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

A strategy based on integer programming for optimal dosing and timing of preventive hypoglycemic treatments in type 1 diabetes management

BACKGROUND AND OBJECTIVES

One of the major problems related to type 1 diabetes (T1D) management is hypoglycemia, a condition characterized by low blood glucose levels and responsible for reduced quality of life and increased mortality. Fast-acting carbohydrates, also known as hypoglycemic treatments (HT), can counteract this event. In the literature, dosage and timing of HT are usually based on heuristic rules. In the present work, we propose an algorithm for mitigating hypoglycemia by suggesting preventive HT consumption, with dosages and timing determined by solving an optimization problem.

METHODS

By leveraging integer programming and linear inequality constraints, the algorithm can bind the amount of suggested carbohydrates to standardized quantities (i.e., those available in "off-the-shelf" HT) and the minimal distance between consecutive suggestions (to reduce the nuisance for patients).

RESULTS

The proposed method was tested in silico and compared with competitor algorithms using the UVa/Padova T1D simulator. At the cost of a slight increase of HT consumed per day, the proposed algorithm produces the lowest median and interquartile range of the time spent in hypoglycemia, with a statistically significant improvement over most competitor algorithms. Also, the average number of hypoglycemic events per day is reduced to 0 in median.

CONCLUSIONS

Thanks to its positive performances and reduced computational burden, the proposed algorithm could be a candidate tool for integration in a DSS aimed at improving T1D management.

Generalization of a Deep Learning Model for Continuous Glucose Monitoring-Based Hypoglycemia Prediction: Algorithm Development and Validation Study

Background

Predicting hypoglycemia while maintaining a low false alarm rate is a challenge for the wide adoption of continuous glucose monitoring (CGM) devices in diabetes management. One small study suggested that a deep learning model based on the long short-term memory (LSTM) network had better performance in hypoglycemia prediction than traditional machine learning algorithms in European patients with type 1 diabetes. However, given that many well-recognized deep learning models perform poorly outside the training setting, it remains unclear whether the LSTM model could be generalized to different populations or patients with other diabetes subtypes.

Objective

The aim of this study was to validate LSTM hypoglycemia prediction models in more diverse populations and across a wide spectrum of patients with different subtypes of diabetes.

Methods

We assembled two large data sets of patients with type 1 and type 2 diabetes. The primary data set including CGM data from 192 Chinese patients with diabetes was used to develop the LSTM, support vector machine (SVM), and random forest (RF) models for hypoglycemia prediction with a prediction horizon of 30 minutes. Hypoglycemia was categorized into mild (glucose=54-70 mg/dL) and severe (glucose<54 mg/dL) levels. The validation data set of 427 patients of European-American ancestry in the United States was used to validate the models and examine their generalizations. The predictive performance of the models was evaluated according to the sensitivity, specificity, and area under the receiver operating characteristic curve (AUC).

Results

For the difficult-to-predict mild hypoglycemia events, the LSTM model consistently achieved AUC values greater than 97% in the primary data set, with a less than 3% AUC reduction in the validation data set, indicating that the model was robust and generalizable across populations. AUC values above 93% were also achieved when the LSTM model was applied to both type 1 and type 2 diabetes in the validation data set, further strengthening the generalizability of the model. Under different satisfactory levels of sensitivity for mild and severe hypoglycemia prediction, the LSTM model achieved higher specificity than the SVM and RF models, thereby reducing false alarms.

Conclusions

Our results demonstrate that the LSTM model is robust for hypoglycemia prediction and is generalizable across populations or diabetes subtypes. Given its additional advantage of false-alarm reduction, the LSTM model is a strong candidate to be widely implemented in future CGM devices for hypoglycemia prediction.

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.

Detection of Hypoglycemia and Hyperglycemia Using Noninvasive Wearable Sensors: Electrocardiograms and Accelerometry

BACKGROUND

Monitoring glucose excursions is important in diabetes management. This can be achieved using continuous glucose monitors (CGMs). However, CGMs are expensive and invasive. Thus, alternative low-cost noninvasive wearable sensors capable of predicting glycemic excursions could be a game changer to manage diabetes.

METHODS

In this article, we explore two noninvasive sensor modalities, electrocardiograms (ECGs) and accelerometers, collected on five healthy participants over two weeks, to predict both hypoglycemic and hyperglycemic excursions. We extract 29 features encompassing heart rate variability features from the ECG, and time- and frequency-domain features from the accelerometer. We evaluated two machine learning approaches to predict glycemic excursions: a classification model and a regression model.

RESULTS

The best model for both hypoglycemia and hyperglycemia detection was the regression model based on ECG and accelerometer data, yielding 76% sensitivity and specificity for hypoglycemia and 79% sensitivity and specificity for hyperglycemia. This had an improvement of 5% in sensitivity and specificity for both hypoglycemia and hyperglycemia when compared with using ECG data alone.

