Hypoglycemia prediction using machine learning models for patients with type 2 diabetes

Digital Health and Machine Learning Technologies for Blood Glucose Monitoring and Management of Gestational Diabetes

Innovations in digital health and machine learning are changing the path of clinical health and care. People from different geographical locations and cultural backgrounds can benefit from the mobility of wearable devices and smartphones to monitor their health ubiquitously. This paper focuses on reviewing the digital health and machine learning technologies used in gestational diabetes - a subtype of diabetes that occurs during pregnancy. This paper reviews sensor technologies used in blood glucose monitoring devices, digital health innovations and machine learning models for gestational diabetes monitoring and management, in clinical and commercial settings, and discusses future directions. Despite one in six mothers having gestational diabetes, digital health applications were underdeveloped, especially the techniques that can be deployed in clinical practice. There is an urgent need to (1) develop clinically interpretable machine learning methods for patients with gestational diabetes, assisting health professionals with treatment, monitoring, and risk stratification before, during and after their pregnancies; (2) adapt and develop clinically-proven devices for patient self-management of health and well-being at home settings ("virtual ward" and virtual consultation), thereby improving clinical outcomes by facilitating timely intervention; and (3) ensure innovations are affordable and sustainable for all women with different socioeconomic backgrounds and clinical resources.

Exploring the progress of artificial intelligence in managing type 2 diabetes mellitus: a comprehensive review of present innovations and anticipated challenges ahead

A significant worldwide health issue, Type 2 Diabetes Mellitus (T2DM) calls for creative solutions. This in-depth review examines the growing severity of T2DM and the requirement for individualized management approaches. It explores the use of artificial intelligence (AI) in the treatment of diabetes, highlighting its potential for diagnosis, customized treatment plans, and patient self-management. The paper highlights the roles played by AI applications such as expert systems, machine learning algorithms, and deep learning approaches in the identification of retinopathy, the interpretation of clinical guidelines, and prediction models. Examined are difficulties with individualized diabetes treatment, including complex technological issues and patient involvement. The review highlights the revolutionary potential of AI in the management of diabetes and calls for a balanced strategy in which AI supports clinical knowledge. It is crucial to pay attention to ethical issues, data privacy, and joint research initiatives.

Prediction of Hypoglycemia From Continuous Glucose Monitoring in Insulin-Treated Patients With Type 2 Diabetes Using Transfer Learning on Type 1 Diabetes Data: A Deep Transfer Learning Approach

BACKGROUND

Hypoglycemia is common in insulin-treated type 2 diabetes (T2D) patients, which can lead to decreased quality of life or premature death. Deep learning models offer promise of accurate predictions, but data scarcity poses a challenge. This study aims to develop a deep learning model utilizing transfer learning to predict hypoglycemia.

METHODS

Continuous glucose monitoring (CGM) data from 226 patients with type 1 diabetes (T1D) and 180 patients with T2D were utilized. Data were structured into one-hour samples and labeled as hypoglycemia or not depending on whether three consecutive CGM values were below 3.9 [mmol/L] (70 mg/dL) one hour after the sample. A convolutional neural network (CNN) was pre-trained with the T1D data set and subsequently fitted using a T2D data set, all while being optimized toward maximizing the area under the receiver operating characteristics curve (AUC) value, and it was externally validated on a separate T2D data set.

RESULTS

The developed model was externally validated with 334 711 one-hour CGM samples, of which 15 695 (4.69%) were labeled as hypoglycemic. The model achieved an AUC of 0.941 and a positive predictive value of 40.49% at a specificity of 95% and a sensitivity of 69.16%.

CONCLUSIONS

The transfer learned CNN model showed promising performance in predicting hypoglycemic episodes and with slightly better results than a non-transfer learned CNN model.

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.

Artificial intelligence in diabetes management: Advancements, opportunities, and challenges

The increasing prevalence of diabetes, high avoidable morbidity and mortality due to diabetes and diabetic complications, and related substantial economic burden make diabetes a significant health challenge worldwide. A shortage of diabetes specialists, uneven distribution of medical resources, low adherence to medications, and improper self-management contribute to poor glycemic control in patients with diabetes. Recent advancements in digital health technologies, especially artificial intelligence (AI), provide a significant opportunity to achieve better efficiency in diabetes care, which may diminish the increase in diabetes-related health-care expenditures. Here, we review the recent progress in the application of AI in the management of diabetes and then discuss the opportunities and challenges of AI application in clinical practice. Furthermore, we explore the possibility of combining and expanding upon existing digital health technologies to develop an AI-assisted digital health-care ecosystem that includes the prevention and management of diabetes.

Effect of Artificial Intelligence-based Health Education Accurately Linking System (AI-HEALS) for Type 2 diabetes self-management: protocol for a mixed-methods study

BACKGROUND

Patients with type 2 diabetes (T2DM) have an increasing need for personalized and Precise management as medical technology advances. Artificial intelligence (AI) technologies on mobile devices are being developed gradually in a variety of healthcare fields. As an AI field, knowledge graph (KG) is being developed to extract and store structured knowledge from massive data sets. It has great prospects for T2DM medical information retrieval, clinical decision-making, and individual intelligent question and answering (QA), but has yet to be thoroughly researched in T2DM intervention. Therefore, we designed an artificial intelligence-based health education accurately linking system (AI-HEALS) to evaluate if the AI-HEALS-based intervention could help patients with T2DM improve their self-management abilities and blood glucose control in primary healthcare.

METHODS

This is a nested mixed-method study that includes a community-based cluster-randomized control trial and personal in-depth interviews. Individuals with T2DM between the ages of 18 and 75 will be recruited from 40-45 community health centers in Beijing, China. Participants will either receive standard diabetes primary care (SDPC) (control, 3 months) or SDPC plus AI-HEALS online health education program (intervention, 3 months). The AI-HEALS runs in the WeChat service platform, which includes a KBQA, a system of physiological indicators and lifestyle recording and monitoring, medication and blood glucose monitoring reminders, and automated, personalized message sending. Data on sociodemography, medical examination, blood glucose, and self-management behavior will be collected at baseline, as well as 1,3,6,12, and 18 months later. The primary outcome is to reduce HbA1c levels. Secondary outcomes include changes in self-management behavior, social cognition, psychology, T2DM skills, and health literacy. Furthermore, the cost-effectiveness of the AI-HEALS-based intervention will be evaluated.

