from all subjects. The clustered hidden layers comprise two dense layers adapting to the gender-specific variability in the data. Finally, the subject-specific dense layers offer additional fine-tuning to personalized glucose dynamics resulting in an accurate BGC prediction at the output. OhioT1DM clinical dataset is used for the training and performance evaluation of the proposed model. A detailed analytical and clinical assessment have been performed using root mean square (RMSE), mean absolute error (MAE), and Clarke error grid analysis (EGA), respectively, which demonstrates the robustness and reliability of the proposed method. Consistently leading performance has been achieved for 30- (RMSE = 16.06 $\pm$ 2.74, MAE = 10.64 $\pm$ 1.35), 60- (RMSE = 30.89 $\pm$ 4.31, MAE = 22.07 $\pm$ 2.96), 90- (RMSE = 40.51 $\pm$ 5.16, MAE = 30.16 $\pm$ 4.10), and 120-minute (RMSE = 47.39 $\pm$ 5.62, MAE = 36.36 $\pm$ 4.54) prediction horizon (PH). In addition, the EGA analysis confirms the clinical feasibility by maintaining more than 94% BGC predictions in the clinically safe zone for up to 120-minute PH. Moreover, the improvement is established by benchmarking against the state-of-the-art statistical, machine learning (ML), and deep learning (DL) methods.

Assessment of Seasonal Stochastic Local Models for Glucose Prediction without Meal Size Information under Free-Living Conditions

Accurate blood glucose (BG) forecasting is key in diabetes management, as it allows preventive actions to mitigate harmful hypoglycemic/hyperglycemic episodes. Considering the encouraging results obtained by seasonal stochastic models in proof-of-concept studies, this work assesses the methodology in two datasets (open-loop and closed-loop) recorded in free-living conditions. First, similar postprandial glycemic profiles are grouped together with fuzzy C-means clustering. Then, a seasonal stochastic model is identified for each cluster. Finally, real-time BG forecasting is performed by weighting each model’s prediction. The proposed methodology (named C-SARIMA) is compared to other linear and nonlinear black-box methods: autoregressive integrated moving average (ARIMA), its variant with input (ARIMAX), a feed-forward neural network (NN), and its modified version (NN-X) fed by BG, insulin, and carbohydrates (timing and dosing) information for several prediction horizons (PHs). In the open-loop dataset, C-SARIMA grants a median root-mean-squared error (RMSE) of 20.13 mg/dL (PH = 30) and 27.23 mg/dL (PH = 45), not significantly different from ARIMA and NN. Over a longer PH, C-SARIMA achieves an RMSE = 31.96 mg/dL (PH = 60) and RMSE = 33.91 mg/dL (PH = 75), significantly outperforming the ARIMA and NN, without significant differences from the ARIMAX for PH ≥ 45 and the NN-X for PH ≥ 60. Similar results hold on the closed-loop dataset: for PH = 30 and 45 min, the C-SARIMA achieves an RMSE = 21.63 mg/dL and RMSE = 29.67 mg/dL, not significantly different from the ARIMA and NN. On longer PH, the C-SARIMA outperforms the ARIMA for PH > 45 and the NN for PH > 60 without significant differences from the ARIMAX for PH ≥ 45. Although using less input information, the C-SARIMA achieves similar performance to other prediction methods such as the ARIMAX and NN-X and outperforming the CGM-only approaches on PH > 45min.

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.

Hypoglycaemia detection and prediction techniques: A systematic review on the latest developments

The main objective of diabetes control is to correct hyperglycaemia while avoiding hypoglycaemia, especially in insulin-treated patients. Fear of hypoglycaemia is a hurdle to effective correction of hyperglycaemia because it promotes under-dosing of insulin. Strategies to minimise hypoglycaemia include education and training for improved hypoglycaemia awareness and the development of technologies to allow their early detection and thus minimise their occurrence. Patients with impaired hypoglycaemia awareness would benefit the most from these technologies. The purpose of this systematic review is to review currently available or in-development technologies that support detection of hypoglycaemia or hypoglycaemia risk, and identify gaps in the research. Nanomaterial use in sensors is a promising strategy to increase the accuracy of continuous glucose monitoring devices for low glucose values. Hypoglycaemia is associated with changes on vital signs, so electrocardiogram and encephalogram could also be used to detect hypoglycaemia. Accuracy improvements through multivariable measures can make already marketed galvanic skin response devices a good noninvasive alternative. Breath volatile organic compounds can be detected by dogs and devices and alert patients at hypoglycaemia onset, while near-infrared spectroscopy can also be used as a hypoglycaemia alarms. Finally, one of the main directions of research are deep learning algorithms to analyse continuous glucose monitoring data and provide earlier and more accurate prediction of hypoglycaemia. Current developments for early identification of hypoglycaemia risk combine improvements of available 'needle-type' enzymatic glucose sensors and noninvasive alternatives. Patient usability will be essential to demonstrate to allow their implementation for daily use in diabetes management.

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.

The challenge of predicting blood glucose concentration changes in patients with type I diabetes

Patients with Type I Diabetes (T1D) must take insulin injections to prevent the serious long term effects of hyperglycemia. They must also be careful not to inject too much insulin because this could induce (potentially fatal) hypoglycemia. Patients therefore follow a "regimen" that determines how much insulin to inject at each time, based on various measurements. We can produce an effective regimen if we can accurately predict a patient's future blood glucose (BG) values from his/her current features. This study explores the challenges of predicting future BG by applying a number of machine learning algorithms, as well as various data preprocessing variations (corresponding to 312 [learner, preprocessed-dataset] combinations), to a new T1D dataset that contains 29,601 entries from 47 different patients. Our most accurate predictor, a weighted ensemble of two Gaussian Process Regression models, achieved a (cross-validation) errL1 loss of 2.7 mmol/L (48.65 mg/dl). This result was unexpectedly poor given that one can obtain an errL1 of 2.9 mmol/L (52.43 mg/dl) using the naive approach of simply predicting the patient's average BG. These results suggest that the diabetes diary data that is typically collected may be insufficient to produce accurate BG prediction models; additional data may be necessary to build accurate BG prediction models over hours.