CONCLUSIONS

Electrocardiogram is a promising alternative not only to detect hypoglycemia but also to predict hyperglycemia. Supplementing ECG data with contextual information from accelerometer data can improve glucose prediction.

Individualized Models for Glucose Prediction in Type 1 Diabetes: Comparing Black-Box Approaches to a Physiological White-Box One

OBJECTIVE

Accurate blood glucose (BG) prediction are key in next-generation tools for type 1 diabetes (T1D) management, such as improved decision support systems and advanced closed-loop control. Glucose prediction algorithms commonly rely on black-box models. Large physiological models, successfully adopted for simulation, were little explored for glucose prediction, mostly because their parameters are hard to individualize. In this work, we develop a BG prediction algorithm based on a personalized physiological model inspired by the UVA/Padova T1D Simulator. Then we compare white-box and advanced black-box personalized prediction techniques.

METHODS

A personalized nonlinear physiological model is identified from patient data through a Bayesian approach based on Markov Chain Monte Carlo technique. The individualized model was integrated within a particle filter (PF) to predict future BG concentrations. The black-box methodologies considered are non-parametric models estimated via gaussian regression (NP), three deep learning methods: long-short-term-memory (LSTM), gated recurrent unit (GRU), temporal convolutional networks (TCN), and a recursive autoregressive with exogenous input model (rARX). BG forecasting performances are assessed for several prediction horizons (PH) on 12 individuals with T1D, monitored in free-living conditions under open-loop therapy for 10 weeks.

RESULTS

NP models provide the most effective BG predictions by achieving a root mean square error (RMSE), RMSE = 18.99 mg/dL, RMSE = 25.72 mg/dL and RMSE = 31.60 mg/dL, significantly outperforming: LSTM, GRU (for PH = 30 minutes), TCN, rARX, and the proposed physiological model for PH=30, 45 and 60 minutes.

CONCLUSIONS

Black-box strategies remain preferable for glucose prediction even when compared to a white-box model with sound physiological structure and individualized parameters.

A 2-dimensional model framework for blood glucose prediction based on iterative learning control architecture

The accurate, timely, and personalized prediction for future blood glucose (BG) levels is undoubtedly needed for further advancement of diabetes management technologies. Human inherent circadian rhythm and regular lifestyle resulting in similarity of daily glycemic dynamics play a positive role in the prediction of blood glucose. Inspired by the iterative learning control (ILC) method in the field of automatic control, a 2-dimensional (2-D) model framework is constructed to predict the future blood glucose levels by taking both the short-range information within a day (intra-day) and long-range information between days (inter-day) into account. In this framework, the radial basis function neural network was applied to capture nonlinear relationships in glycemic metabolism, that is, short-range temporal dependence and long-range contemporaneous dependence on previous days. We build models for each patient, and the models were tested on the in silico datasets at various prediction horizons (PHs). The learning model developed in the 2-D framework successfully increases the accuracy and reduces the delay of predictions. This modeling framework provides a new point of view for BG level prediction and contributes to the development of personalized glucose management, such as hypoglycemia warning and glycemic control.

Combined Use of Glucose-Specific Model Identification and Alarm Strategy Based on Prediction-Funnel to Improve Online Forecasting of Hypoglycemic Events

BACKGROUND

Advanced decision support systems for type 1 diabetes (T1D) management often embed prediction modules, which allow T1D people to take preventive actions to avoid critical episodes like hypoglycemia. Real-time prediction of blood glucose (BG) concentration relies on a subject-specific model of glucose-insulin dynamics. Model parameter identification is usually based on the mean square error (MSE) cost function, and the model is usually used to predict BG at a single prediction horizon (PH). Finally, a hypo-alarm is raised if the predicted BG crosses a threshold. This work aims to show that real-time hypoglycemia forecasting can be improved by leveraging: a glucose-specific mean square error (gMSE) cost function in model's parameters identification, and a "prediction-funnel," that is, confidence intervals (CIs) for multiple PHs, within the hypo-alarm-raising strategy.

METHODS

Autoregressive integrated moving average with exogenous input (ARIMAX) models are selected to illustrate the proposed solution (use of gMSE and prediction-funnel) and its assessment against the conventional approach (MSE and single PH). The gMSE penalizes the model misfit in unsafe BG ranges (e.g., hypoglycemia), and the prediction-funnel allows raising an alarm by monitoring if the CIs cross a suitable threshold. The algorithms were evaluated by measuring precision (P), recall (R), F1-score (F1), false positive per day (FP/day), and time gain (TG) on a real dataset collected in 11 T1D individuals.

RESULTS

The best performance is achieved exploiting both the gMSE and the prediction-funnel: P = 65%, R = 88%, F1 = 75%, FP/day = 0.29, and mean TG = 15 minutes.