DISCUSSION

KBQA system is an innovative and cost-effective technology for health education and promotion for T2DM patients, but it is not yet widely used in the T2DM interventions. This trial will provide evidence on the efficacy of AI and mHealth-based personalized interventions in primary care for improving T2DM outcomes and self-management behaviors.

TRIAL REGISTRATION

Biomedical Ethics Committee of Peking University: IRB00001052-22,058, 2022/06/06; Clinical Trials: ChiCTR2300068952, 02/03/2023.

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.

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.

Quantifying the utility of islet autoantibody levels in the prediction of type 1 diabetes in children

AIMS/HYPOTHESIS

The aim of this study was to explore the utility of islet autoantibody (IAb) levels for the prediction of type 1 diabetes in autoantibody-positive children.

METHODS

Prospective cohort studies in Finland, Germany, Sweden and the USA followed 24,662 children at increased genetic or familial risk of developing islet autoimmunity and diabetes. For the 1403 who developed IAbs (523 of whom developed diabetes), levels of autoantibodies against insulin (IAA), glutamic acid decarboxylase (GADA) and insulinoma-associated antigen-2 (IA-2A) were harmonised for analysis. Diabetes prediction models using multivariate logistic regression with inverse probability censored weighting (IPCW) were trained using 10-fold cross-validation. Discriminative power for disease was estimated using the IPCW concordance index (C index) with 95% CI estimated via bootstrap.

RESULTS

A baseline model with covariates for data source, sex, diabetes family history, HLA risk group and age at seroconversion with a 10-year follow-up period yielded a C index of 0.61 (95% CI 0.58, 0.63). The performance improved after adding the IAb positivity status for IAA, GADA and IA-2A at seroconversion: C index 0.72 (95% CI 0.71, 0.74). Using the IAb levels instead of positivity indicators resulted in even better performance: C index 0.76 (95% CI 0.74, 0.77). The predictive power was maintained when using the IAb levels alone: C index 0.76 (95% CI 0.75, 0.76). The prediction was better for shorter follow-up periods, with a C index of 0.82 (95% CI 0.81, 0.83) at 2 years, and remained reasonable for longer follow-up periods, with a C index of 0.76 (95% CI 0.75, 0.76) at 11 years. Inclusion of the results of a third IAb test added to the predictive power, and a suitable interval between seroconversion and the third test was approximately 1.5 years, with a C index of 0.78 (95% CI 0.77, 0.78) at 10 years follow-up.

CONCLUSIONS/INTERPRETATION

Consideration of quantitative patterns of IAb levels improved the predictive power for type 1 diabetes in IAb-positive children beyond qualitative IAb positivity status.

Review: Machine learning in precision pharmacotherapy of type 2 diabetes-A promising future or a glimpse of hope?

Precision pharmacotherapy of diabetes requires judicious selection of the optimal therapeutic agent for individual patients. Artificial intelligence (AI), a swiftly expanding discipline, holds substantial potential to transform current practices in diabetes diagnosis and management. This manuscript provides a comprehensive review of contemporary research investigating drug responses in patient subgroups, stratified via either supervised or unsupervised machine learning approaches. The prevalent algorithmic workflow for investigating drug responses using machine learning involves cohort selection, data processing, predictor selection, development and validation of machine learning methods, subgroup allocation, and subsequent analysis of drug response. Despite the promising feature, current research does not yet provide sufficient evidence to implement machine learning algorithms into routine clinical practice, due to a lack of simplicity, validation, or demonstrated efficacy. Nevertheless, we anticipate that the evolving evidence base will increasingly substantiate the role of machine learning in molding precision pharmacotherapy for diabetes.

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.

Treatment Discontinuation Prediction in Patients With Diabetes Using a Ranking Model: Machine Learning Model Development

BACKGROUND

Treatment discontinuation (TD) is one of the major prognostic issues in diabetes care, and several models have been proposed to predict a missed appointment that may lead to TD in patients with diabetes by using binary classification models for the early detection of TD and for providing intervention support for patients. However, as binary classification models output the probability of a missed appointment occurring within a predetermined period, they are limited in their ability to estimate the magnitude of TD risk in patients with inconsistent intervals between appointments, making it difficult to prioritize patients for whom intervention support should be provided.

OBJECTIVE

This study aimed to develop a machine-learned prediction model that can output a TD risk score defined by the length of time until TD and prioritize patients for intervention according to their TD risk.

METHODS

This model included patients with diagnostic codes indicative of diabetes at the University of Tokyo Hospital between September 3, 2012, and May 17, 2014. The model was internally validated with patients from the same hospital from May 18, 2014, to January 29, 2016. The data used in this study included 7551 patients who visited the hospital after January 1, 2004, and had diagnostic codes indicative of diabetes. In particular, data that were recorded in the electronic medical records between September 3, 2012, and January 29, 2016, were used. The main outcome was the TD of a patient, which was defined as missing a scheduled clinical appointment and having no hospital visits within 3 times the average number of days between the visits of the patient and within 60 days. The TD risk score was calculated by using the parameters derived from the machine-learned ranking model. The prediction capacity was evaluated by using test data with the C-index for the performance of ranking patients, area under the receiver operating characteristic curve, and area under the precision-recall curve for discrimination, in addition to a calibration plot.

RESULTS

The means (95% confidence limits) of the C-index, area under the receiver operating characteristic curve, and area under the precision-recall curve for the TD risk score were 0.749 (0.655, 0.823), 0.758 (0.649, 0.857), and 0.713 (0.554, 0.841), respectively. The observed and predicted probabilities were correlated with the calibration plots.

CONCLUSIONS

A TD risk score was developed for patients with diabetes by combining a machine-learned method with electronic medical records. The score calculation can be integrated into medical records to identify patients at high risk of TD, which would be useful in supporting diabetes care and preventing TD.