Improved Methods for Mid-Term Blood Glucose Level Prediction Using Dietary and Insulin Logs

Background and Objectives: The daily lifestyle management of diabetes requires accurate predictions of the blood glucose level between meals. The objective of this study was to improve the accuracy achieved by previous work, especially on the mid-term, i.e., 120 to 180 min prediction horizons, for insulin-dependent patients. Materials and Methods: An absorption model-based method is proposed to train an artificial neural network with the bolus and basal insulin dosing and timing, the baseline blood glucose level, the maximal glucose infusion rate, and the total carbohydrate content as parameters. The approach was implemented in various algorithmic setups, and it was validated on data from a small-scale clinical trial with continuous glucose monitoring. Results: Root mean square error results for the mid-term horizons are 1.72 mmol/L (120 min) and 1.95 mmol/L (180 min). The accuracy of the proposed model measured on the clinical data is better than the accuracy reported by any other currently available and comparable models. Conclusions: A relatively short (ca. two weeks) training sample of a continuous glucose monitor and dietary/insulin log is sufficient to provide accurate predictions. For the outpatient application in practice, a hybrid model is proposed that combines the present mid-term method with the authors’ previous work for short-term predictions.

Forecasting of Glucose Levels and Hypoglycemic Events: Head-to-Head Comparison of Linear and Nonlinear Data-Driven Algorithms Based on Continuous Glucose Monitoring Data Only

In type 1 diabetes management, the availability of algorithms capable of accurately forecasting future blood glucose (BG) concentrations and hypoglycemic episodes could enable proactive therapeutic actions, e.g., the consumption of carbohydrates to mitigate, or even avoid, an impending critical event. The only input of this kind of algorithm is often continuous glucose monitoring (CGM) sensor data, because other signals (such as injected insulin, ingested carbs, and physical activity) are frequently unavailable. Several predictive algorithms fed by CGM data only have been proposed in the literature, but they were assessed using datasets originated by different experimental protocols, making a comparison of their relative merits difficult. The aim of the present work was to perform a head-to-head comparison of thirty different linear and nonlinear predictive algorithms using the same dataset, given by 124 CGM traces collected over 10 days with the newest Dexcom G6 sensor available on the market and considering a 30-min prediction horizon. We considered the state-of-the art methods, investigating, in particular, linear black-box methods (autoregressive; autoregressive moving-average; and autoregressive integrated moving-average, ARIMA) and nonlinear machine-learning methods (support vector regression, SVR; regression random forest; feed-forward neural network, fNN; and long short-term memory neural network). For each method, the prediction accuracy and hypoglycemia detection capabilities were assessed using either population or individualized model parameters. As far as prediction accuracy is concerned, the results show that the best linear algorithm (individualized ARIMA) provides accuracy comparable to that of the best nonlinear algorithm (individualized fNN), with root mean square errors of 22.15 and 21.52 mg/dL, respectively. As far as hypoglycemia detection is concerned, the best linear algorithm (individualized ARIMA) provided precision = 64%, recall = 82%, and one false alarm/day, comparable to the best nonlinear technique (population SVR): precision = 63%, recall = 69%, and 0.5 false alarms/day. In general, the head-to-head comparison of the thirty algorithms fed by CGM data only made using a wide dataset shows that individualized linear models are more effective than population ones, while no significant advantages seem to emerge when employing nonlinear methodologies.

Blood Glucose Level Prediction of Diabetic Type 1 Patients Using Nonlinear Autoregressive Neural Networks

Diabetes type 1 is a chronic disease which is increasing at an alarming rate throughout the world. Studies reveal that the complications associated with diabetes can be reduced by proper management of the disease by continuously monitoring and forecasting the blood glucose level of patients. Objective. The prior prediction of blood glucose level is necessary to overcome the lag time for insulin absorption in diabetic type 1 patients. Method. In this research, we use continuous glucose monitoring (CGM) data to predict future blood glucose level using the previous data points. We compare two neural network techniques. We apply the optimal feedforward neural network and then propose optimal nonlinear autoregressive neural networks for blood glucose prediction 15–30 minutes earlier for diabetic type 1 patients. We validate the proposed model with 2 virtual subjects using their 24-hour blood glucose level data. These two case studies have been compiled from AIDA, i.e., the freeware mathematical diabetes simulator. Results. In the prediction horizon (PH) of 15 and 30 minutes, improved results have been shown for minimal inputs for blood glucose level of a particular subject. Root mean square error (RMSE) is used for performance calculation. For the optimal feedforward neural network, the RMSE is 0.9984 and 3.78 ml/dl, and for the optimal nonlinear autoregressive neural network, it reduces the RMSE to 0.60 and 1.12 ml/dl for 15 min and 30 min prediction horizons, respectively, for subject 1. Similarly, for subject 2 for the optimal feedforward neural network, RMSE is 1.43 and 3.51 ml/dl which is improved using the optimal autoregressive neural network to 0.7911 and 1.6756 ml/dl for 15 min and 30 min prediction horizons, respectively. Validation. We further validate our proposed model using UCI machine learning datasets (Abalone and Servo), and it shows improved results on that as well. Conclusion and Future Work. The proposed optimal nonlinear autoregressive neural network model performs better than the feedforward neural network model for these time series data. In the future, we intend to investigate a greater collection of AIDA scenarios and data that are real and influence other factors of BGLs.

