Blood Glucose Level Prediction: Advanced Deep-Ensemble Learning Approach

Multivariate Glucose Forecasting Using Deep Multihead Attention Layers Inside Neural Basis Expansion Networks

Glucose forecasting is a crucial feature in a closed-loop diabetes management system relying on minimally invasive continuous glucose monitoring (CGM) sensors. Forecasting is required to prevent hyperglycaemia or hypoglycaemia due to delayed or incorrect dosage of insulin while using CGM sensors, which suffer from physiological delay due to diffusion kinetics between blood and interstitial fluid. Recent works have demonstrated better performance with deep learning methods in this application. However, deep learning methods suffer from model non-interpretability, time lag, prediction accuracy, large training data requirements, and high-end computational resource requirements. In this paper, we seek to address challenges of accuracy, data requirements, and personalisation problems by proposing and validating a novel network architecture where multihead attention layers followed by a combination of fully connected dense and theta layers embedded deep inside neural basis expansion network layers. This network leads towards possible partially interpretable models with high forecasting accuracy. In comparison to previous works, the proposed network leads to an average root mean squared error (RMSE) of 16.57 $\pm$ 2.56 mg/dl and mean absolute relative difference (MARD) of 6.81 $\pm$ 1.39%, which is better in comparison to previous work, when the network was validated on OhioT1DM database for a prediction horizon (PH) of 30 mins. Better results compared to previous work were also obtained for a PH = 60 mins where mean RMSE was 29.25 $\pm$ 6.02 mg/dl and MARD was 12.15 $\pm$ 3.15%.

Personalized Blood Glucose Forecasting From Limited CGM Data Using Incrementally Retrained LSTM

For people with Type 1 diabetes (T1D), accurate blood glucose (BG) forecasting is crucial for the effective delivery of insulin by Artificial Pancreas (AP) systems. Deep learning frameworks like Long Short-Term-Memory (LSTM) have been widely used to predict BG using continuous glucose monitor (CGM) data. However, these methods usually require large amounts of training data for personalized forecasts. Moreover, individuals with diabetes exhibit diverse glucose variability (GV), resulting in varying forecast accuracy. To address these limitations, we propose a novel deep learning framework: Incrementally Retrained Stacked LSTM (IS-LSTM). This approach gradually adapts to individualsâ data and employs parameter-transfer for efficiency. We compare our method to three benchmarks using two CGM datasets from individuals with T1D: OpenAPS and Replace-BG. On both datasets, our approach significantly reduces root mean square error compared to the state of the art (Stacked LSTM): from 14.55 to 10.23 mg/dL (OpenAPS) and 17.15 to 13.41 mg/dL (Replace-BG) at 30-minute Prediction Horizon (PH). Clarke error grid analysis demonstrates clinical feasibility with at least 98.81% and 97.25% of predictions within the clinically safe zone at 30- and 60-minute PHs. Further, we demonstrate the effectiveness of our method in cold-start scenarios, which helps new CGM users obtain accurate predictions.

Physical Activity Integration in Blood Glucose Level Prediction: Different Levels of Data Fusion

Blood glucose level (BGL) prediction contributes to more effective management of diabetes. Physical activity (PA), which affects BGL, is a crucial factor in diabetes management. Due to the erratic nature of PA's impact on BGL inter- and intra-patients, deploying PA in BGL prediction is challenging. Hence, it is crucial to discover optimal approaches for utilising PA to improve the performance of BGL prediction. This work contributes to this gap by proposing several PA-informed BGL prediction models. Different approaches are developed to extract information from PA data and integrate this information with BGL data at signal, feature, and decision levels. For signal-level fusion, different automatically-recorded PA data are fused with BGL data. Also, three feature engineering approaches are developed for feature-level fusion: subjective assessments of PA, objective assessments of PA, and statistics of PA. Furthermore, in decision-level fusion, ensemble learning is used to combine predictions from models trained with different inputs. Then, a comparative investigation is performed between the developed PA-informed approaches and the no-fusion approach, as well as between themselves. The analyses are performed on the publicly available Ohio dataset with rigorous evaluation. The results show that among the developed approaches, fusing heart rate data at the signal-level and PA intensity categories at the feature-level with BGL data are effective ways of deploying PA in BGL prediction.