Machine learning for diabetes clinical decision support: a review

Type 2 diabetes has recently acquired the status of an epidemic silent killer, though it is non-communicable. There are two main reasons behind this perception of the disease. First, a gradual but exponential growth in the disease prevalence has been witnessed irrespective of age groups, geography or gender. Second, the disease dynamics are very complex in terms of multifactorial risks involved, initial asymptomatic period, different short-term and long-term complications posing serious health threat and related co-morbidities. Majority of its risk factors are lifestyle habits like physical inactivity, lack of exercise, high body mass index (BMI), poor diet, smoking except some inevitable ones like family history of diabetes, ethnic predisposition, ageing etc. Nowadays, machine learning (ML) is increasingly being applied for alleviation of diabetes health burden and many research works have been proposed in the literature to offer clinical decision support in different application areas as well. In this paper, we present a review of such efforts for the prevention and management of type 2 diabetes. Firstly, we present the medical gaps in diabetes knowledge base, guidelines and medical practice identified from relevant articles and highlight those that can be addressed by ML. Further, we review the ML research works in three different application areas namely—(1) risk assessment (statistical risk scores and ML-based risk models), (2) diagnosis (using non-invasive and invasive features), (3) prognosis (from normoglycemia/prior morbidity to incident diabetes and prognosis of incident diabetes to related complications). We discuss and summarize the shortcomings or gaps in the existing ML methodologies for diabetes to be addressed in future. This review provides the breadth of ML predictive modeling applications for diabetes while highlighting the medical and technological gaps as well as various aspects involved in ML-based diabetes clinical decision support.

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.

Using Momentary Assessment and Machine Learning to Identify Barriers to Self-management in Type 1 Diabetes: Observational Study

Background

For adolescents living with type 1 diabetes (T1D), completion of multiple daily self-management tasks, such as monitoring blood glucose and administering insulin, can be challenging because of psychosocial and contextual barriers. These barriers are hard to assess accurately and specifically by using traditional retrospective recall. Ecological momentary assessment (EMA) uses mobile technologies to assess the contexts, subjective experiences, and psychosocial processes that surround self-management decision-making in daily life. However, the rich data generated via EMA have not been frequently examined in T1D or integrated with machine learning analytic approaches.

Objective

The goal of this study is to develop a machine learning algorithm to predict the risk of missed self-management in young adults with T1D. To achieve this goal, we train and compare a number of machine learning models through a learned filtering architecture to explore the extent to which EMA data were associated with the completion of two self-management behaviors: mealtime self-monitoring of blood glucose (SMBG) and insulin administration.

Methods

We analyzed data from a randomized controlled pilot study using machine learning–based filtering architecture to investigate whether novel information related to contextual, psychosocial, and time-related factors (ie, time of day) relate to self-management. We combined EMA-collected contextual and insulin variables via the MyDay mobile app with Bluetooth blood glucose data to construct machine learning classifiers that predicted the 2 self-management behaviors of interest.

Results

With 1231 day-level SMBG frequency counts for 45 participants, demographic variables and time-related variables were able to predict whether daily SMBG was below the clinical threshold of 4 times a day. Using the 1869 data points derived from app-based EMA data of 31 participants, our learned filtering architecture method was able to infer nonadherence events with high accuracy and precision. Although the recall score is low, there is high confidence that the nonadherence events identified by the model are truly nonadherent.

Conclusions

Combining EMA data with machine learning methods showed promise in the relationship with risk for nonadherence. The next steps include collecting larger data sets that would more effectively power a classifier that can be deployed to infer individual behavior. Improvements in individual self-management insights, behavioral risk predictions, enhanced clinical decision-making, and just-in-time patient support in diabetes could result from this type of approach.

Machine Learning and Smart Devices for Diabetes Management: Systematic Review

(1) Background: The use of smart devices to better manage diabetes has increased significantly in recent years. These technologies have been introduced in order to make life easier for patients with diabetes by allowing better control of the stability of blood sugar levels and anticipating the occurrence of dangerous events (hypo/hyperglycemia), etc. That being said, the main objectives of the self-management of diabetes is to improve the lifestyle and life quality of patients with diabetes; (2) Methods: We performed a systematic review based on articles that focus on the use of smart devices for the monitoring and better management of diabetes. The search was focused on keywords related to the topic, such as “Diabetes”, “Technology”, “Self-management”, “Artificial Intelligence”, etc. This was performed using databases, such as Scopus, Google Scholar, and PubMed; (3) Results: A total of 89 studies, published between 2011 and 2021, were included. The majority of the selected research aims to solve a diabetes management problem (e.g., blood glucose prediction, early detection of risk events, and the automatic adjustment of insulin doses, etc.). In these studies, wearable devices were used in combination with artificial intelligence (AI) techniques; (4) Conclusions: Wearable devices have attracted a great deal of scientific interest in the field of healthcare for people with chronic conditions, such as diabetes. They are capable of assisting in the management of diabetes, as well as preventing complications associated with this condition. Furthermore, the usage of these devices has improved illness management and quality of life.

Development and validation of a machine learning model for classification of next glucose measurement in hospitalized patients

BACKGROUND

Inpatient glucose management can be challenging due to evolving factors that influence a patient's blood glucose (BG) throughout hospital admission. The purpose of our study was to predict the category of a patient's next BG measurement based on electronic medical record (EMR) data.

METHODS

EMR data from 184,361 admissions containing 4,538,418 BG measurements from five hospitals in the Johns Hopkins Health System were collected from patients who were discharged between January 1, 2015 and May 31, 2019. Index BGs used for prediction included the 5th to penultimate BG measurements (N = 2,740,539). The outcome was category of next BG measurement: hypoglycemic (BG  ≤  70 mg/dl), controlled (BG 71-180 mg/dl), or hyperglycemic (BG > 180 mg/dl). A random forest algorithm that included a broad range of clinical covariates predicted the outcome and was validated internally and externally.

FINDINGS

In our internal validation test set, 72·8%, 25·7%, and 1·5% of BG measurements occurring after the index BG were controlled, hyperglycemic, and hypoglycemic respectively. The sensitivity/specificity for prediction of controlled, hyperglycemic, and hypoglycemic were 0·77/0·81, 0·77/0·89, and 0·73/0·91, respectively. On external validation in four hospitals, the ranges of sensitivity/specificity for prediction of controlled, hyperglycemic, and hypoglycemic were 0·64-0·70/0·80-0·87, 0·75-0·80/0·82-0·84, and 0·76-0·78/0·87-0·90, respectively.