CONCLUSIONS

The combined use of a glucose-specific metric and an alarm-raising strategy based on the prediction-funnel allows achieving a more effective and reliable hypoglycemia prediction algorithm.

A simple modeling framework for prediction in the human glucose-insulin system

Forecasting blood glucose (BG) levels with routinely collected data is useful for glycemic management. BG dynamics are nonlinear, complex, and nonstationary, which can be represented by nonlinear models. However, the sparsity of routinely collected data creates parameter identifiability issues when high-fidelity complex models are used, thereby resulting in inaccurate forecasts. One can use models with reduced physiological fidelity for robust and accurate parameter estimation and forecasting with sparse data. For this purpose, we approximate the nonlinear dynamics of BG regulation by a linear stochastic differential equation: we develop a linear stochastic model, which can be specialized to different settings: type 2 diabetes mellitus (T2DM) and intensive care unit (ICU), with different choices of appropriate model functions. The model includes deterministic terms quantifying glucose removal from the bloodstream through the glycemic regulation system and representing the effect of nutrition and externally delivered insulin. The stochastic term encapsulates the BG oscillations. The model output is in the form of an expected value accompanied by a band around this value. The model parameters are estimated patient-specifically, leading to personalized models. The forecasts consist of values for BG mean and variation, quantifying possible high and low BG levels. Such predictions have potential use for glycemic management as part of control systems. We present experimental results on parameter estimation and forecasting in T2DM and ICU settings. We compare the model's predictive capability with two different nonlinear models built for T2DM and ICU contexts to have a sense of the level of prediction achieved by this model.

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.

Data-based modeling for hypoglycemia prediction: Importance, trends, and implications for clinical practice

Background and objective

Hypoglycemia is a key barrier to achieving optimal glycemic control in people with diabetes, which has been proven to cause a set of deleterious outcomes, such as impaired cognition, increased cardiovascular disease, and mortality. Hypoglycemia prediction has come to play a role in diabetes management as big data analysis and machine learning (ML) approaches have become increasingly prevalent in recent years. As a result, a review is needed to summarize the existing prediction algorithms and models to guide better clinical practice in hypoglycemia prevention.

Materials and methods

PubMed, EMBASE, and the Cochrane Library were searched for relevant studies published between 1 January 2015 and 8 December 2022. Five hypoglycemia prediction aspects were covered: real-time hypoglycemia, mild and severe hypoglycemia, nocturnal hypoglycemia, inpatient hypoglycemia, and other hypoglycemia (postprandial, exercise-related).

Results

From the 5,042 records retrieved, we included 79 studies in our analysis. Two major categories of prediction models are identified by an overview of the chosen studies: simple or logistic regression models based on clinical data and data-based ML models (continuous glucose monitoring data is most commonly used). Models utilizing clinical data have identified a variety of risk factors that can lead to hypoglycemic events. Data-driven models based on various techniques such as neural networks, autoregressive, ensemble learning, supervised learning, and mathematical formulas have also revealed suggestive features in cases of hypoglycemia prediction.

Conclusion

In this study, we looked deep into the currently established hypoglycemia prediction models and identified hypoglycemia risk factors from various perspectives, which may provide readers with a better understanding of future trends in this topic.

Chinese diabetes datasets for data-driven machine learning

Data of the diabetes mellitus patients is essential in the study of diabetes management, especially when employing the data-driven machine learning methods into the management. To promote and facilitate the research in diabetes management, we have developed the ShanghaiT1DM and ShanghaiT2DM Datasets and made them publicly available for research purposes. This paper describes the datasets, which was acquired on Type 1 (n = 12) and Type 2 (n = 100) diabetic patients in Shanghai, China. The acquisition has been made in real-life conditions. The datasets contain the clinical characteristics, laboratory measurements and medications of the patients. Moreover, the continuous glucose monitoring readings with 3 to 14 days as a period together with the daily dietary information are also provided. The datasets can contribute to the development of data-driven algorithms/models and diabetes monitoring/managing technologies.

Comparison of ARIMA model, DNN model and LSTM model in predicting disease burden of occupational pneumoconiosis in Tianjin, China

BACKGROUND

This study aims to explore appropriate model for predicting the disease burden of pneumoconiosis in Tianjin by comparing the prediction effects of Autoregressive Integrated Moving Average (ARIMA) model, Deep Neural Networks (DNN) model and multivariate Long Short-Term Memory Neural Network (LSTM) models.

METHODS

Disability adjusted life year (DALY) was used to evaluate the disease burden of occupational pneumoconiosis. ARIMA model, DNN model and multivariate LSTM model were used to establish prediction model. Three performance evaluation metrics including Root Mean Squared Error (RMSE), Mean Absolute Error (MAE) and Mean Absolute Percentage Error (MAPE) were used to compare the prediction effects of the three models.

