Clinically Accurate Prediction of Glucose Levels in Patients with Type 1 Diabetes

Fear of Hypoglycemia and Diabetes Distress: Expected Reduction by Glucose Prediction

BACKGROUND

Extended glucose predictions are novel in diabetes management. Currently, there is no solution widely available. People with diabetes mellitus (DM) are offered features like trend arrows and limited predictions linked to predefined situations. Thus, the impact of extended glucose predictions on the burden of diabetes and person-reported outcomes (PROs) is unclear.

METHODS

In this online survey, 206 people with type 1 and type 2 diabetes (T1D and T2D), 70.9% and 29.1%, respectively, who participated in the dia·link online panel and were current continuous glucose monitoring (CGM) users, were presented with different scenarios of hypothetical extended glucose predictions. They were asked to imagine how low glucose predictions of 30 minutes and overnight as well as glucose predictions up to 2 hours would influence their diabetes management. Subsequently, they completed the Hypoglycemia Fear Survey II (HFS-II) and the T1 Diabetes Distress Scale (T1-DDS) by rating each item on a 5-point scale (-2: strong deterioration to +2: strong improvement) according to the potential change due to using glucose predictions.

RESULTS

For all glucose prediction periods, 30 minutes, up to 2 hours, and at nighttime, the surveyed participants expected moderate improvements in both fear of hypoglycemia (HFS-II: 0.57 ± 0.49) and overall diabetes distress (T1-DDS = 0.44 ± 0.49). The T1-DDS did not differ for type of therapy or diabetes.

CONCLUSIONS

People with T1D and T2D would see glucose predictions as a potential improvement regarding reduced fear of hypoglycemia and diabetes distress. Therefore, glucose predictions represent a value for them in lowering the burden of diabetes and its management.

Blood Glucose Prediction from Nutrition Analytics in Type 1 Diabetes: A Review

INTRODUCTION

Type 1 Diabetes (T1D) affects over 9 million worldwide and necessitates meticulous self-management for blood glucose (BG) control. Utilizing BG prediction technology allows for increased BG control and a reduction in the diabetes burden caused by self-management requirements. This paper reviews BG prediction models in T1D, which include nutritional components.

METHOD

A systematic search, utilizing the PRISMA guidelines, identified articles focusing on BG prediction algorithms for T1D that incorporate nutritional variables. Eligible studies were screened and analyzed for model type, inclusion of additional aspects in the model, prediction horizon, patient population, inputs, and accuracy.

RESULTS

The study categorizes 138 blood glucose prediction models into data-driven (54%), physiological (14%), and hybrid (33%) types. Prediction horizons of ≤30 min are used in 36% of models, 31-60 min in 34%, 61-90 min in 11%, 91-120 min in 10%, and >120 min in 9%. Neural networks are the most used data-driven technique (47%), and simple carbohydrate intake is commonly included in models (data-driven: 72%, physiological: 52%, hybrid: 67%). Real or free-living data are predominantly used (83%).

CONCLUSION

The primary goal of blood glucose prediction in T1D is to enable informed decisions and maintain safe BG levels, considering the impact of all nutrients for meal planning and clinical relevance.

The Reporting Quality of Machine Learning Studies on Pediatric Diabetes Mellitus: Systematic Review

BACKGROUND

Diabetes mellitus (DM) is a major health concern among children with the widespread adoption of advanced technologies. However, concerns are growing about the transparency, replicability, biasedness, and overall validity of artificial intelligence studies in medicine.

OBJECTIVE

We aimed to systematically review the reporting quality of machine learning (ML) studies of pediatric DM using the Minimum Information About Clinical Artificial Intelligence Modelling (MI-CLAIM) checklist, a general reporting guideline for medical artificial intelligence studies.

METHODS

We searched the PubMed and Web of Science databases from 2016 to 2020. Studies were included if the use of ML was reported in children with DM aged 2 to 18 years, including studies on complications, screening studies, and in silico samples. In studies following the ML workflow of training, validation, and testing of results, reporting quality was assessed via MI-CLAIM by consensus judgments of independent reviewer pairs. Positive answers to the 17 binary items regarding sufficient reporting were qualitatively summarized and counted as a proxy measure of reporting quality. The synthesis of results included testing the association of reporting quality with publication and data type, participants (human or in silico), research goals, level of code sharing, and the scientific field of publication (medical or engineering), as well as with expert judgments of clinical impact and reproducibility.