INTERPRETATION

A machine learning algorithm using EMR data can accurately predict the category of a hospitalized patient's next BG measurement. Further studies should determine the effectiveness of integration of this model into the EMR in reducing rates of hypoglycemia and hyperglycemia.

Using machine learning to predict severe hypoglycaemia in hospital

AIM

To predict the risk of hypoglycaemia using machine-learning techniques in hospitalized patients.

METHODS

We conducted a retrospective cohort study of patients hospitalized under general internal medicine (GIM) and cardiovascular surgery (CV) at a tertiary care teaching hospital in Toronto, Ontario. Three models were generated using supervised machine learning: least absolute shrinkage and selection operator (LASSO) logistic regression; gradient-boosted trees; and a recurrent neural network. Each model included baseline patient data and time-varying data. Natural-language processing was used to incorporate text data from physician and nursing notes.

RESULTS

We included 8492 GIM admissions and 8044 CV admissions. Hypoglycaemia occurred in 16% of GIM admissions and 13% of CV admissions. The area under the curve for the models in the held-out validation set was approximately 0.80 on the GIM ward and 0.82 on the CV ward. When the threshold for hypoglycaemia was lowered to 2.9 mmol/L (52 mg/dL), similar results were observed. Among the patients at the highest decile of risk, the positive predictive value was approximately 50% and the sensitivity was 99%.

CONCLUSION

Machine-learning approaches can accurately identify patients at high risk of hypoglycaemia in hospital. Future work will involve evaluating whether implementing this model with targeted clinical interventions can improve clinical outcomes.

Predicting Progression Patterns of Type 2 Diabetes using Multi-sensor Measurements

Type 2 diabetes - a prevalent chronic disease worldwide - increases risk for serious health consequences including heart and kidney disease. Forecasting diabetes progression can inform disease management strategies, thereby potentially reducing the likelihood or severity of its consequences. We use continuous glucose monitoring and actigraphy data from 54 individuals with Type 2 diabetes to predict their future hemoglobin A1c, HDL cholesterol, LDL cholesterol, and triglyceride levels one year later. We use a combination of convolutional and recurrent neural networks to develop a deep neural network architecture that can learn the dynamic patterns in different sensors' data and combine those patterns with additional demographic and lab data. To further demonstrate the generalizability of our models, we also evaluate their performance using an independent public dataset of individuals with Type 1 diabetes. In addition to diabetes, our approach could be useful for other serious and chronic physical illness, where dynamic (e.g., from multiple sensors) and static (e.g., demographic) data are used for creating predictive models.

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

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

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.

Deep transfer learning and data augmentation improve glucose levels prediction in type 2 diabetes patients

Accurate prediction of blood glucose variations in type 2 diabetes (T2D) will facilitate better glycemic control and decrease the occurrence of hypoglycemic episodes as well as the morbidity and mortality associated with T2D, hence increasing the quality of life of patients. Owing to the complexity of the blood glucose dynamics, it is difficult to design accurate predictive models in every circumstance, i.e., hypo/normo/hyperglycemic events. We developed deep-learning methods to predict patient-specific blood glucose during various time horizons in the immediate future using patient-specific every 30-min long glucose measurements by the continuous glucose monitoring (CGM) to predict future glucose levels in 5 min to 1 h. In general, the major challenges to address are (1) the dataset of each patient is often too small to train a patient-specific deep-learning model, and (2) the dataset is usually highly imbalanced given that hypo- and hyperglycemic episodes are usually much less common than normoglycemia. We tackle these two challenges using transfer learning and data augmentation, respectively. We systematically examined three neural network architectures, different loss functions, four transfer-learning strategies, and four data augmentation techniques, including mixup and generative models. Taken together, utilizing these methodologies we achieved over 95% prediction accuracy and 90% sensitivity for a time period within the clinically useful 1 h prediction horizon that would allow a patient to react and correct either hypoglycemia and/or hyperglycemia. We have also demonstrated that the same network architecture and transfer-learning methods perform well for the type 1 diabetes OhioT1DM public dataset.

Machine learning-based glucose prediction with use of continuous glucose and physical activity monitoring data: The Maastricht Study

BACKGROUND

Closed-loop insulin delivery systems, which integrate continuous glucose monitoring (CGM) and algorithms that continuously guide insulin dosing, have been shown to improve glycaemic control. The ability to predict future glucose values can further optimize such devices. In this study, we used machine learning to train models in predicting future glucose levels based on prior CGM and accelerometry data.

METHODS

We used data from The Maastricht Study, an observational population-based cohort that comprises individuals with normal glucose metabolism, prediabetes, or type 2 diabetes. We included individuals who underwent >48h of CGM (n = 851), most of whom (n = 540) simultaneously wore an accelerometer to assess physical activity. A random subset of individuals was used to train models in predicting glucose levels at 15- and 60-minute intervals based on either CGM data or both CGM and accelerometer data. In the remaining individuals, model performance was evaluated with root-mean-square error (RMSE), Spearman's correlation coefficient (rho) and surveillance error grid. For a proof-of-concept translation, CGM-based prediction models were optimized and validated with the use of data from individuals with type 1 diabetes (OhioT1DM Dataset, n = 6).

RESULTS

Models trained with CGM data were able to accurately predict glucose values at 15 (RMSE: 0.19mmol/L; rho: 0.96) and 60 minutes (RMSE: 0.59mmol/L, rho: 0.72). Model performance was comparable in individuals with type 2 diabetes. Incorporation of accelerometer data only slightly improved prediction. The error grid results indicated that model predictions were clinically safe (15 min: >99%, 60 min >98%). Our prediction models translated well to individuals with type 1 diabetes, which is reflected by high accuracy (RMSEs for 15 and 60 minutes of 0.43 and 1.73 mmol/L, respectively) and clinical safety (15 min: >99%, 60 min: >91%).