Developing an Individual Glucose Prediction Model Using Recurrent Neural Network

In this study, we propose a personalized glucose prediction model using deep learning for hospitalized patients who experience Type-2 diabetes. We aim for our model to assist the medical personnel who check the blood glucose and control the amount of insulin doses. Herein, we employed a deep learning algorithm, especially a recurrent neural network (RNN), that consists of a sequence processing layer and a classification layer for the glucose prediction. We tested a simple RNN, gated recurrent unit (GRU), and long-short term memory (LSTM) and varied the architectures to determine the one with the best performance. For that, we collected data for a week using a continuous glucose monitoring device. Type-2 inpatients are usually experiencing bad health conditions and have a high variability of glucose level. However, there are few studies on the Type-2 glucose prediction model while many studies performed on Type-1 glucose prediction. This work has a contribution in that the proposed model exhibits a comparative performance to previous works on Type-1 patients. For 20 in-hospital patients, we achieved an average root mean squared error (RMSE) of 21.5 and an Mean absolute percentage error (MAPE) of 11.1%. The GRU with a single RNN layer and two dense layers was found to be sufficient to predict the glucose level. Moreover, to build a personalized model, at most, 50% of data are required for training.

Ensemble methods in combination with compartment models for blood glucose level prediction in type 1 diabetes mellitus

Backgroung: Type 1 diabetes is a disease that adversely affects the daily life of a large percentage of people worldwide. Daily glucose levels regulation and useful advices provided to patients regarding their diet are essential for diabetes treatment. For this reason, the interest of the academic community has focused on developing innovative systems, such as decision support systems, based on glucose prediction algorithms. The present work presents the predictive capabilities of ensemble methods compared to individual algorithms while combining each method with compartment models for fast acting insulin absorption simulation. Methods: An approach of combining widely used glycemia prediction algorithms is proposed and three different ensemble methods (Linear, Bagging and Boosting metaregressor) are applied and evaluated on their ability to provide accurate predictions for 30, 45 and 60 minutes ahead prediction horizon. Moreover, glycemia levels, long and short acting insulin dosages and consumed carbohydrates from six type one people with diabetes are used as input data and the results are evaluated in terms of root-mean square error and Clarke error grid analysis. Results: According to results, ensemble methods can provide more accurate glucose concentration in comparison to individual algorithms. Bagging metaregressor, specifically, performed better than individual algorithms in all prediction horizons for small datasets. Bagging ensemble method improved the percentage in zone A according to Clarkes error grid analysis by 4% and in some cases by 9%. Moreover, compartment models are proved to improve results in combination with any method at any prediction horizon. This strengthen the potential practical usefulness of the ensemble methods and the importance of building accurate compartment models.

A Hybrid Dynamic Wavelet-Based Modeling Method for Blood Glucose Concentration Prediction in Type 1 Diabetes

Background:

Diabetes mellitus (DM) is a chronic disease that affects public health. The prediction of blood glucose concentration (BGC) is essential to improve the therapy of type 1 DM (T1DM).

Methods:

Having considered the risk of hyper- and hypo-glycemia, we provide a new hybrid modeling approach for BGC prediction based on a dynamic wavelet neural network (WNN) model, including a heuristic input selection. The proposed models include a hybrid dynamic WNN (HDWNN) and a hybrid dynamic fuzzy WNN (HDFWNN). These wavelet-based networks are designed based on dominant wavelets selected by the genetic algorithm-orthogonal least square method. Furthermore, the HDFWNN model structure is improved using fuzzy rule induction, an important innovation in the fuzzy wavelet modeling. The proposed networks are tested on real data from 12 T1DM patients and also simulated data from 33 virtual patients with an UVa/ Padova simulator, an approved simulator by the US Food and Drug Administration.

Results:

A comparison study is performed in terms of new glucose-based assessment metrics, such as gFIT, glucose-weighted form of ESOD_n (gESOD_n), and glucose-weighted R² (gR²). For real patients’ data, the values of the mentioned indices are accomplished as gFIT = 0.97 ± 0.01, gESOD_n = 1.18 ± 0.38, and gR² = 0.88 ± 0.07. HDFWNN, HDWNN and jump NN method showed the prediction error (root mean square error [RMSE]) of 11.23 ± 2.77 mg/dl, 10.79 ± 3.86 mg/dl and 16.45 ± 4.33 mg/dl, respectively.

Conclusion:

Furthermore, the generalized estimating equation and post hoc tests show that proposed models perform better compared with other proposed methods.

Blood Uric Acid Prediction With Machine Learning: Model Development and Performance Comparison

Background

Uric acid is associated with noncommunicable diseases such as cardiovascular diseases, chronic kidney disease, coronary artery disease, stroke, diabetes, metabolic syndrome, vascular dementia, and hypertension. Therefore, uric acid is considered to be a risk factor for the development of noncommunicable diseases. Most studies on uric acid have been performed in developed countries, and the application of machine-learning approaches in uric acid prediction in developing countries is rare. Different machine-learning algorithms will work differently on different types of data in various diseases; therefore, a different investigation is needed for different types of data to identify the most accurate algorithms. Specifically, no study has yet focused on the urban corporate population in Bangladesh, despite the high risk of developing noncommunicable diseases for this population.