Optimizing hypoglycaemia prediction in type 1 diabetes with Ensemble Machine Learning modeling

BACKGROUND

Type 1 diabetes (T1D) is a chronic endocrine disorder characterized by high blood glucose levels, impacting millions of people globally. Its management requires intensive insulin therapy, frequent blood glucose monitoring, and lifestyle adjustments. The accurate prediction of the short-term course of glucose levels in the subcutaneous space in T1D people, as measured by a continuous glucose monitoring (CGM) system, is essential for improving glucose control by avoiding harmful hypoglycaemic and hyperglycaemic glucose swings, facilitating precise insulin management and individualized care and, in turn, minimizing long-term vascular complications.

METHODS

In this study, we propose an ensemble univariate short-term predictive model of the subcutaneous glucose concentration in T1D targeting at improving its error in the hypoglycaemic region. As such, the underlying basis functions are selected to minimize the percentage of erroneous predictions (EP) in the hypoglycaemic region, with EP being evaluated with continuous glucose error grid analysis (CG-EGA). The dataset comprises 29 individuals with T1D, who were monitored for 2 to 4 weeks during the GlucoseML prospective observational clinical study.

RESULTS

Among six different basis models (i.e., linear regression (LR), automatic relevance determination (ARD), support vector regression (SVR), Gaussian process regression (GPR), eXtreme gradient boosting (XGBoost), and long short-term memory (LSTM)), XGBoost and SVR showed a dominant performance in the hypoglycaemic region and were selected as the constituent basis models of the ensemble model. The results indicate that the ensemble model significantly reduces the percentage of EP in the hypoglycaemic region for a 30 min prediction horizon to 19% as compared with its individual basis models (i.e., XGBoost and SVR), whilst its errors over the entire glucose range (hypoglycaemia, euglycaemia, and hyperglycaemia) are similar to those of the basis models.

CONCLUSIONS

The consideration of the performance of the basis functions in the hypoglycaemic region during the construction of the ensemble model contributes to enhancing their joint performance in that specific area. This could lead to more precise insulin management and a reduced risk of short-term hypoglycaemic fluctuations.

Shortcomings in the Evaluation of Blood Glucose Forecasting

OBJECTIVE

Recent years have seen an increase in machine learning (ML)-based blood glucose (BG) forecasting models, with a growing emphasis on potential application to hybrid or closed-loop predictive glucose controllers. However, current approaches focus on evaluating the accuracy of these models using benchmark data generated under the behavior policy, which may differ significantly from the data the model may encounter in a control setting. This study challenges the efficacy of such evaluation approaches, demonstrating that they can fail to accurately capture an ML-based model's true performance in closed-loop control settings.

METHODS

Forecast error measured using current evaluation approaches was compared to the control performance of two forecasters - a ML-based model (LSTM) and a rule-based model (Loop) - in silico when the forecasters were utilized with a model-based controller in a hybrid closed-loop setting.

RESULTS

Under current evaluation standards, LSTM achieves a significantly lower (better) forecast error than Loop with a root mean squared error (RMSE) of vs. at the 30-minute prediction horizon. Yet in a control setting, LSTM led to significantly worse control performance with only 77.14% (IQR 66.57-84.03) time-in-range compared to 86.20% (IQR 78.28-91.21) for Loop.

CONCLUSION

Prevailing evaluation methods can fail to accurately capture the forecaster's performance when utilized in closed-loop settings.

SIGNIFICANCE

Our findings underscore the limitations of current evaluation standards and the need for alternative evaluation metrics and training strategies when developing BG forecasters for closed-loop control systems.

Towards Personalized AI-Based Diabetes Therapy: A Review

Insulin pumps and other smart devices have recently made significant advancements in the treatment of diabetes, a disorder that affects people all over the world. The development of medical AI has been influenced by AI methods designed to help physicians make diagnoses, choose a course of therapy, and predict outcomes. In this article, we thoroughly analyse how AI is being used to enhance and personalize diabetes treatment. The search turned up 77 original research papers, from which we've selected the most crucial information regarding the learning models employed, the data typology, the deployment stage, and the application domains. We identified two key trends, enabled mostly by AI: patient-based therapy personalization and therapeutic algorithm optimization. In the meanwhile, we point out various shortcomings in the existing literature, like a lack of multimodal database analysis or a lack of interpretability. The rapid improvements in AI and the expansion of the amount of data already available offer the possibility to overcome these difficulties shortly and enable a wider deployment of this technology in clinical settings.

Deep learning for blood glucose level prediction: How well do models generalize across different data sets?