CONCLUSIONS

Machine learning-based models are able to accurately and safely predict glucose values at 15- and 60-minute intervals based on CGM data only. Future research should further optimize the models for implementation in closed-loop insulin delivery systems.

Harnessing Digital Health Technologies to Remotely Manage Diabetic Foot Syndrome: A Narrative Review

About 422 million people worldwide have diabetes and approximately one-third of them have a major risk factor for diabetic foot ulcers, including poor sensation in their feet from peripheral neuropathy and/or poor perfusion to their feet from peripheral artery disease. The current healthcare ecosystem, which is centered on the treatment of established foot disease, often fails to adequately control key reversible risk factors to prevent diabetic foot ulcers leading to unacceptable high foot disease amputation rate, 40% recurrence of ulcers rate in the first year, and high hospital admissions. Thus, the latest diabetic foot ulcer guidelines emphasize that a paradigm shift in research priority from siloed hospital treatments to innovative integrated community prevention is now critical to address the high diabetic foot ulcer burden. The widespread uptake and acceptance of wearable and digital health technologies provide a means to timely monitor major risk factors associated with diabetic foot ulcer, empower patients in self-care, and effectively deliver the remote monitoring and multi-disciplinary prevention needed for those at-risk people and address the health care access disadvantage that people living in remote areas. This narrative review paper summarizes some of the latest innovations in three specific areas, including technologies supporting triaging high-risk patients, technologies supporting care in place, and technologies empowering self-care. While many of these technologies are still in infancy, we anticipate that in response to the Coronavirus Disease 2019 pandemic and current unmet needs to decentralize care for people with foot disease, we will see a new wave of innovations in the area of digital health, smart wearables, telehealth technologies, and “hospital-at-home” care delivery model. These technologies will be quickly adopted at scale to improve remote management of diabetic foot ulcers, smartly triaging those who need to be seen in outpatient or inpatient clinics, and supporting acute or subacute care at home.

Ability of Current Machine Learning Algorithms to Predict and Detect Hypoglycemia in Patients With Diabetes Mellitus: Meta-analysis

Background

Machine learning (ML) algorithms have been widely introduced to diabetes research including those for the identification of hypoglycemia.

Objective

The objective of this meta-analysis is to assess the current ability of ML algorithms to detect hypoglycemia (ie, alert to hypoglycemia coinciding with its symptoms) or predict hypoglycemia (ie, alert to hypoglycemia before its symptoms have occurred).

Methods

Electronic literature searches (from January 1, 1950, to September 14, 2020) were conducted using the Dialog platform that covers 96 databases of peer-reviewed literature. Included studies had to train the ML algorithm in order to build a model to detect or predict hypoglycemia and test its performance. The set of 2 × 2 data (ie, number of true positives, false positives, true negatives, and false negatives) was pooled with a hierarchical summary receiver operating characteristic model.

Results

A total of 33 studies (14 studies for detecting hypoglycemia and 19 studies for predicting hypoglycemia) were eligible. For detection of hypoglycemia, pooled estimates (95% CI) of sensitivity, specificity, positive likelihood ratio (PLR), and negative likelihood ratio (NLR) were 0.79 (0.75-0.83), 0.80 (0.64-0.91), 8.05 (4.79-13.51), and 0.18 (0.12-0.27), respectively. For prediction of hypoglycemia, pooled estimates (95% CI) were 0.80 (0.72-0.86) for sensitivity, 0.92 (0.87-0.96) for specificity, 10.42 (5.82-18.65) for PLR, and 0.22 (0.15-0.31) for NLR.

Conclusions

Current ML algorithms have insufficient ability to detect ongoing hypoglycemia and considerate ability to predict impeding hypoglycemia in patients with diabetes mellitus using hypoglycemic drugs with regard to diagnostic tests in accordance with the Users’ Guide to Medical Literature (PLR should be ≥5 and NLR should be ≤0.2 for moderate reliability). However, it should be emphasized that the clinical applicability of these ML algorithms should be evaluated according to patients’ risk profiles such as for hypoglycemia and its associated complications (eg, arrhythmia, neuroglycopenia) as well as the average ability of the ML algorithms. Continued research is required to develop more accurate ML algorithms than those that currently exist and to enhance the feasibility of applying ML in clinical settings.

Trial Registration

PROSPERO International Prospective Register of Systematic Reviews CRD42020163682; http://www.crd.york.ac.uk/PROSPERO/display_record.php?ID=CRD42020163682

Use and performance of machine learning models for type 2 diabetes prediction in community settings: A systematic review and meta-analysis

OBJECTIVE

We aimed to identify machine learning (ML) models for type 2 diabetes (T2DM) prediction in community settings and determine their predictive performance.

METHOD

Systematic review of ML predictive modelling studies in 13 databases since 2009 was conducted. Primary outcomes included metrics of discrimination, calibration, and classification. Secondary outcomes included important variables, level of validation, and intended use of models. Meta-analysis of c-indices, subgroup analyses, meta-regression, publication bias assessments and sensitivity analyses were conducted.

RESULTS

Twenty-three studies (40 prediction models) were included. Studies with high-, moderate-, and low- risk of bias were 3, 14, and 6 respectively. All studies conducted internal validation whereas none conducted external validation of their models. Twenty studies provided classification metrics to varying extents whereas only 7 studies performed model calibration. Eighteen studies reported information on both the variables used for model development and the feature importance. Twelve studies highlighted potential applicability of their models for T2DM screening. Meta-analysis produced a good pooled c-index (0.812). Sources of heterogeneity were identified through subgroup analyses and meta-regression. Issues pertaining to methodological quality and reporting were observed.

CONCLUSIONS

We found evidence of good performance of ML models for T2DM prediction in the community. Improvements to methodology, reporting and validation are needed before they can be used at scale.

Identification of risk factors for patients with diabetes: diabetic polyneuropathy case study

BACKGROUND

Methods of data mining and analytics can be efficiently applied in medicine to develop models that use patient-specific data to predict the development of diabetic polyneuropathy. However, there is room for improvement in the accuracy of predictive models. Existing studies of diabetes polyneuropathy considered a limited number of predictors in one study to enable a comparison of efficiency of different machine learning methods with different predictors to find the most efficient one. The purpose of this study is the implementation of machine learning methods for identifying the risk of diabetes polyneuropathy based on structured electronic medical records collected in databases of medical information systems.