RESULTS

From 1990 to 2021, there were 10,694 cases of pneumoconiosis patients in Tianjin, resulting in a total of 112,725.52 person-years of DALY. During this period, the annual DALY showed a fluctuating trend, but it had a strong correlation with the number of pneumoconiosis patients, the average age of onset, the average age of receiving dust and the gross industrial product, and had a significant nonlinear relationship with them. The comparison of prediction results showed that the performance of multivariate LSTM model and DNN model is much better than that of traditional ARIMA model. Compared with the DNN model, the multivariate LSTM model performed better in the training set, showing lower RMES (42.30 vs. 380.96), MAE (29.53 vs. 231.20) and MAPE (1.63% vs. 2.93%), but performed less stable than the DNN on the test set, showing slightly higher RMSE (1309.14 vs. 656.44), MAE (886.98 vs. 594.47) and MAPE (36.86% vs. 22.43%).

CONCLUSION

The machine learning techniques of DNN and LSTM are an innovative method to accurately and efficiently predict the burden of pneumoconiosis with the simplest data. It has great application prospects in the monitoring and early warning system of occupational disease burden.

A Hypoglycemia Early Alarm Method for Patients with Type 1 Diabetes Based on Multi-dimensional Sequential Pattern Mining

Hypoglycemia is a limiting factor for blood glucose management. Serious symptoms such as seizures, and coma may occur during severe hypoglycemia, and nocturnal hypoglycemia is particularly dangerous for patients with type 1 diabetes (T1D). An effective early alarm method is essential for hypoglycemia prevention but challenging, as blood glucose is affected by many factors and the hypoglycemia sequence patterns vary from person to person. In this paper, we proposed a hypoglycemia early alarm method for mining the hidden information in blood glucose based on multi-dimensional sequential pattern mining. The blood glucose, meal, and insulin time series information were used to construct a multi-dimensional database, then the UniSeq algorithm was used to extract multi-dimensional hypoglycemia sequence patterns. Hypoglycemia early alarm was realized through pattern matching with real-time blood glucose. The public OhioT1DM dataset was used for performance evaluation. The experiment results were: 75.76% Sensitivity, 75% Precision, 75.38% F1 score, and 25.17 minutes early alarm time. The result verified that multi-dimensional sequential pattern mining can extract more hidden information and demonstrate more potential significance in providing comprehensive diagnosis support for personalized treatment. Furthermore, early alarms for potential hypoglycemia can also reserve sufficient time for blood glucose management.

A parsimonious model of blood glucose homeostasis

The mathematical modelling of biological systems has historically followed one of two approaches: comprehensive and minimal. In comprehensive models, the involved biological pathways are modelled independently, then brought together as an ensemble of equations that represents the system being studied, most often in the form of a large system of coupled differential equations. This approach often contains a very large number of tuneable parameters (> 100) where each describes some physical or biochemical subproperty. As a result, such models scale very poorly when assimilation of real world data is needed. Furthermore, condensing model results into simple indicators is challenging, an important difficulty in scenarios where medical diagnosis is required. In this paper, we develop a minimal model of glucose homeostasis with the potential to yield diagnostics for pre-diabetes. We model glucose homeostasis as a closed control system containing a self-feedback mechanism that describes the collective effects of the physiological components involved. The model is analyzed as a planar dynamical system, then tested and verified using data collected with continuous glucose monitors (CGMs) from healthy individuals in four separate studies. We show that, although the model has only a small number (3) of tunable parameters, their distributions are consistent across subjects and studies both for hyperglycemic and for hypoglycemic episodes.

Sense and Learn: Recent Advances in Wearable Sensing and Machine Learning for Blood Glucose Monitoring and Trend-Detection

Diabetes mellitus is characterized by elevated blood glucose levels, however patients with diabetes may also develop hypoglycemia due to treatment. There is an increasing demand for non-invasive blood glucose monitoring and trends detection amongst people with diabetes and healthy individuals, especially athletes. Wearable devices and non-invasive sensors for blood glucose monitoring have witnessed considerable advances. This review is an update on recent contributions utilizing novel sensing technologies over the past five years which include electrocardiogram, electromagnetic, bioimpedance, photoplethysmography, and acceleration measures as well as bodily fluid glucose sensors to monitor glucose and trend detection. We also review methods that use machine learning algorithms to predict blood glucose trends, especially for high risk events such as hypoglycemia. Convolutional and recurrent neural networks, support vector machines, and decision trees are examples of such machine learning algorithms. Finally, we address the key limitations and challenges of these studies and provide recommendations for future work.