Deep learning-based models for predicting blood glucose levels in diabetic patients can facilitate proactive measures to prevent critical events and are essential for closed-loop control therapy systems. However, selecting appropriate models from the literature may not always yield conclusive results, as the choice could be influenced by biases or misleading evaluations stemming from different methodologies, datasets, and preprocessing techniques. This study aims to compare and comprehensively analyze the performance of various deep learning models across diverse datasets to assess their applicability and generalizability across a broader spectrum of scenarios. Commonly used deep learning models for blood glucose level forecasting, such as feed-forward neural network, convolutional neural network, long short-term memory network (LSTM), temporal convolutional neural network, and self-attention network (SAN), are considered in this study. To evaluate the generalization capabilities of each model, four datasets of varying sizes, encompassing samples from different age groups and conditions, are utilized. Performance metrics include Root Mean Square Error (RMSE), Mean Absolute Difference (MAD), and Coefficient of Determination (CoD) for analytical asssessment, Clarke Error Grid (CEG) for clinical assessments, Kolmogorov-Smirnov (KS) test for statistical analysis, and generalization ability evaluations to obtain both coarse and granular insights. The experimental findings indicate that the LSTM model demonstrates superior performance with the lowest root mean square error and highest generalization capability among all other models, closely followed by SAN. The ability of LSTM and SAN to capture long-term dependencies in blood glucose data and their correlations with various influencing factors and events contribute to their enhanced performance. Despite the lower predictive performance, the FFN was able to capture patterns and trends in the data, suggesting its applicability in forecasting future direction. Moreover, this study helps in identifying the optimal model based on specific objectives, whether prioritizing generalization or accuracy.

Data-driven blood glucose level prediction in type 1 diabetes: a comprehensive comparative analysis

Accurate prediction of blood glucose level (BGL) has proven to be an effective way to help in type 1 diabetes management. The choice of input, along with the fundamental choice of model structure, is an existing challenge in BGL prediction. Investigating the performance of different data-driven time series forecasting approaches with different inputs for BGL prediction is beneficial in advancing BGL prediction performance. Limited work has been made in this regard, which has resulted in different conclusions. This paper performs a comprehensive investigation of different data-driven time series forecasting approaches using different inputs. To do so, BGL prediction is comparatively investigated from two perspectives; the model's approach and the model's input. First, we compare the performance of BGL prediction using different data-driven time series forecasting approaches, including classical time series forecasting, traditional machine learning, and deep neural networks. Secondly, for each prediction approach, univariate input, using BGL data only, is compared to a multivariate input, using data on carbohydrate intake, injected bolus insulin, and physical activity in addition to BGL data. The investigation is performed on two publicly available Ohio datasets. Regression-based and clinical-based metrics along with statistical analyses are performed for evaluation and comparison purposes. The outcomes show that the traditional machine learning model is the fastest model to train and has the best BGL prediction performance especially when using multivariate input. Also, results show that simply adding extra variables does not necessarily improve BGL prediction performance significantly, and data fusion approaches may be required to effectively leverage other variables' information.

Prediction of Survival in Patients With Esophageal Cancer After Immunotherapy Based on Small-Size Follow-Up Data

Esophageal cancer (EC) poses a significant health concern, particularly among the elderly, warranting effective treatment strategies. While immunotherapy holds promise in activating the immune response against tumors, its specific impact and associated reactions in EC patients remain uncertain. Precise prognosis prediction becomes crucial for guiding appropriate interventions. This study, based on data from the First Affiliated Hospital of Xiamen University (January 2017 to May 2021), focuses on 113 EC patients undergoing immunotherapy. The primary objectives are to elucidate the effectiveness of immunotherapy in EC treatment and to introduce a stacking ensemble learning method for predicting the survival of EC patients who have undergone immunotherapy, in the context of small sample sizes, addressing the imperative of supporting clinical decision-making for healthcare professionals. Our method incorporates five sub-learners and one meta-learner. Leveraging optimal features from the training dataset, this approach achieved compelling accuracy (89.13%) and AUC (88.83%) in predicting three-year survival status, surpassing conventional techniques. The model proves efficient in guiding clinical decisions, especially in scenarios with small-size follow-up data.