Objective

The aim of this study was to develop a model for predicting blood uric acid values based on basic health checkup test results, dietary information, and sociodemographic characteristics using machine-learning algorithms. The prediction of health checkup test measurements can be very helpful to reduce health management costs.

Methods

Various machine-learning approaches were used in this study because clinical input data are not completely independent and exhibit complex interactions. Conventional statistical models have limitations to consider these complex interactions, whereas machine learning can consider all possible interactions among input data. We used boosted decision tree regression, decision forest regression, Bayesian linear regression, and linear regression to predict personalized blood uric acid based on basic health checkup test results, dietary information, and sociodemographic characteristics. We evaluated the performance of these five widely used machine-learning models using data collected from 271 employees in the Grameen Bank complex of Dhaka, Bangladesh.

Results

The mean uric acid level was 6.63 mg/dL, indicating a borderline result for the majority of the sample (normal range <7.0 mg/dL). Therefore, these individuals should be monitoring their uric acid regularly. The boosted decision tree regression model showed the best performance among the models tested based on the root mean squared error of 0.03, which is also better than that of any previously reported model.

Conclusions

A uric acid prediction model was developed based on personal characteristics, dietary information, and some basic health checkup measurements. This model will be useful for improving awareness among high-risk individuals and populations, which can help to save medical costs. A future study could include additional features (eg, work stress, daily physical activity, alcohol intake, eating red meat) in improving prediction.

Application of Artificial Intelligence in Diabetes Education and Management: Present Status and Promising Prospect

Despite the rapid development of science and technology in healthcare, diabetes remains an incurable lifelong illness. Diabetes education aiming to improve the self-management skills is an essential way to help patients enhance their metabolic control and quality of life. Artificial intelligence (AI) technologies have made significant progress in transforming available genetic data and clinical information into valuable knowledge. The application of AI tech in disease education would be extremely beneficial considering their advantages in promoting individualization and full-course education intervention according to the unique pictures of different individuals. This paper reviews and discusses the most recent applications of AI techniques to various aspects of diabetes education. With the information and evidence collected, this review attempts to provide insight and guidance for the development of prospective, data-driven decision support platforms for diabetes management, with a focus on individualized patient management and lifelong educational interventions.

Review of Non-invasive Glucose Sensing Techniques: Optical, Electrical and Breath Acetone

Annual deaths in the U.S. attributed to diabetes are expected to increase from 280,210 in 2015 to 385,840 in 2030. The increase in the number of people affected by diabetes has made it one of the major public health challenges around the world. Better management of diabetes has the potential to decrease yearly medical costs and deaths associated with the disease. Non-invasive methods are in high demand to take the place of the traditional finger prick method as they can facilitate continuous glucose monitoring. Research groups have been trying for decades to develop functional commercial non-invasive glucose measurement devices. The challenges associated with non-invasive glucose monitoring are the many factors that contribute to inaccurate readings. We identify and address the experimental and physiological challenges and provide recommendations to pave the way for a systematic pathway to a solution. We have reviewed and categorized non-invasive glucose measurement methods based on: (1) the intrinsic properties of glucose, (2) blood/tissue properties and (3) breath acetone analysis. This approach highlights potential critical commonalities among the challenges that act as barriers to future progress. The focus here is on the pertinent physiological aspects, remaining challenges, recent advancements and the sensors that have reached acceptable clinical accuracy.

Fuzzy jump wavelet neural network based on rule induction for dynamic nonlinear system identification with real data applications

Aim

Fuzzy wavelet neural network (FWNN) has proven to be a promising strategy in the identification of nonlinear systems. The network considers both global and local properties, deals with imprecision present in sensory data, leading to desired precisions. In this paper, we proposed a new FWNN model nominated “Fuzzy Jump Wavelet Neural Network” (FJWNN) for identifying dynamic nonlinear-linear systems, especially in practical applications.

Methods

The proposed FJWNN is a fuzzy neural network model of the Takagi-Sugeno-Kang type whose consequent part of fuzzy rules is a linear combination of input regressors and dominant wavelet neurons as a sub-jump wavelet neural network. Each fuzzy rule can locally model both linear and nonlinear properties of a system. The linear relationship between the inputs and the output is learned by neurons with linear activation functions, whereas the nonlinear relationship is locally modeled by wavelet neurons. Orthogonal least square (OLS) method and genetic algorithm (GA) are respectively used to purify the wavelets for each sub-JWNN. In this paper, fuzzy rule induction improves the structure of the proposed model leading to less fuzzy rules, inputs of each fuzzy rule and model parameters. The real-world gas furnace and the real electromyographic (EMG) signal modeling problem are employed in our study. In the same vein, piecewise single variable function approximation, nonlinear dynamic system modeling, and Mackey–Glass time series prediction, ratify this method superiority. The proposed FJWNN model is compared with the state-of-the-art models based on some performance indices such as RMSE, RRSE, Rel ERR%, and VAF%.

Results

The proposed FJWNN model yielded the following results: RRSE (mean±std) of 10e-5±6e-5 for piecewise single-variable function approximation, RMSE (mean±std) of 2.6–4±2.6e-4 for the first nonlinear dynamic system modelling, RRSE (mean±std) of 1.59e-3±0.42e-3 for Mackey–Glass time series prediction, RMSE of 0.3421 for gas furnace modelling and VAF% (mean±std) of 98.24±0.71 for the EMG modelling of all trial signals, indicating a significant enhancement over previous methods.