Optimization and Evaluation of an Intelligent Short-Term Blood Glucose Prediction Model Based on Noninvasive Monitoring and Deep Learning Techniques

Continuous noninvasive blood glucose monitoring and estimation management by using photoplethysmography (PPG) technology always have a series of problems, such as substantial time variability, inaccuracy, and complex nonlinearity. This paper proposes a blood glucose (BG) prediction model for more precise prediction based on BG series decomposition by complete aggregation empirical mode decomposition based on adaptive white noise (CEEMDAN) and the gated recurrent unit (GRU) that is optimized by improved bacterial foraging optimization (IBFO). Hierarchical clustering technology recombines the decomposed BG series according to their sample entropy and the correlations with the original BG trends. Dynamic BG trends are regressed separately for each recombined BG series by the GRU model to realize the more precise estimations, which are optimized by IBFO for its structure and superparameters. Through experiments, the optimized and basic LSTM, RNN, and support vector regression (SVR) are compared to evaluate the performance of the proposed model. The experimental results indicate that the root mean square error (RMSE) and mean absolute percentage error (MAPE) of the 15-min IBFO-GRU prediction is improved on average by about 13.1% and 18.4%, respectively, compared with those of the RNN and LSTM optimized by IBFO. Meanwhile, the proposed model improved the Clarke error grid results by about 2.6% and 5.0% compared with those of the IBFO-LSTM and IBFO-RNN in 30-min prediction and by 4.1% and 6.6% in 15-min ahead forecast, respectively. The evaluation outcomes of our proposed CEEMDAN-IBFO-GRU model have high accuracy and adaptability and can effectively provide early intervention control of the occurrence of hyperglycemic complications.

Comparison of ARIMA and LSTM for prediction of hemorrhagic fever at different time scales in China

Objectives

This study intends to build and compare two kinds of forecasting models at different time scales for hemorrhagic fever incidence in China.

Methods

Autoregressive Integrated Moving Average (ARIMA) and Long Short-Term Memory Neural Network (LSTM) were adopted to fit monthly, weekly and daily incidence of hemorrhagic fever in China from 2013 to 2018. The two models, combined and uncombined with rolling forecasts, were used to predict the incidence in 2019 to examine their stability and applicability.

Results

ARIMA (2, 1, 1) (0, 1, 1)₁₂, ARIMA (1, 1, 3) (1, 1, 1)₅₂ and ARIMA (5, 0, 1) were selected as the best fitting ARIMA model for monthly, weekly and daily incidence series, respectively. The LSTM model with 64 neurons and Stochastic Gradient Descent (SGDM) for monthly incidence, 8 neurons and Adaptive Moment Estimation (Adam) for weekly incidence, and 64 neurons and Root Mean Square Prop (RMSprop) for daily incidence were selected as the best fitting LSTM models. The values of root mean square error (RMSE), mean absolute error (MAE) and mean absolute percentage error (MAPE) of the models combined with rolling forecasts in 2019 were lower than those of the direct forecasting models for both ARIMA and LSTM. It was shown from the forecasting performance in 2019 that ARIMA was better than LSTM for monthly and weekly forecasting while the LSTM was better than ARIMA for daily forecasting in rolling forecasting models.

Conclusions

Both ARIMA and LSTM could be used to build a prediction model for the incidence of hemorrhagic fever. Different models might be more suitable for the incidence prediction at different time scales. The findings can provide a good reference for future selection of prediction models and establishments of early warning systems for hemorrhagic fever.

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

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

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.

A personalized blood glucose level prediction model with a fine-tuning strategy: A proof-of-concept study

BACKGROUND

The accurate prediction of blood glucose (BG) level is still a challenge for diabetes management. This is due to various factors such as diet, personal physiological characteristics, stress, and activities influence changes in BG level. To develop an accurate BG level predictive model, we propose a personalized model based on a convolutional neural network (CNN) with a fine-tuning strategy.

METHODS

We utilized continuous glucose monitoring (CGM) datasets from 1052 professional CGM sessions and split them into three groups according to type 1, type 2, and gestational diabetes mellitus (T1DM, T2DM, and GDM, respectively). During the preprocessing, only CGM data points were utilized, and future BG levels of four different prediction horizons (PHs, 15, 30, 45, and 60 min) were used as output. In training, we trained a general CNN and a multi-output random forest regressor using a hold-out method for each group. Next, we developed two personalized models: (1) by fine-tuning the general CNN on partial sample points of each CGM dataset, and (2) by learning a CNN from scratch on the points.

RESULTS

For all groups, the fine-tuned CNN showed the lowest average root mean squared error, average mean absolute percentage error, highest average time gain (PH = 15 and 60 min in T1DM) and highest percentage in region A of Clarke error grid analysis at all PHs. In the performance comparison between the fine-tuned CNN and other models, we found that the fine-tuned CNN improved the performance of the general CNN in most cases and outperformed the scratch CNN at all PHs in all groups, making the fine-tuning strategy was useful for accurate BG level prediction. We analyzed all cases of four predictive patterns in each group, and found that the input BG level trend and the BG level at the time of prediction were related to the future BG level trend.