METHODS

For the purposes of our study, we developed a structured procedure for predictive modelling, which includes data extraction and preprocessing, model adjustment and performance assessment, selection of the best models and interpretation of results. The dataset contained a total number of 238,590 laboratory records. Each record 27 laboratory tests, age, gender and presence of retinopathy or nephropathy). The records included information about 5846 patients with diabetes. Diagnosis served as a source of information about the target class values for classification.

RESULTS

It was discovered that inclusion of two expressions, namely "nephropathy" and "retinopathy" allows to increase the performance, achieving up to 79.82% precision, 81.52% recall, 80.64% F1 score, 82.61% accuracy, and 89.88% AUC using the neural network classifier. Additionally, different models showed different results in terms of interpretation significance: random forest confirmed that the most important risk factor for polyneuropathy is the increased neutrophil level, meaning the presence of inflammation in the body. Linear models showed linear dependencies of the presence of polyneuropathy on blood glucose levels, which is confirmed by the clinical interpretation of the importance of blood glucose control.

CONCLUSION

Depending on whether one needs to identify pathophysiological mechanisms for one's prospective study or identify early or late predictors, the choice of model will vary. In comparison with the previous studies, our research makes a comprehensive comparison of different decisions using a large and well-structured dataset applied to different decision support tasks.

Prediction of Type 2 Diabetes Risk and Its Effect Evaluation Based on the XGBoost Model

In view of the harm of diabetes to the population, we have introduced an ensemble learning algorithm—EXtreme Gradient Boosting (XGBoost) to predict the risk of type 2 diabetes and compared it with Support Vector Machines (SVM), the Random Forest (RF) and K-Nearest Neighbor (K-NN) algorithm in order to improve the prediction effect of existing models. The combination of convenient sampling and snowball sampling in Xicheng District, Beijing was used to conduct a questionnaire survey on the personal data, eating habits, exercise status and family medical history of 380 middle-aged and elderly people. Then, we trained the models and obtained the disease risk index for each sample with 10-fold cross-validation. Experiments were made to compare the commonly used machine learning algorithms mentioned above and we found that XGBoost had the best prediction effect, with an average accuracy of 0.8909 and the area under the receiver’s working characteristic curve (AUC) was 0.9182. Therefore, due to the superiority of its architecture, XGBoost has more outstanding prediction accuracy and generalization ability than existing algorithms in predicting the risk of type 2 diabetes, which is conducive to the intelligent prevention and control of diabetes in the future.

Artificial Intelligence in Pharmacoepidemiology: A Systematic Review. Part 1-Overview of Knowledge Discovery Techniques in Artificial Intelligence

Aim

To perform a systematic review on the application of artificial intelligence (AI) based knowledge discovery techniques in pharmacoepidemiology.

Study Eligibility Criteria

Clinical trials, meta-analyses, narrative/systematic review, and observational studies using (or mentioning articles using) artificial intelligence techniques were eligible. Articles without a full text available in the English language were excluded.

Data Sources

Articles recorded from 1950/01/01 to 2019/05/06 in Ovid MEDLINE were screened.

Participants

Studies including humans (real or simulated) exposed to a drug.

Results

In total, 72 original articles and 5 reviews were identified via Ovid MEDLINE. Twenty different knowledge discovery methods were identified, mainly from the area of machine learning (66/72; 91.7%). Classification/regression (44/72; 61.1%), classification/regression + model optimization (13/72; 18.0%), and classification/regression + features selection (12/72; 16.7%) were the three most frequent tasks in reviewed literature that machine learning methods has been applied to solve. The top three used techniques were artificial neural networks, random forest, and support vector machines models.

Conclusions

The use of knowledge discovery techniques of artificial intelligence techniques has increased exponentially over the years covering numerous sub-topics of pharmacoepidemiology.

Systematic Review Registration

Systematic review registration number in PROSPERO: CRD42019136552.

Homogeneous and heterogeneous ensemble classification methods in diabetes disease: a review

This paper explores the use of ensemble classification methods in the context of the diabetes disease. An analysis was carried out that formulates and answers seven research questions: publication trends, channels and venues; medical tasks undertaken; ensemble types proposed; single techniques used to construct the ensemble methods; rules used to draw the output of the ensemble; datasets used to build and evaluate the ensemble methods; and tools used. A total of 107 papers were chosen after a study selection process. Ensemble methods were applied to diabetes in 2003 for the first time. All medical tasks related to the diabetes disease were investigated, and the diagnosis task was the most frequently addressed activity by means of ensemble methods. The homogeneous ensembles were the most common in the literature. Moreover, decision trees and support vector machines were the most used techniques to build homogeneous and heterogeneous ensembles, respectively. The most frequently found combiner was the majority voting rule. Our findings suggest that ensemble classification methods yield better accuracy than single classifiers. This statement, however, requires an aggregation of the evidence reported in the literature by means of a systematic literature review.

Prediction of Nocturnal Hypoglycemia From Continuous Glucose Monitoring Data in People With Type 1 Diabetes: A Proof-of-Concept Study

BACKGROUND

Intensive insulin therapy has documented benefits but may also come at the expense of a higher risk of hypoglycemia. Hypoglycemia is associated with higher all-cause mortality and nocturnal hypoglycemia has been associated with the sudden dead-in-bed syndrome. This proof-of-concept study sought to investigate if nocturnal hypoglycemia can be predicted.

METHOD

Continuous glucose monitoring, meal, insulin, and demographics data from 463 people with type 1 diabetes were obtained from a clinical trial. A total of 4721 nights without or with hypoglycemia (429) were available including data from three consecutive days before the night. Thirty-two features were calculated based on these data. Data were split into 20% participants for evaluation and 80% for training. The optimal feature subset was found from forward selection of the 80% participants with linear discriminant analysis as basis for the classifier.

RESULTS

The forward selection resulted in a feature subset of four features. The evaluation resulted in an area under the receiver operating characteristics curve (ROC-AUC) of 0.79 leading to a sensitivity and a specificity of, e.g., 75% and 70%.