Conclusions

The FJWNN demonstrated promising accuracy and generalization while moderating network complexity. This improvement is due to applying main useful wavelets in combination with linear regressors and using fuzzy rule induction. Compared to the state-of-the-art models, the proposed FJWNN yielded better performance and, therefore, can be considered a novel tool for nonlinear system identification.

Black-box Model Identification of Physical Activity in Type-l Diabetes Patients

In this paper we consider the problem of predicting future values of glucose in type-1 diabetes. In particular, we investigate the benefit of including physical activity, measured by an off-the-shelf wearable device, to other physiologic signals frequently used to predict blood-glucose concentration, namely injected insulin, carbohydrates intake, and past glucose samples measured by a Continuous Glucose Monitoring (CGM) sensor. Derivation of individualized predictors is crucial to cope with the wide inter- and intra-subject variability: learning and updating patient-specific models of the glucose-insulin system and using them to design personalized control actions has the potential to improve substantially patients' quality oflife. On data collected by 6 subjects for 5 days, we identify a black-box liner model that uses insulin and meal as inputs and glucose as output. Prediction Error Method (PEM) is used for parameter estimation. The personalized model is employed to derive patient-tailored predictors. This procedure is then repeated using a further physiological input, accounting for physical activity. The prediction accuracy of the two models, including or not physical activity, was compared on the basis of two metrics commonly used in system identification, namely Coefficient of Determination (COD) and Root Mean Squared Error. The models identified with physical activity have better performance, increasing the 3-hr prediction COD by mean ± standard deviation of 18.5% ± 30.1%.

Long-Term Glucose Forecasting Using a Physiological Model and Deconvolution of the Continuous Glucose Monitoring Signal

(1) Objective: Blood glucose forecasting in type 1 diabetes (T1D) management is a maturing field with numerous algorithms being published and a few of them having reached the commercialisation stage. However, accurate long-term glucose predictions (e.g., >60 min), which are usually needed in applications such as precision insulin dosing (e.g., an artificial pancreas), still remain a challenge. In this paper, we present a novel glucose forecasting algorithm that is well-suited for long-term prediction horizons. The proposed algorithm is currently being used as the core component of a modular safety system for an insulin dose recommender developed within the EU-funded PEPPER (Patient Empowerment through Predictive PERsonalised decision support) project. (2) Methods: The proposed blood glucose forecasting algorithm is based on a compartmental composite model of glucose-insulin dynamics, which uses a deconvolution technique applied to the continuous glucose monitoring (CGM) signal for state estimation. In addition to commonly employed inputs by glucose forecasting methods (i.e., CGM data, insulin, carbohydrates), the proposed algorithm allows the optional input of meal absorption information to enhance prediction accuracy. Clinical data corresponding to 10 adult subjects with T1D were used for evaluation purposes. In addition, in silico data obtained with a modified version of the UVa-Padova simulator was used to further evaluate the impact of accounting for meal absorption information on prediction accuracy. Finally, a comparison with two well-established glucose forecasting algorithms, the autoregressive exogenous (ARX) model and the latent variable-based statistical (LVX) model, was carried out. (3) Results: For prediction horizons beyond 60 min, the performance of the proposed physiological model-based (PM) algorithm is superior to that of the LVX and ARX algorithms. When comparing the performance of PM against the secondly ranked method (ARX) on a 120 min prediction horizon, the percentage improvement on prediction accuracy measured with the root mean square error, A-region of error grid analysis (EGA), and hypoglycaemia prediction calculated by the Matthews correlation coefficient, was 18.8 % , 17.9 % , and 80.9 % , respectively. Although showing a trend towards improvement, the addition of meal absorption information did not provide clinically significant improvements. (4) Conclusion: The proposed glucose forecasting algorithm is potentially well-suited for T1D management applications which require long-term glucose predictions.

Feasibility study of portable microwave microstrip open-loop resonator for non-invasive blood glucose level sensing: proof of concept

Self-management of blood glucose level is part and parcel of diabetes treatment, which involves invasive, painful, and uncomfortable methods. A proper non-invasive blood glucose monitor (NIBGM) is therefore desirable to deal better with it. Microwave resonators can potentially be used for such a purpose. Following the positive results from an in vitro previous work, a portable device based upon a microwave resonator was developed and assessed in a multicenter proof of concept. Its electrical response was analyzed when an individual's tongue was placed onto it. The study was performed with 352 individuals during their oral glucose tolerance tests, having four measurements per individual. The findings revealed that the accuracy must be improved before the diabetes community can make real use of the device. However, the relationship between the measuring parameter and the individual's blood glucose level is coherent with that from previous works, although with higher data dispersion. This is reflected in correlation coefficients between glycemia and the measuring magnitude consistently negative, although small, for the different datasets analyzed. Further research is proposed, focused on system improvements, individual calibration, and multitechnology approach. The study of the influence of other blood components different to glucose is also advised. Graphical abstract.

Glucose Concentration Measurement in Human Blood Plasma Solutions with Microwave Sensors

Three microwave sensors are used to track the glucose level of different human blood plasma solutions. In this paper, the sensors are evaluated as glucose trackers in a context close to real human blood. Different plasma solutions sets were prepared from a human blood sample at several added glucose concentrations up to 10 wt%, adding also ascorbic acid and lactic acid at different concentrations. The experimental results for the different sensors/solutions combinations are presented in this work. The sensors show good performance and linearity as glucose level retrievers, although the sensitivities change as the rest of components vary. Different sensor behaviors depending upon the concentrations of glucose and other components are identified and characterized. The results obtained in terms of sensitivity are coherent with previous works, highlighting the contribution of glucose to the dielectric losses of the solution. The results are also consistent with the frequency evolution of the electromagnetic signature of glucose found in the literature, and are helpful for selecting frequency bands for sensing purposes and envisioning future approaches to the challenging measurement in real biological contexts. Discussion of the implications of the results and guidelines for further research and development of more accurate sensors is offered.