CONCLUSIONS

We demonstrated the efficacy of the fine-tuning method in a large number of CGM datasets and analyzed the four predictive patterns. Therefore, we believe that the proposed method will significantly contribute to the development of an accurate personalized model and the analysis for its predictions.

A predictive model incorporating the change detection and Winsorization methods for alerting hypoglycemia and hyperglycemia

This paper focuses on establishing an effective predictive model to quickly and accurately alert hypoglycemia and hyperglycemia for helping control blood glucose levels of people with diabetes. In general, a good predictive model is established on the features of data. Inspired by this, we first analyze the characteristics of continuous glucose monitoring (CGM) data by the equality of variances test and outlier detection, which show time-varying fluctuations and jump points in CGM data. Therefore, we incorporate the change detection method and the Winsorization method into the predictive model based on the autoregressive moving average (ARMA) model and the recursive least squares (RLS) method to fit the above characteristics. To the best of our knowledge, the proposed method is the first attempt to give a solution for matching the time-varying fluctuations and jump points of CGM data simultaneously. A case study using CGM data is given to validate the effectiveness of the proposed method under 30-min-ahead prediction. The results show that the proposed method can improve the true alarm ratio of hypoglycemia and hyperglycemia from 0.7983 to 0.8783, and lengthen the average advance detection time of hypoglycemia and hyperglycemia from 19.77 to 22.64 min.

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.

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.

Linear Model Identification for Personalized Prediction and Control in Diabetes

OBJECTIVE

Type-1 diabetes (T1D) is a metabolic disease, characterized by impaired blood glucose (BG) regulation, which forces patients to multiple daily therapeutic actions, the most critical of which is exogenous insulin administration. T1D management can considerably benefit of mathematical models enabling accurate BG predictions and effective/safe automated insulin delivery. In building these models, dealing with large inter- and intra-patient variability in glucose-insulin dynamics represents a major challenge. The aim of the present work is to assess linear black-box methods, including a novel non-parametric methodology, for learning individualized models of glucose response to insulin and meal, suitable for model-based prediction and control.

METHODS

We focus on data-driven techniques for linear model-learning and compare the state-of-art parametric pipeline, exploring all its degrees of freedom (including population vs. individualized parameter identification, model class chosen among ARX/ARMAX/ARIMAX/Box-Jenkins, model order selection criteria, etc.), with a novel non-parametric approach based on Gaussian regression and stable spline kernel. By using data collected in 11 T1D individuals, we evaluate effectiveness of the different models by measuring root mean squared error (RMSE), coefficient of determination (COD), and time gain of the associated BG predictors.

RESULTS

Among the tested approaches, the non-parametric technique results in the best prediction performance: median RMSE=29.8mg/dL, and median COD=57.4%, for a prediction horizon (PH) of 60 min. With respect to the state-of-the-art parametric techniques, the non-parametric approach grants a COD improvement of about 2%, 7%, 21%, and 41% for PH = 30, 60, 90, and 120 min (paired-sample t-test p 0.001, p=0.003, p=0.03, and p=0.07 respectively).

CONCLUSION

Non-parametric linear model-learning grants statistically significant improvement with respect to the state-of-art parametric approach. The higher PH, the more pronounced the improvement.

SIGNIFICANCE

The use of a linear non-parametric model-learning approach for model-based prediction and control could bring to a more prompt, safe and effective T1D management.

A review of biosensor technology and algorithms for glucose monitoring

Diabetes mellitus (DM) has become a serious illness in the whole world. Until now, there is no effective cure for patients with DM. It is well known that the glucose level is one key factor to determine the progress of DM. It is also an important reference to carry out the accurate and timely treatment for patients with DM. In this article, the related biosensors technology that can be utilized to identify and predict glucose level are reviewed in detail, including the algorithms that can help to achieve numerical value of glucose level. Firstly, the biosensor technology based on the physiological fluids are illustrated, including blood, sweat, interstitial fluid, ocular fluid, and other available fluids. Secondly, the algorithms for achieving numerical value of glucose level are investigated, including the physiological model-based method and the machine learning-based method. Finally, the future development trend and challenges of glucose level monitoring are given and the conclusions are drawn.

Feature-Based Machine Learning Model for Real-Time Hypoglycemia Prediction

BACKGROUND

Hypoglycemia is a serious health concern in youth with type 1 diabetes (T1D). Real-time data from continuous glucose monitoring (CGM) can be used to predict hypoglycemic risk, allowing patients to take timely intervention measures.

METHODS

A machine learning model is developed for probabilistic prediction of hypoglycemia (<70 mg/dL) in 30- and 60-minute time horizons based on CGM datasets obtained from 112 patients over a range of 90 days consisting of over 1.6 million CGM values under normal living conditions. A comprehensive set of features relevant for hypoglycemia are developed and a parsimonious subset with most influence on predicting hypoglycemic risk is identified. Model performance is evaluated both with and without contextual information on insulin and carbohydrate intake.