RESULTS

After screening 1043 records, 28 studies were included. The sample size of the training cohort ranged from 5 to 561. Six studies featured only in silico patients. The reporting quality was low, with great variation among the 21 studies assessed using MI-CLAIM. The number of items with sufficient reporting ranged from 4 to 12 (mean 7.43, SD 2.62). The items on research questions and data characterization were reported adequately most often, whereas items on patient characteristics and model examination were reported adequately least often. The representativeness of the training and test cohorts to real-world settings and the adequacy of model performance evaluation were the most difficult to judge. Reporting quality improved over time (r=0.50; P=.02); it was higher than average in prognostic biomarker and risk factor studies (P=.04) and lower in noninvasive hypoglycemia detection studies (P=.006), higher in studies published in medical versus engineering journals (P=.004), and higher in studies sharing any code of the ML pipeline versus not sharing (P=.003). The association between expert judgments and MI-CLAIM ratings was not significant.

CONCLUSIONS

The reporting quality of ML studies in the pediatric population with DM was generally low. Important details for clinicians, such as patient characteristics; comparison with the state-of-the-art solution; and model examination for valid, unbiased, and robust results, were often the weak points of reporting. To assess their clinical utility, the reporting standards of ML studies must evolve, and algorithms for this challenging population must become more transparent and replicable.

Machine Learning Models for Blood Glucose Level Prediction in Patients With Diabetes Mellitus: Systematic Review and Network Meta-Analysis

BACKGROUND

Machine learning (ML) models provide more choices to patients with diabetes mellitus (DM) to more properly manage blood glucose (BG) levels. However, because of numerous types of ML algorithms, choosing an appropriate model is vitally important.

OBJECTIVE

In a systematic review and network meta-analysis, this study aimed to comprehensively assess the performance of ML models in predicting BG levels. In addition, we assessed ML models used to detect and predict adverse BG (hypoglycemia) events by calculating pooled estimates of sensitivity and specificity.

METHODS

PubMed, Embase, Web of Science, and Institute of Electrical and Electronics Engineers Explore databases were systematically searched for studies on predicting BG levels and predicting or detecting adverse BG events using ML models, from inception to November 2022. Studies that assessed the performance of different ML models in predicting or detecting BG levels or adverse BG events of patients with DM were included. Studies with no derivation or performance metrics of ML models were excluded. The Quality Assessment of Diagnostic Accuracy Studies tool was applied to assess the quality of included studies. Primary outcomes were the relative ranking of ML models for predicting BG levels in different prediction horizons (PHs) and pooled estimates of the sensitivity and specificity of ML models in detecting or predicting adverse BG events.

RESULTS

In total, 46 eligible studies were included for meta-analysis. Regarding ML models for predicting BG levels, the means of the absolute root mean square error (RMSE) in a PH of 15, 30, 45, and 60 minutes were 18.88 (SD 19.71), 21.40 (SD 12.56), 21.27 (SD 5.17), and 30.01 (SD 7.23) mg/dL, respectively. The neural network model (NNM) showed the highest relative performance in different PHs. Furthermore, the pooled estimates of the positive likelihood ratio and the negative likelihood ratio of ML models were 8.3 (95% CI 5.7-12.0) and 0.31 (95% CI 0.22-0.44), respectively, for predicting hypoglycemia and 2.4 (95% CI 1.6-3.7) and 0.37 (95% CI 0.29-0.46), respectively, for detecting hypoglycemia.

CONCLUSIONS

Statistically significant high heterogeneity was detected in all subgroups, with different sources of heterogeneity. For predicting precise BG levels, the RMSE increases with a rise in the PH, and the NNM shows the highest relative performance among all the ML models. Meanwhile, current ML models have sufficient ability to predict adverse BG events, while their ability to detect adverse BG events needs to be enhanced.

TRIAL REGISTRATION

PROSPERO CRD42022375250; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=375250.

Modeling risk of hypoglycemia during and following physical activity in people with type 1 diabetes using explainable mixed-effects machine learning

BACKGROUND

Physical activity (PA) can cause increased hypoglycemia (glucose <70 mg/dL) risk in people with type 1 diabetes (T1D). We modeled the probability of hypoglycemia during and up to 24 h following PA and identified key factors associated with hypoglycemia risk.

METHODS

We leveraged a free-living dataset from Tidepool comprised of glucose measurements, insulin doses, and PA data from 50 individuals with T1D (6448 sessions) for training and validating machine learning models. We also used data from the T1Dexi pilot study that contains glucose management and PA data from 20 individuals with T1D (139 session) for assessing the accuracy of the best performing model on an independent test dataset. We used mixed-effects logistic regression (MELR) and mixed-effects random forest (MERF) to model hypoglycemia risk around PA. We identified risk factors associated with hypoglycemia using odds ratio and partial dependence analysis for the MELR and MERF models, respectively. Prediction accuracy was measured using the area under the receiver operating characteristic curve (AUROC).