Closed-Loop Control with Unannounced Exercise for Adults with Type 1 Diabetes using the Ensemble Model Predictive Control

This paper presents an individualized Ensemble Model Predictive Control (EnMPC) algorithm for blood glucose (BG) stabilization and hypoglycemia prevention in people with type 1 diabetes (T1D) who exercise regularly. The EnMPC formulation can be regarded as a simplified multi-stage MPC allowing for the consideration of N _en scenarios gathered from the patient's recent behavior. The patient's physical activity behavior is characterized by an exercise-specific input signal derived from the deconvolution of the patient's continuous glucose monitor (CGM), accounting for known inputs such as meal, and insulin pump records. The EnMPC controller was tested in a cohort of in silico patients with representative inter-subject and intra-subject variability from the FDA-accepted UVA/Padova simulation platform. Results show a significant improvement on hypoglycemia prevention after 30 min of mild to moderate exercise in comparison to a similarly tuned baseline controller (rMPC); with a reduction in hypoglycemia occurrences (< 70 mg/dL), from 3.08% ± 3.55 with rMPC to 0.78% ± 2.04 with EnMPC (P < 0.05).

GluNet: A Deep Learning Framework for Accurate Glucose Forecasting

For people with Type 1 diabetes (T1D), forecasting of blood glucose (BG) can be used to effectively avoid hyperglycemia, hypoglycemia and associated complications. The latest continuous glucose monitoring (CGM) technology allows people to observe glucose in real-time. However, an accurate glucose forecast remains a challenge. In this work, we introduce GluNet, a framework that leverages on a personalized deep neural network to predict the probabilistic distribution of short-term (30-60 minutes) future CGM measurements for subjects with T1D based on their historical data including glucose measurements, meal information, insulin doses, and other factors. It adopts the latest deep learning techniques consisting of four components: data pre-processing, label transform/recover, multi-layers of dilated convolution neural network (CNN), and post-processing. The method is evaluated in-silico for both adult and adolescent subjects. The results show significant improvements over existing methods in the literature through a comprehensive comparison in terms of root mean square error (RMSE) ([Formula: see text] mg/dL) with short time lag ([Formula: see text] minutes) for prediction horizons (PH) = 30 mins (minutes), and RMSE ([Formula: see text] mg/dL) with time lag ([Formula: see text] mins) for PH = 60 mins for virtual adult subjects. In addition, GluNet is also tested on two clinical data sets. Results show that it achieves an RMSE ([Formula: see text] mg/dL) with time lag ([Formula: see text] mins) for PH = 30 mins and an RMSE ([Formula: see text] mg/dL) with time lag ([Formula: see text] mins) for PH = 60 mins. These are the best reported results for glucose forecasting when compared with other methods including the neural network for predicting glucose (NNPG), the support vector regression (SVR), the latent variable with exogenous input (LVX), and the auto regression with exogenous input (ARX) algorithm.

Prediction and prevention of hypoglycaemic events in type-1 diabetic patients using machine learning

Tight blood glucose control reduces the risk of microvascular and macrovascular complications in patients with type 1 diabetes. However, this is very difficult due to the large intra-individual variability and other factors that affect glycaemic control. The main limiting factor to achieve strict control of glucose levels in patients on intensive insulin therapy is the risk of severe hypoglycaemia. Therefore, hypoglycaemia is the main safety problem in the treatment of type 1 diabetes, negatively affecting the quality of life of patients suffering from this disease. Decision support tools based on machine learning methods have become a viable way to enhance patient safety by anticipating adverse glycaemic events. This study proposes the application of four machine learning algorithms to tackle the problem of safety in diabetes management: (1) grammatical evolution for the mid-term continuous prediction of blood glucose levels, (2) support vector machines to predict hypoglycaemic events during postprandial periods, (3) artificial neural networks to predict hypoglycaemic episodes overnight, and (4) data mining to profile diabetes management scenarios. The proposal consists of the combination of prediction and classification capabilities of the implemented approaches. The resulting system significantly reduces the number of episodes of hypoglycaemia, improving safety and providing patients with greater confidence in decision-making.

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.

Artificial Intelligence for Diabetes Management and Decision Support: Literature Review

Background

Artificial intelligence methods in combination with the latest technologies, including medical devices, mobile computing, and sensor technologies, have the potential to enable the creation and delivery of better management services to deal with chronic diseases. One of the most lethal and prevalent chronic diseases is diabetes mellitus, which is characterized by dysfunction of glucose homeostasis.

Objective

The objective of this paper is to review recent efforts to use artificial intelligence techniques to assist in the management of diabetes, along with the associated challenges.

Methods

A review of the literature was conducted using PubMed and related bibliographic resources. Analyses of the literature from 2010 to 2018 yielded 1849 pertinent articles, of which we selected 141 for detailed review.

Results

We propose a functional taxonomy for diabetes management and artificial intelligence. Additionally, a detailed analysis of each subject category was performed using related key outcomes. This approach revealed that the experiments and studies reviewed yielded encouraging results.

Conclusions

We obtained evidence of an acceleration of research activity aimed at developing artificial intelligence-powered tools for prediction and prevention of complications associated with diabetes. Our results indicate that artificial intelligence methods are being progressively established as suitable for use in clinical daily practice, as well as for the self-management of diabetes. Consequently, these methods provide powerful tools for improving patients’ quality of life.