Blood glucose forecasting from temporal and static information in children with T1D

Background

The overarching goal of blood glucose forecasting is to assist individuals with type 1 diabetes (T1D) in avoiding hyper- or hypoglycemic conditions. While deep learning approaches have shown promising results for blood glucose forecasting in adults with T1D, it is not known if these results generalize to children. Possible reasons are physical activity (PA), which is often unplanned in children, as well as age and development of a child, which both have an effect on the blood glucose level.

Materials and Methods

In this study, we collected time series measurements of glucose levels, carbohydrate intake, insulin-dosing and physical activity from children with T1D for one week in an ethics approved prospective observational study, which included daily physical activities. We investigate the performance of state-of-the-art deep learning methods for adult data-(dilated) recurrent neural networks and a transformer-on our dataset for short-term (30  min) and long-term (2  h) prediction. We propose to integrate static patient characteristics, such as age, gender, BMI, and percentage of basal insulin, to account for the heterogeneity of our study group.

Results

Integrating static patient characteristics (SPC) proves beneficial, especially for short-term prediction. LSTMs and GRUs with SPC perform best for a prediction horizon of 30  min (RMSE of 1.66  mmol/l), a vanilla RNN with SPC performs best across different prediction horizons, while the performance significantly decays for long-term prediction. For prediction during the night, the best method improves to an RMSE of 1.50  mmol/l. Overall, the results for our baselines and RNN models indicate that blood glucose forecasting for children conducting regular physical activity is more challenging than for previously studied adult data.

Conclusion

We find that integrating static data improves the performance of deep-learning architectures for blood glucose forecasting of children with T1D and achieves promising results for short-term prediction. Despite these improvements, additional clinical studies are warranted to extend forecasting to longer-term prediction horizons.

An enhanced diabetes prediction amidst COVID-19 using ensemble models

In the contemporary landscape of healthcare, the early and accurate prediction of diabetes has garnered paramount importance, especially in the wake of the COVID-19 pandemic where individuals with diabetes exhibit increased vulnerability. This research embarked on a mission to enhance diabetes prediction by employing state-of-the-art machine learning techniques. Initial evaluations highlighted the Support Vector Machines (SVM) classifier as a promising candidate with an accuracy of 76.62%. To further optimize predictions, the study delved into advanced feature engineering techniques, generating interaction and polynomial features that unearthed hidden patterns in the data. Subsequent correlation analyses, visualized through heatmaps, revealed significant correlations, especially with attributes like Glucose. By integrating the strengths of Decision Trees, Gradient Boosting, and SVM in an ensemble model, we achieved an accuracy of 93.2%, showcasing the potential of harmonizing diverse algorithms. This research offers a robust blueprint for diabetes prediction, holding profound implications for early diagnosis, personalized treatments, and preventive care in the context of global health challenges and with the goal of increasing life expectancy.

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.

A Probabilistic Approach to Blood Glucose Prediction in Type 1 Diabetes Under Meal Uncertainties

Currently, most reliable and commercialized artificial pancreas systems for type 1 diabetes are hybrid closed-loop systems, which require the user to announce every meal and its size. However, estimating the amount of carbohydrates in a meal and announcing each and every meal is an error-prone process that introduces important uncertainties to the problem, which when not considered, lead to sub-optimal outcomes of the controller. To address this problem, we propose a novel deep-learning-based model for probabilistic glucose prediction, called the Input and State Recurrent Kalman Network (ISRKN), which consists in the incorporation of an input and state Kalman filter in the latent space of a deep neural network so that the posterior distributions can be computed in closed form and the uncertainty can be propagated using the Kalman equations. In addition, the proposed architecture allows explicit estimation of the meal uncertainty distribution, whose parameters are encoded in the filter parameters. Results using the UVA/Padova simulator and data from a clinical trial show that the proposed model outperforms other probabilistic models using several probabilistic metrics across different degrees of distributional shifts.

Predicting three-month fasting blood glucose and glycated hemoglobin changes in patients with type 2 diabetes mellitus based on multiple machine learning algorithms