RESULTS

The analysis identified risk factors significantly associated with hypoglycemia during and following PA in both MELR and MERF models including glucose and body exposure to insulin at the start of PA, low blood glucose index 24 h prior to PA, and PA intensity and timing. Both models showed overall hypoglycemia risk peaking 1 h after PA and again 5-10 h after PA, which is consistent with the hypoglycemia risk pattern observed in the training dataset. Time following PA impacted hypoglycemia risk differently across different PA types. Accuracy of hypoglycemia prediction using the fixed effects of the MERF model was highest when predicting hypoglycemia during the first hour following the start of PA (AUROCVALIDATION = 0.83 and AUROCTESTING = 0.86) and decreased when predicting hypoglycemia in the 24 h after PA (AUROCVALIDATION = 0.66 and AUROCTESTING = 0.68).

CONCLUSION

Hypoglycemia risk after the start of PA can be modeled using mixed-effects machine learning to identify key risk factors that may be used within decision support and insulin delivery systems. We published the population-level MERF model online for others to use.

A Conditional Generative Adversarial Network for Synthesis of Continuous Glucose Monitoring Signals

This report describes how a Conditional Generative Adversarial Network (CGAN) was used to synthesize realistic continuous glucose monitoring systems (CGM) from healthy individuals and individuals with type 1 diabetes over a range of different HbA1c levels. The results showed that even though the CGAN generated data, did not perfectly reflect real world CGM, many of the important features were captured and reflected in the synthetic signals. It is briefly discussed how heterogenous data sources constitutes a challenge for comparison of predictive CGM models. Therefore 40,000 CGM days were generated by the trained CGAN, equivalent to 940,000 hours of synthetic CGM measurements. These data have been made available in a public database, which can be used as a reference in future studies.

Incorporating Glucose Variability into Glucose Forecasting Accuracy Assessment Using the New Glucose Variability Impact Index and the Prediction Consistency Index: An LSTM Case Example

BACKGROUND

In this work, we developed glucose forecasting algorithms trained and evaluated on a large dataset of free-living people with type 1 diabetes (T1D) using closed-loop (CL) and sensor-augmented pump (SAP) therapies; and we demonstrate how glucose variability impacts accuracy. We introduce the glucose variability impact index (GVII) and the glucose prediction consistency index (GPCI) to assess the accuracy of prediction algorithms.

METHODS

A long-short-term-memory (LSTM) neural network was designed to predict glucose up to 60 minutes in the future using continuous glucose measurements and insulin data collected from 175 people with T1D (41,318 days) and evaluated on 75 people (11,333 days) from the Tidepool Big Data Donation Dataset. LSTM was compared with two naïve forecasting algorithms as well as Ridge linear regression and a random forest using root-mean-square error (RMSE). Parkes error grid quantified clinical accuracy. Regression analysis was used to derive the GVII and GPCI.

RESULTS

The LSTM had highest accuracy and best GVII and GPCI. RMSE for CL was 19.8 ± 3.2 and 33.2 ± 5.4 mg/dL for 30- and 60-minute prediction horizons, respectively. RMSE for SAP was 19.6 ± 3.8 and 33.1 ± 7.3 mg/dL for 30- and 60-minute prediction horizons, respectively; 99.6% and 97.6% of predictions were within zones A+B of the Parkes error grid at 30- and 60-minute prediction horizons, respectively. Glucose variability was strongly correlated with RMSE (R≥0.64, P < 0.001); GVII and GPCI demonstrated a means to compare algorithms across datasets with different glucose variability.

CONCLUSIONS

The LSTM model was accurate on a large real-world free-living dataset. Glucose variability should be considered when assessing prediction accuracy using indices such as GVII and GPCI.

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.

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

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

Machine Learning Techniques for Hypoglycemia Prediction: Trends and Challenges

(1) Background: the use of machine learning techniques for the purpose of anticipating hypoglycemia has increased considerably in the past few years. Hypoglycemia is the drop in blood glucose below critical levels in diabetic patients. This may cause loss of cognitive ability, seizures, and in extreme cases, death. In almost half of all the severe cases, hypoglycemia arrives unannounced and is essentially asymptomatic. The inability of a diabetic patient to anticipate and intervene the occurrence of a hypoglycemic event often results in crisis. Hence, the prediction of hypoglycemia is a vital step in improving the life quality of a diabetic patient. The objective of this paper is to review work performed in the domain of hypoglycemia prediction by using machine learning and also to explore the latest trends and challenges that the researchers face in this area; (2) Methods: literature obtained from PubMed and Google Scholar was reviewed. Manuscripts from the last five years were searched for this purpose. A total of 903 papers were initially selected of which 57 papers were eventually shortlisted for detailed review; (3) Results: a thorough dissection of the shortlisted manuscripts provided an interesting split between the works based on two categories: hypoglycemia prediction and hypoglycemia detection. The entire review was carried out keeping this categorical distinction in perspective while providing a thorough overview of the machine learning approaches used to anticipate hypoglycemia, the type of training data, and the prediction horizon.