An ARIMA Model With Adaptive Orders for Predicting Blood Glucose Concentrations and Hypoglycemia

The continuous glucose monitoring system is an effective tool, which enables the users to monitor their blood glucose (BG) levels. Based on the continuous glucose monitoring (CGM) data, we aim at predicting future BG levels so that appropriate actions can be taken in advance to prevent hyperglycemia or hypoglycemia. Due to the time-varying nonstationarity of CGM data, verified by Augmented Dickey-Fuller test and analysis of variance, an autoregressive integrated moving average (ARIMA) model with an adaptive identification algorithm of model orders is proposed in the prediction framework. Such identification algorithm adaptively determines the model orders and simultaneously estimates the corresponding parameters using Akaike Information Criterion and least square estimation. A case study is conducted with the CGM data of diabetics under daily living conditions to analyze the prediction performance of the proposed model together with the early hypoglycemic alarms. Results show that the proposed model outperforms the adaptive univariate model and ARIMA model.

Prediction of Adverse Glycemic Events From Continuous Glucose Monitoring Signal

The most important objective of any diabetes therapy is to maintain the blood glucose concentration within the euglycemic range, avoiding or at least mitigating critical hypo/hyperglycemic episodes. Modern continuous glucose monitoring (CGM) devices bear the promise of providing the patients with an increased and timely awareness of glycemic conditions as these get dangerously near to hypo/hyperglycemia. The challenge is to detect, with reasonable advance, the patterns leading to risky situations, allowing the patient to make therapeutic decisions on the basis of future (predicted) glucose concentration levels. We underline that a technically sound performance comparison of the approaches proposed in recent years has yet to be done, thus it is unclear which one is preferred. The aim of this study is to fill this gap by carrying out a comparative analysis among the most common methods for glucose event prediction. Both regression and classification algorithms have been implemented and analyzed, including static and dynamic training approaches. The dataset consists of 89 CGM time series measured in diabetic subjects for 7 subsequent days. Performance metrics, specifically defined to assess and compare the event-prediction capabilities of the methods, have been introduced and analyzed. Our numerical results show that a static training approach exhibits better performance, in particular when regression methods are considered. However, classifiers show some improvement when trained for a specific event category, such as hyperglycemia, achieving performance comparable to the regressors, with the advantage of predicting the events sooner.

Artificial Intelligence Methodologies and Their Application to Diabetes

In the past decade diabetes management has been transformed by the addition of continuous glucose monitoring and insulin pump data. More recently, a wide variety of functions and physiologic variables, such as heart rate, hours of sleep, number of steps walked and movement, have been available through wristbands or watches. New data, hydration, geolocation, and barometric pressure, among others, will be incorporated in the future. All these parameters, when analyzed, can be helpful for patients and doctors' decision support. Similar new scenarios have appeared in most medical fields, in such a way that in recent years, there has been an increased interest in the development and application of the methods of artificial intelligence (AI) to decision support and knowledge acquisition. Multidisciplinary research teams integrated by computer engineers and doctors are more and more frequent, mirroring the need of cooperation in this new topic. AI, as a science, can be defined as the ability to make computers do things that would require intelligence if done by humans. Increasingly, diabetes-related journals have been incorporating publications focused on AI tools applied to diabetes. In summary, diabetes management scenarios have suffered a deep transformation that forces diabetologists to incorporate skills from new areas. This recently needed knowledge includes AI tools, which have become part of the diabetes health care. The aim of this article is to explain in an easy and plane way the most used AI methodologies to promote the implication of health care providers-doctors and nurses-in this field.

Variables to Be Monitored via Biomedical Sensors for Complete Type 1 Diabetes Mellitus Management: An Extension of the "On-Board" Concept

Type 1 diabetes mellitus (DM1) is a growing disease, and a deep understanding of the patient is required to prescribe the most appropriate treatment, adjusted to the patient's habits and characteristics. Before now, knowledge regarding each patient has been incomplete, discontinuous, and partial. However, the recent development of continuous glucose monitoring (CGM) and new biomedical sensors/gadgets, based on automatic continuous monitoring, offers a new perspective on DM1 management, since these innovative devices allow the collection of 24-hour biomedical data in addition to blood glucose levels. With this, it is possible to deeply characterize a diabetic person, offering a better understanding of his or her illness evolution, and, going further, develop new strategies to manage DM1. This new and global monitoring makes it possible to extend the "on-board" concept to other features. This well-known approach to the processing of variable "insulin" describes some inertias and aggregated/remaining effects. In this work, such analysis is carried out along with a thorough study of the significant variables to be taken into account/monitored-and how to arrange them-for a deep characterization of diabetic patients. Lastly, we present a case study evaluating the experience of the continuous and comprehensive monitoring of a diabetic patient, concluding that the huge potential of this new perspective could provide an acute insight into the patient's status and extract the maximum amount of knowledge, thus improving the DM1 management system in order to be fully functional.