Fasting blood glucose (FBG) and glycosylated hemoglobin (HbA1c) are key indicators reflecting blood glucose control in type 2 diabetes mellitus (T2DM) patients. The purpose of this study is to establish a predictive model for blood glucose changes in T2DM patients after 3 months of treatment, achieving personalized treatment.A retrospective study was conducted on type 2 diabetes mellitus real-world medical data from 4 cities in Sichuan Province, China from January 2015 to December 2020. After data preprocessing, data inputting, data sampling, and feature screening, 16 kinds of machine learning methods were used to construct prediction models, and 5 prediction models with the best prediction performance were screened respectively. A total of 100,000 cases were included to establish the FBG model, and 2,169 cases were established to establish the HbA1c model. The best prediction model both of FBG and HbA1c finally obtained are realized by ensemble learning and modified random forest inputting, the AUC values are 0.819 and 0.970, respectively. The most important indicators of the FBG and HbA1c prediction model were FBG and HbA1c. Medication compliance, follow-up outcome, dietary habits, BMI, and waist circumference also had a greater impact on FBG levels. The prediction accuracy of the models of the two blood glucose control indicators is high and has certain clinical applicability.HbA1c and FBG are mutually important predictors, and there is a close relationship between them.

Heterogeneous temporal representation for diabetic blood glucose prediction

Background and aims: Blood glucose prediction (BGP) has increasingly been adopted for personalized monitoring of blood glucose levels in diabetic patients, providing valuable support for physicians in diagnosis and treatment planning. Despite the remarkable success achieved, applying BGP in multi-patient scenarios remains problematic, largely due to the inherent heterogeneity and uncertain nature of continuous glucose monitoring (CGM) data obtained from diverse patient profiles. Methodology: This study proposes the first graph-based Heterogeneous Temporal Representation (HETER) network for multi-patient Blood Glucose Prediction (BGP). Specifically, HETER employs a flexible subsequence repetition method (SSR) to align the heterogeneous input samples, in contrast to the traditional padding or truncation methods. Then, the relationships between multiple samples are constructed as a graph and learned by HETER to capture global temporal characteristics. Moreover, to address the limitations of conventional graph neural networks in capturing local temporal dependencies and providing linear representations, HETER incorporates both a temporally-enhanced mechanism and a linear residual fusion into its architecture. Results: Comprehensive experiments were conducted to validate the proposed method using real-world data from 112 patients in two hospitals, comparing it with five well-known baseline methods. The experimental results verify the robustness and accuracy of the proposed HETER, which achieves the maximal improvement of 31.42%, 27.18%, and 34.85% in terms of MAE, MAPE, and RMSE, respectively, over the second-best comparable method. Discussions: HETER integrates global and local temporal information from multi-patient samples to alleviate the impact of heterogeneity and uncertainty. This method can also be extended to other clinical tasks, thereby facilitating efficient and accurate capture of crucial pattern information in structured medical data.

Blood Glucose Level Time Series Forecasting: Nested Deep Ensemble Learning Lag Fusion

Blood glucose level prediction is a critical aspect of diabetes management. It enables individuals to make informed decisions about their insulin dosing, diet, and physical activity. This, in turn, improves their quality of life and reduces the risk of chronic and acute complications. One conundrum in developing time-series forecasting models for blood glucose level prediction is to determine an appropriate length for look-back windows. On the one hand, studying short histories foists the risk of information incompletion. On the other hand, analysing long histories might induce information redundancy due to the data shift phenomenon. Additionally, optimal lag lengths are inconsistent across individuals because of the domain shift occurrence. Therefore, in bespoke analysis, either optimal lag values should be found for each individual separately or a globally suboptimal lag value should be used for all. The former approach degenerates the analysis's congruency and imposes extra perplexity. With the latter, the fine-tunned lag is not necessarily the optimum option for all individuals. To cope with this challenge, this work suggests an interconnected lag fusion framework based on nested meta-learning analysis that improves the accuracy and precision of predictions for personalised blood glucose level forecasting. The proposed framework is leveraged to generate blood glucose prediction models for patients with type 1 diabetes by scrutinising two well-established publicly available Ohio type 1 diabetes datasets. The models developed undergo vigorous evaluation and statistical analysis from mathematical and clinical perspectives. The results achieved underpin the efficacy of the proposed method in blood glucose level time-series prediction analysis.