Multi-Hour Blood Glucose Prediction in Type 1 Diabetes: A Patient-Specific Approach Using Shallow Neural Network Models

Background: Considering current insulin action profiles and the nature of glycemic responses to insulin, there is an acute need for longer term, accurate, blood glucose predictions to inform insulin dosing schedules and enable effective decision support for the treatment of type 1 diabetes (T1D). However, current methods achieve acceptable accuracy only for prediction horizons of up to 1 h, whereas typical postprandial excursions and insulin action profiles last 4-6 h. In this study, we present models for prediction horizons of 60-240 min developed by leveraging "shallow" neural networks, allowing for significantly lower complexity compared with related approaches. Methods: Patient-specific neural network-based predictive models are developed and tested on previously collected data from a cohort of 24 subjects with T1D. Models are designed to avoid serious pitfalls through incorporating essential physiological knowledge into model structure. Patient-specific models were generated to predict glucose 60, 90, 120, 180, and 240 min ahead, and a "transfer learning" approach to improve accuracy for patients where data are limited. Finally, we determined subgroup characteristics that result in higher model accuracy overall. Results: Root mean squared error was 28 ± 4, 33 ± 4, 38 ± 6, 40 ± 8, and 43 ± 12 mg/dL for 60, 90, 120, 180, and 240 min, respectively. For all prediction horizons, at least 93% of predictions were clinically acceptable by the Clarke error grid. Variance of historic continuous glucose monitor (CGM) values was a strong predictor for the need of transfer learning approaches. Conclusions: A shallow neural network, using features extracted from past CGM data and insulin logs, can achieve multi-hour glucose predictions with satisfactory accuracy. Models are patient specific, learnt on readily available data without the need for additional tests, and improve accuracy while lowering complexity compared with related approaches, paving the way for new advisory and closed loop algorithms able to encompass most of the insulin action timeframe.

Artificial Neural Networks Model for Predicting Type 2 Diabetes Mellitus Based on VDR Gene FokI Polymorphism, Lipid Profile and Demographic Data

Type 2 diabetes mellitus (T2DM) is a multifactorial disease associated with many genetic polymorphisms; among them is the FokI polymorphism in the vitamin D receptor (VDR) gene. In this case-control study, samples from 82 T2DM patients and 82 healthy controls were examined to investigate the association of the FokI polymorphism and lipid profile with T2DM in the Jordanian population. DNA was extracted from blood and genotyped for the FokI polymorphism by polymerase chain reaction (PCR) and DNA sequencing. Lipid profile and fasting blood sugar were also measured. There were significant differences in high-density lipoprotein (HDL) cholesterol and triglyceride levels between T2DM and control samples. Frequencies of the FokI polymorphism (CC, CT and TT) were determined in T2DM and control samples and were not significantly different. Furthermore, there was no significant association between the FokI polymorphism and T2DM or lipid profile. A feed-forward neural network (FNN) was used as a computational platform to predict the persons with diabetes based on the FokI polymorphism, lipid profile, gender and age. The accuracy of prediction reached 88% when all parameters were included, 81% when the FokI polymorphism was excluded, and 72% when lipids were only included. This is the first study investigating the association of the VDR gene FokI polymorphism with T2DM in the Jordanian population, and it showed negative association. Diabetes was predicted with high accuracy based on medical data using an FNN. This highlights the great value of incorporating neural network tools into large medical databases and the ability to predict patient susceptibility to diabetes.

Deep Physiological Model for Blood Glucose Prediction in T1DM Patients

Accurate estimations for the near future levels of blood glucose are crucial for Type 1 Diabetes Mellitus (T1DM) patients in order to be able to react on time and avoid hypo and hyper-glycemic episodes. Accurate predictions for blood glucose are the base for control algorithms in glucose regulating systems such as the artificial pancreas. Numerous research studies have already been conducted in order to provide predictions for blood glucose levels with particularities in the input signals and underlying models used. These models can be categorized into two major families: those based on tuning glucose physiological-metabolic models and those based on learning glucose evolution patterns based on machine learning techniques. This paper reviews the state of the art in blood glucose predictions for T1DM patients and proposes, implements, validates and compares a new hybrid model that decomposes a deep machine learning model in order to mimic the metabolic behavior of physiological blood glucose methods. The differential equations for carbohydrate and insulin absorption in physiological models are modeled using a Recurrent Neural Network (RNN) implemented using Long Short-Term Memory (LSTM) cells. The results show Root Mean Square Error (RMSE) values under 5 mg/dL for simulated patients and under 10 mg/dL for real patients.