Personalized blood glucose prediction: A hybrid approach using grammatical evolution and physiological models

The large patient variability in human physiology and the effects of variables such as exercise or meals challenge current prediction modeling techniques. Physiological models are very precise but they are typically complex and specific physiological knowledge is required. In contrast, data-based models allow the incorporation of additional inputs and accurately capture the relationship between these inputs and the outcome, but at the cost of losing the physiological meaning of the model. In this work, we designed a hybrid approach comprising physiological models for insulin and grammatical evolution, taking into account the clinical harm caused by deviations from the target blood glucose by using a penalizing fitness function based on the Clarke error grid. The prediction models were built using data obtained over 14 days for 100 virtual patients generated by the UVA/Padova T1D simulator. Midterm blood glucose was predicted for the 100 virtual patients using personalized models and different scenarios. The results obtained were promising; an average of 98.31% of the predictions fell in zones A and B of the Clarke error grid. Midterm predictions using personalized models are feasible when the configuration of grammatical evolution explored in this study is used. The study of new alternative models is important to move forward in the development of alarm-and-control applications for the management of type 1 diabetes and the customization of the patient's treatments. The hybrid approach can be adapted to predict short-term blood glucose values to detect continuous glucose-monitoring sensor errors and to estimate blood glucose values when the continuous glucose-monitoring system fails to provide them.

Kernel-based adaptive learning improves accuracy of glucose predictive modelling in type 1 diabetes: A proof-of-concept study

This study aims at demonstrating the need for nonlinear recursive models to the identification and prediction of the dynamic glucose system in type 1 diabetes. Nonlinear regression is performed in a reproducing kernel Hilbert space, by the Approximate Linear Dependency Kernel Recursive Least Squares (KRLS-ALD) algorithm, such that a sparse model structure is accomplished. The method is evaluated on seven people with type 1 diabetes in free-living conditions, where a change in glycaemic dynamics is forced by increasing the level of physical activity in the middle of the observational period. The univariate input allows for short-term (≤30 min) predictions with KRLS-ALD reaching an average root mean square error of 15.22±5.95 mgdL^-1 and an average time lag of 17.14±2.67 min for an horizon of 30 min. Its performance is considerably better than that of time-invariant (regularized) linear regression models.

Comparison of Machine Learning Approaches Toward Assessing the Risk of Developing Cardiovascular Disease as a Long-Term Diabetes Complication

The estimation of long-term diabetes complications risk is essential in the process of medical decision making. Guidelines for the management of Type 2 Diabetes Mellitus (T2DM) advocate calculating the Cardiovascular Disease (CVD) risk to initiate appropriate treatment. The objective of this study is to investigate the use of sophisticated machine learning techniques toward the development of personalized models able to predict the risk of fatal or nonfatal CVD incidence in T2DM patients. The important challenge of handling the unbalanced nature of the available dataset is addressed by applying novel ensemble strategies. Hybrid Wavelet Neural Networks (HWNNs) and Self-Organizing Maps (SOMs) constitute the primary models for building ensembles following a subsampling approach. Different methods for combining the decisions of the primary models are applied and comparatively assessed. Data from the 5-year follow up of 560 patients with T2DM are used for development and evaluation purposes. The highest discrimination performance (Area Under the Curve (AUC): 71.48%) is achieved by taking into account both the HWNN- and SOM- based primary models' outputs. The proposed method is superior to the Binomial Linear Regression (BLR) model justifying the need to apply more sophisticated techniques in order to produce reliable CVD risk scores.

A review of personalized blood glucose prediction strategies for T1DM patients

This paper presents a methodological review of models for predicting blood glucose (BG) concentration, risks and BG events. The surveyed models are classified into three categories, and they are presented in summary tables containing the most relevant data regarding the experimental setup for fitting and testing each model as well as the input signals and the performance metrics. Each category exhibits trends that are presented and discussed. This document aims to be a compact guide to determine the modeling options that are currently being exploited for personalized BG prediction.

Continuous Glucose Monitoring Sensors: Past, Present and Future Algorithmic Challenges

Continuous glucose monitoring (CGM) sensors are portable devices that allow measuring and visualizing the glucose concentration in real time almost continuously for several days and are provided with hypo/hyperglycemic alerts and glucose trend information. CGM sensors have revolutionized Type 1 diabetes (T1D) management, improving glucose control when used adjunctively to self-monitoring blood glucose systems. Furthermore, CGM devices have stimulated the development of applications that were impossible to create without a continuous-time glucose signal, e.g., real-time predictive alerts of hypo/hyperglycemic episodes based on the prediction of future glucose concentration, automatic basal insulin attenuation methods for hypoglycemia prevention, and the artificial pancreas. However, CGM sensors’ lack of accuracy and reliability limited their usability in the clinical practice, calling upon the academic community for the development of suitable signal processing methods to improve CGM performance. The aim of this paper is to review the past and present algorithmic challenges of CGM sensors, to show how they have been tackled by our research group, and to identify the possible future ones.

Non-invasive detection of fasting blood glucose level via electrochemical measurement of saliva

Machine learning techniques such as logistic regression (LR), support vector machine (SVM) and artificial neural network (ANN) were used to detect fasting blood glucose levels (FBGL) in a mixed population of healthy and diseased individuals in an Indian population. The occurrence of elevated FBGL was estimated in a non-invasive manner from the status of an individual’s salivary electrochemical parameters such as pH, redox potential, conductivity and concentration of sodium, potassium and calcium ions. The samples were obtained from 175 randomly selected volunteers comprising half healthy and half diabetic patients. The models were trained using 70 % of the total data, and tested upon the remaining set. For each algorithm, data points were cross-validated by randomly shuffling them three times prior to implementing the model. The performance of the machine learning technique was reported in terms of four statistically significant parameters—accuracy, precision, sensitivity and F1 score. SVM using RBF kernel showed the best performance for classifying high FBGLs with approximately 85 % accuracy, 84 % precision, 85 % sensitivity and 85 % F₁ score. This study has been approved by the ethical committee of All India Institute of Medical Sciences, New Delhi, India with the reference number: IEC/NP-278/01-08-2014, RP-29/2014.