Glucose Transformer: Forecasting Glucose Level and Events of Hyperglycemia and Hypoglycemia

To avoid the adverse consequences from abrupt increases in blood glucose, diabetic inpatients should be closely monitored. Using blood glucose data from type 2 diabetes patients, we propose a deep learning model-based framework to forecast blood glucose levels. We used continuous glucose monitoring (CGM) data collected from inpatients with type 2 diabetes for a week. We adopted the Transformer model, commonly used in sequence data, to forecast the blood glucose level over time and detect hyperglycemia and hypoglycemia in advance. We expected the attention mechanism in Transformer to reveal a hint of hyperglycemia and hypoglycemia, and performed a comparative study to determine whether Transformer was effective in the classification and regression of glucose. Hyperglycemia and hypoglycemia rarely occur and this results in an imbalance in the classification. We built a data augmentation model using the generative adversarial network. Our contributions are as follows. First, we developed a deep learning framework utilizing the encoder part of Transformer to perform the regression and classification under a unified framework. Second, we adopted a data augmentation model using the generative adversarial network suitable for time-series data to solve the data imbalance problem and to improve performance. Third, we collected data for type 2 diabetic inpatients for mid-time. Finally, we incorporated transfer learning to improve the performance of regression and classification.

Causality analysis in type 1 diabetes mellitus with application to blood glucose level prediction

Effective control of blood glucose level (BGL) is the key factor in the management of type 1 diabetes mellitus (T1D). BGL prediction is an important tool to help maximise the time BGL is in the target range and thus minimise both acute and chronic diabetes-related complications. To predict future BGL, histories of variables known to affect BGL, such as carbohydrate intake, injected bolus insulin, and physical activity, are utilised. Due to these identified cause and effect relationships, T1D management can be examined via the causality context. In this respect, this work initially investigates these relations and quantifies the causality strengths of each variable with BGL using the convergent cross mapping method (CCM). Then, considering the extended CCM, the causality strengths of each variable for different lags are quantified. After that, the optimal time lag for each variable is determined according to the quantified causality effects. Subsequently, the feasibility of leveraging causality information as prior knowledge for BGL prediction is investigated by proposing two approaches. In the first approach, causality strengths are used as weights for relevant affecting variables. In the second approach, the optimal causal lags and the corresponding causality strengths are considered the shifts and weights for the variables, respectively. Overall, the evaluation criteria and statistical analysis used for comparing results show the effectiveness of using causality analysis in T1D management.

Automatic inference of hypoglycemia causes in type 1 diabetes: a feasibility study

Background

Hypoglycemia is the most common adverse consequence of treating diabetes, and is often due to suboptimal patient self-care. Behavioral interventions by health professionals and self-care education helps avoid recurrent hypoglycemic episodes by targeting problematic patient behaviors. This relies on time-consuming investigation of reasons behind the observed episodes, which involves manual interpretation of personal diabetes diaries and communication with patients. Therefore, there is a clear motivation to automate this process using a supervised machine learning paradigm. This manuscript presents a feasibility study of automatic identification of hypoglycemia causes.

Methods

Reasons for 1885 hypoglycemia events were labeled by 54 participants with type 1 diabetes over a 21 months period. A broad range of possible predictors were extracted describing a hypoglycemic episode and the subject's general self-care from participants' routinely collected data on the Glucollector, their diabetes management platform. Thereafter, the possible hypoglycemia reasons were categorized for two major analysis sections - statistical analysis of relationships between the data features of self-care and hypoglycemia reasons, and classification analysis investigating the design of an automated system to determine the reason for hypoglycemia.

Results

Physical activity contributed to 45% of hypoglycemia reasons on the real world collected data. The statistical analysis provided a number of interpretable predictors of different hypoglycemia reasons based on self-care behaviors. The classification analysis showed the performance of a reasoning system in practical settings with different objectives under F1-score, recall and precision metrics.

Conclusion

The data acquisition characterized the incidence distribution of the various hypoglycemia reasons. The analyses highlighted many interpretable predictors of the various hypoglycemia types. Also, the feasibility study presented a number of concerns valuable in the design of the decision support system for automatic hypoglycemia reason classification. Therefore, automating the identification of the causes of hypoglycemia may help objectively to target behavioral and therapeutic changes in patients' care.

Recent applications of machine learning and deep learning models in the prediction, diagnosis, and management of diabetes: a comprehensive review

Diabetes as a metabolic illness can be characterized by increased amounts of blood glucose. This abnormal increase can lead to critical detriment to the other organs such as the kidneys, eyes, heart, nerves, and blood vessels. Therefore, its prediction, prognosis, and management are essential to prevent harmful effects and also recommend more useful treatments. For these goals, machine learning algorithms have found considerable attention and have been developed successfully. This review surveys the recently proposed machine learning (ML) and deep learning (DL) models for the objectives mentioned earlier. The reported results disclose that the ML and DL algorithms are promising approaches for controlling blood glucose and diabetes. However, they should be improved and employed in large datasets to affirm their applicability.