RESULTS

The model predicted hypoglycemia with >91% sensitivity for 30- and 60-minute prediction horizons while maintaining specificity >90%. Inclusion of insulin and carbohydrate data yielded performance improvement for 60-minute but not for 30-minute predictions. Model performance was highest for nocturnal hypoglycemia (~95% sensitivity). Shortterm (less than one hour) and medium-term (one to four hours) features for good prediction performance are identified.

CONCLUSIONS

Innovative feature identification facilitated high performance for hypoglycemia risk prediction in pediatric youth with T1D. Timely alerts of impending hypoglycemia may enable proactive measures to avoid severe hypoglycemia and achieve optimal glycemic control. The model will be deployed on a patient-facing smartphone application in an upcoming pilot study.

Comparison of ARIMA and LSTM in Forecasting the Incidence of HFMD Combined and Uncombined with Exogenous Meteorological Variables in Ningbo, China

Background: This study intends to identify the best model for predicting the incidence of hand, foot and mouth disease (HFMD) in Ningbo by comparing Autoregressive Integrated Moving Average (ARIMA) and Long Short-Term Memory Neural Network (LSTM) models combined and uncombined with exogenous meteorological variables. Methods: The data of daily HFMD incidence in Ningbo from January 2014 to November 2017 were set as the training set, and the data of December 2017 were set as the test set. ARIMA and LSTM models combined and uncombined with exogenous meteorological variables were adopted to fit the daily incidence of HFMD by using the data of the training set. The forecasting performances of the four fitted models were verified by using the data of the test set. Root mean square error (RMSE) was selected as the main measure to evaluate the performance of the models. Results: The RMSE for multivariate LSTM, univariate LSTM, ARIMA and ARIMAX (Autoregressive Integrated Moving Average Model with Exogenous Input Variables) was 10.78, 11.20, 12.43 and 14.73, respectively. The LSTM model with exogenous meteorological variables has the best performance among the four models and meteorological variables can increase the prediction accuracy of LSTM model. For the ARIMA model, exogenous meteorological variables did not increase the prediction accuracy but became the interference factor of the model. Conclusions: Multivariate LSTM is the best among the four models to fit the daily incidence of HFMD in Ningbo. It can provide a scientific method to build the HFMD early warning system and the methodology can also be applied to other communicable diseases.

Improved Low-Glucose Predictive Alerts Based on Sustained Hypoglycemia: Model Development and Validation Study

BACKGROUND

Predictive alerts for impending hypoglycemic events enable persons with type 1 diabetes to take preventive actions and avoid serious consequences.

OBJECTIVE

This study aimed to develop a prediction model for hypoglycemic events with a low false alert rate, high sensitivity and specificity, and good generalizability to new patients and time periods.

METHODS

Performance improvement by focusing on sustained hypoglycemic events, defined as glucose values less than 70 mg/dL for at least 15 minutes, was explored. Two different modeling approaches were considered: (1) a classification-based method to directly predict sustained hypoglycemic events, and (2) a regression-based prediction of glucose at multiple time points in the prediction horizon and subsequent inference of sustained hypoglycemia. To address the generalizability and robustness of the model, two different validation mechanisms were considered: (1) patient-based validation (model performance was evaluated on new patients), and (2) time-based validation (model performance was evaluated on new time periods).

RESULTS

This study utilized data from 110 patients over 30-90 days comprising 1.6 million continuous glucose monitoring values under normal living conditions. The model accurately predicted sustained events with >97% sensitivity and specificity for both 30- and 60-minute prediction horizons. The false alert rate was kept to <25%. The results were consistent across patient- and time-based validation strategies.

CONCLUSIONS

Providing alerts focused on sustained events instead of all hypoglycemic events reduces the false alert rate and improves sensitivity and specificity. It also results in models that have better generalizability to new patients and time periods.

Stacked LSTM based deep recurrent neural network with kalman smoothing for blood glucose prediction

BACKGROUND

Blood glucose (BG) management is crucial for type-1 diabetes patients resulting in the necessity of reliable artificial pancreas or insulin infusion systems. In recent years, deep learning techniques have been utilized for a more accurate BG level prediction system. However, continuous glucose monitoring (CGM) readings are susceptible to sensor errors. As a result, inaccurate CGM readings would affect BG prediction and make it unreliable, even if the most optimal machine learning model is used.

METHODS

In this work, we propose a novel approach to predicting blood glucose level with a stacked Long short-term memory (LSTM) based deep recurrent neural network (RNN) model considering sensor fault. We use the Kalman smoothing technique for the correction of the inaccurate CGM readings due to sensor error.

RESULTS

For the OhioT1DM (2018) dataset, containing eight weeks' data from six different patients, we achieve an average RMSE of 6.45 and 17.24 mg/dl for 30 min and 60 min of prediction horizon (PH), respectively.