CONCLUSIONS

It was possible to predict nocturnal hypoglycemic episodes with a ROC-AUC of 0.79. A warning at bedtime about nocturnal hypoglycemia could be of great help for people with diabetes to enable preventive actions. Further development of the proposed algorithm is needed for implementation in everyday practice.

Big Data and diabetes: the applications of Big Data for diabetes care now and in the future

We review current applications of Big Data in diabetes care and consider the future potential by carrying out a scoping study of the academic literature on Big Data and diabetes care. Healthcare data are being produced at ever-increasing rates, and this information has the potential to transform the provision of diabetes care. Big Data is beginning to have an impact on diabetes care through data research. The use of Big Data for routine clinical care is still a future application. Vast amounts of healthcare data are already being produced, and the key is harnessing these to produce actionable insights. Considerable development work is required to achieve these goals.

Precision Medicine and Artificial Intelligence: A Pilot Study on Deep Learning for Hypoglycemic Events Detection based on ECG

Tracking the fluctuations in blood glucose levels is important for healthy subjects and crucial diabetic patients. Tight glucose monitoring reduces the risk of hypoglycemia, which can result in a series of complications, especially in diabetic patients, such as confusion, irritability, seizure and can even be fatal in specific conditions. Hypoglycemia affects the electrophysiology of the heart. However, due to strong inter-subject heterogeneity, previous studies based on a cohort of subjects failed to deploy electrocardiogram (ECG)-based hypoglycemic detection systems reliably. The current study used personalised medicine approach and Artificial Intelligence (AI) to automatically detect nocturnal hypoglycemia using a few heartbeats of raw ECG signal recorded with non-invasive, wearable devices, in healthy individuals, monitored 24 hours for 14 consecutive days. Additionally, we present a visualisation method enabling clinicians to visualise which part of the ECG signal (e.g., T-wave, ST-interval) is significantly associated with the hypoglycemic event in each subject, overcoming the intelligibility problem of deep-learning methods. These results advance the feasibility of a real-time, non-invasive hypoglycemia alarming system using short excerpts of ECG signal.

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.

Artificial Intelligence Applications in Type 2 Diabetes Mellitus Care: Focus on Machine Learning Methods

Objectives

The incidence of type 2 diabetes mellitus has increased significantly in recent years. With the development of artificial intelligence applications in healthcare, they are used for diagnosis, therapeutic decision making, and outcome prediction, especially in type 2 diabetes mellitus. This study aimed to identify the artificial intelligence (AI) applications for type 2 diabetes mellitus care.

Methods

This is a review conducted in 2018. We searched the PubMed, Web of Science, and Embase scientific databases, based on a combination of related mesh terms. The article selection process was based on Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA). Finally, 31 articles were selected after inclusion and exclusion criteria were applied. Data gathering was done by using a data extraction form. Data were summarized and reported based on the study objectives.

Results

The main applications of AI for type 2 diabetes mellitus care were screening and diagnosis in different stages. Among all of the reviewed AI methods, machine learning methods with 71% (n = 22) were the most commonly applied techniques. Many applications were in multi method forms (23%). Among the machine learning algorithms applications, support vector machine (21%) and naive Bayesian (19%) were the most commonly used methods. The most important variables that were used in the selected studies were body mass index, fasting blood sugar, blood pressure, HbA1c, triglycerides, low-density lipoprotein, high-density lipoprotein, and demographic variables.

Conclusions

It is recommended to select optimal algorithms by testing various techniques. Support vector machine and naive Bayesian might achieve better performance than other applications due to the type of variables and targets in diabetes-related outcomes classification.

On the Possibility of Predicting Glycaemia 'On the Fly' with Constrained IoT Devices in Type 1 Diabetes Mellitus Patients

Type 1 Diabetes Mellitus (DM1) patients are used to checking their blood glucose levels several times per day through finger sticks and, by subjectively handling this information, to try to predict their future glycaemia in order to choose a proper strategy to keep their glucose levels under control, in terms of insulin dosages and other factors. However, recent Internet of Things (IoT) devices and novel biosensors have allowed the continuous collection of the value of the glucose level by means of Continuous Glucose Monitoring (CGM) so that, with the proper Machine Learning (ML) algorithms, glucose evolution can be modeled, thus permitting a forecast of this variable. On the other hand, glycaemia dynamics require that such a model be user-centric and should be recalculated continuously in order to reflect the exact status of the patient, i.e., an ‘on-the-fly’ approach. In order to avoid, for example, the risk of being disconnected from the Internet, it would be ideal if this task could be performed locally in constrained devices like smartphones, but this would only be feasible if the execution times were fast enough. Therefore, in order to analyze if such a possibility is viable or not, an extensive, passive, CGM study has been carried out with 25 DM1 patients in order to build a solid dataset. Then, some well-known univariate algorithms have been executed in a desktop computer (as a reference) and two constrained devices: a smartphone and a Raspberry Pi, taking into account only past glycaemia data to forecast glucose levels. The results indicate that it is possible to forecast, in a smartphone, a 15-min horizon with a Root Mean Squared Error (RMSE) of 11.65 mg/dL in just 16.15 s, employing a 10-min sampling of the past 6 h of data and the Random Forest algorithm. With the Raspberry Pi, the computational effort increases to 56.49 s assuming the previously mentioned parameters, but this can be improved to 34.89 s if Support Vector Machines are applied, achieving in this case an RMSE of 19.90 mg/dL. Thus, this paper concludes that local on-the-fly forecasting of glycaemia would be affordable with constrained devices.