CONCLUSIONS

To the best of our knowledge, this is the leading average prediction accuracy for the ohioT1DM dataset. Different physiological information, e.g., Kalman smoothed CGM data, carbohydrates from the meal, bolus insulin, and cumulative step counts in a fixed time interval, are crafted to represent meaningful features used as input to the model. The goal of our approach is to lower the difference between the predicted CGM values and the fingerstick blood glucose readings-the ground truth. Our results indicate that the proposed approach is feasible for more reliable BG forecasting that might improve the performance of the artificial pancreas and insulin infusion system for T1D diabetes management.

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.

A multi-level hypoglycemia early alarm system based on sequence pattern mining

Background

Early alarm of hypoglycemia, detection of asymptomatic hypoglycemia, and effective control of blood glucose fluctuation make a great contribution to diabetic treatment. In this study, we designed a multi-level hypoglycemia early alarm system to mine potential information in Continuous Glucose Monitoring (CGM) time series and improve the overall alarm performance for different clinical situations.

Methods

Through symbolizing the historical CGM records, the Prefix Span was adopted to obtain the early alarm/non-alarm frequent sequence libraries of hypoglycemia events. The longest common subsequence was used to remove the common frequent sequence for achieving the hypoglycemia early alarm in different clinical situations. Then, the frequent sequence pattern libraries with different risk thresholds were designed as the core module of the proposed multi-level hypoglycemia early alarm system.

Results

The model was able to predict hypoglycemia events in the clinical dataset of level-I (sensitivity 85.90%, false-positive 23.86%, miss alarm rate 14.10%, average early alarm time 20.61 min), level-II (sensitivity 80.36%, false-positive 17.37%, miss alarm rate 19.63%, average early alarm time 27.66 min), and level-III (sensitivity 78.07%, false-positive 13.59%, miss alarm rate 21.93%, average early alarm time 33.80 min), respectively.

Conclusions

The proposed approach could effectively predict hypoglycemia events based on different risk thresholds to meet different prevention and treatment requirements. Moreover, the experimental results confirm the practicality and prospects of the proposed early alarm system, which reflects further significance in personalized medicine for hypoglycemia prevention.

Advanced Diabetes Management Using Artificial Intelligence and Continuous Glucose Monitoring Sensors

Wearable continuous glucose monitoring (CGM) sensors are revolutionizing the treatment of type 1 diabetes (T1D). These sensors provide in real-time, every 1-5 min, the current blood glucose concentration and its rate-of-change, two key pieces of information for improving the determination of exogenous insulin administration and the prediction of forthcoming adverse events, such as hypo-/hyper-glycemia. The current research in diabetes technology is putting considerable effort into developing decision support systems for patient use, which automatically analyze the patient's data collected by CGM sensors and other portable devices, as well as providing personalized recommendations about therapy adjustments to patients. Due to the large amount of data collected by patients with T1D and their variety, artificial intelligence (AI) techniques are increasingly being adopted in these decision support systems. In this paper, we review the state-of-the-art methodologies using AI and CGM sensors for decision support in advanced T1D management, including techniques for personalized insulin bolus calculation, adaptive tuning of bolus calculator parameters and glucose prediction.

A machine-learning approach to predict postprandial hypoglycemia

BACKGROUND

For an effective artificial pancreas (AP) system and an improved therapeutic intervention with continuous glucose monitoring (CGM), predicting the occurrence of hypoglycemia accurately is very important. While there have been many studies reporting successful algorithms for predicting nocturnal hypoglycemia, predicting postprandial hypoglycemia still remains a challenge due to extreme glucose fluctuations that occur around mealtimes. The goal of this study is to evaluate the feasibility of easy-to-use, computationally efficient machine-learning algorithm to predict postprandial hypoglycemia with a unique feature set.

METHODS

We use retrospective CGM datasets of 104 people who had experienced at least one hypoglycemia alert value during a three-day CGM session. The algorithms were developed based on four machine learning models with a unique data-driven feature set: a random forest (RF), a support vector machine using a linear function or a radial basis function, a K-nearest neighbor, and a logistic regression. With 5-fold cross-subject validation, the average performance of each model was calculated to compare and contrast their individual performance. The area under a receiver operating characteristic curve (AUC) and the F1 score were used as the main criterion for evaluating the performance.

RESULTS

In predicting a hypoglycemia alert value with a 30-min prediction horizon, the RF model showed the best performance with the average AUC of 0.966, the average sensitivity of 89.6%, the average specificity of 91.3%, and the average F1 score of 0.543. In addition, the RF showed the better predictive performance for postprandial hypoglycemic events than other models.

CONCLUSION

In conclusion, we showed that machine-learning algorithms have potential in predicting postprandial hypoglycemia, and the RF model could be a better candidate for the further development of postprandial hypoglycemia prediction algorithm to advance the CGM technology and the AP technology further.