Utility of Big Data in Predicting Short-Term Blood Glucose Levels in Type 1 Diabetes Mellitus Through Machine Learning Techniques

Machine learning techniques combined with wearable electronics can deliver accurate short-term blood glucose level prediction models. These models can learn personalized glucose–insulin dynamics based on the sensor data collected by monitoring several aspects of the physiological condition and daily activity of an individual. Until now, the prevalent approach for developing data-driven prediction models was to collect as much data as possible to help physicians and patients optimally adjust therapy. The objective of this work was to investigate the minimum data variety, volume, and velocity required to create accurate person-centric short-term prediction models. We developed a series of these models using different machine learning time series forecasting techniques suitable for execution within a wearable processor. We conducted an extensive passive patient monitoring study in real-world conditions to build an appropriate data set. The study involved a subset of type 1 diabetic subjects wearing a flash glucose monitoring system. We comparatively and quantitatively evaluated the performance of the developed data-driven prediction models and the corresponding machine learning techniques. Our results indicate that very accurate short-term prediction can be achieved by only monitoring interstitial glucose data over a very short time period and using a low sampling frequency. The models developed can predict glucose levels within a 15-min horizon with an average error as low as 15.43 mg/dL using only 24 historic values collected within a period of sex hours, and by increasing the sampling frequency to include 72 values, the average error is reduced to 10.15 mg/dL. Our prediction models are suitable for execution within a wearable device, requiring the minimum hardware requirements while at simultaneously achieving very high prediction accuracy.

A Review of Predictive Low Glucose Suspend and Its Effectiveness in Preventing Nocturnal Hypoglycemia

To evaluate the effectiveness of predictive low glucose suspend (PLGS) systems within sensor-augmented insulin infusion pumps at preventing nocturnal hypoglycemia in patients with type 1 diabetes (DM1), we performed a systematic review and meta-analysis of randomized crossover trials. Pubmed and Google Scholar were searched for randomized crossover trials, published between January 2013 and July 2018, in nonpregnant outpatients with DM1, which compared event rates during PLGS overnight periods and non-PLGS overnight periods. The primary outcome was the proportion of overnight periods with one or more hypoglycemic measurement. When available, individual patient data were used to assess the effect of clustering measurements within patients. Four studies (272 patients, 10,735 patient-nights: 5422 PLGS and 5313 non-PLGS) were included in the meta-analysis. Two studies reported patient-level data that permitted assessment of the effect of clustering measurements within patients. The effect on the risk difference was minimal. The proportion of overnight periods with one or more episodes of hypoglycemia was 19.6% for the PLGS periods and 27.8% for the non-PLGS periods. Based on the pooled estimate, PLGS overnight periods were associated with an 8.8% lower risk of hypoglycemia (risk difference -0.088; 95% CI -0.119 to -0.056, I² = 67.4%, τ² = 0.0006, 4 studies). PLGS systems can reduce nocturnal hypoglycemic events in patients with DM1.

LSTM DSS Automatism and Dataset Optimization for Diabetes Prediction

The paper is focused on the application of Long Short-Term Memory (LSTM) neural network enabling patient health status prediction focusing the attention on diabetes. The proposed topic is an upgrade of a Multi-Layer Perceptron (MLP) algorithm that can be fully embedded into an Enterprise Resource Planning (ERP) platform. The LSTM approach is applied for multi-attribute data processing and it is integrated into an information system based on patient management. To validate the proposed model, we have adopted a typical dataset used in the literature for data mining model testing. The study is focused on the procedure to follow for a correct LSTM data analysis by using artificial records (LSTM-AR-), improving the training dataset stability and test accuracy if compared with traditional MLP and LSTM approaches. The increase of the artificial data is important for all cases where only a few data of the training dataset are available, as for more practical cases. The paper represents a practical application about the LSTM approach into the decision support systems (DSSs) suitable for homecare assistance and for de-hospitalization processes. The paper goal is mainly to provide guidelines for the application of LSTM neural network in type I and II diabetes prediction adopting automatic procedures. A percentage improvement of test set accuracy of 6.5% has been observed by applying the LSTM-AR- approach, comparing results with up-to-date MLP works. The LSTM-AR- neural network can be applied as an alternative approach for all homecare platforms where not enough training sequential dataset is available.

Artificial intelligence predicts the progression of diabetic kidney disease using big data machine learning

Artificial intelligence (AI) is expected to support clinical judgement in medicine. We constructed a new predictive model for diabetic kidney diseases (DKD) using AI, processing natural language and longitudinal data with big data machine learning, based on the electronic medical records (EMR) of 64,059 diabetes patients. AI extracted raw features from the previous 6 months as the reference period and selected 24 factors to find time series patterns relating to 6-month DKD aggravation, using a convolutional autoencoder. AI constructed the predictive model with 3,073 features, including time series data using logistic regression analysis. AI could predict DKD aggravation with 71% accuracy. Furthermore, the group with DKD aggravation had a significantly higher incidence of hemodialysis than the non-aggravation group, over 10 years (N = 2,900). The new predictive model by AI could detect progression of DKD and may contribute to more effective and accurate intervention to reduce hemodialysis.

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

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

Detecting Hypoglycemia Incidents Reported in Patients' Secure Messages: Using Cost-Sensitive Learning and Oversampling to Reduce Data Imbalance

BACKGROUND

Improper dosing of medications such as insulin can cause hypoglycemic episodes, which may lead to severe morbidity or even death. Although secure messaging was designed for exchanging nonurgent messages, patients sometimes report hypoglycemia events through secure messaging. Detecting these patient-reported adverse events may help alert clinical teams and enable early corrective actions to improve patient safety.

OBJECTIVE

We aimed to develop a natural language processing system, called HypoDetect (Hypoglycemia Detector), to automatically identify hypoglycemia incidents reported in patients' secure messages.

METHODS

An expert in public health annotated 3000 secure message threads between patients with diabetes and US Department of Veterans Affairs clinical teams as containing patient-reported hypoglycemia incidents or not. A physician independently annotated 100 threads randomly selected from this dataset to determine interannotator agreement. We used this dataset to develop and evaluate HypoDetect. HypoDetect incorporates 3 machine learning algorithms widely used for text classification: linear support vector machines, random forest, and logistic regression. We explored different learning features, including new knowledge-driven features. Because only 114 (3.80%) messages were annotated as positive, we investigated cost-sensitive learning and oversampling methods to mitigate the challenge of imbalanced data.

RESULTS

The interannotator agreement was Cohen kappa=.976. Using cross-validation, logistic regression with cost-sensitive learning achieved the best performance (area under the receiver operating characteristic curve=0.954, sensitivity=0.693, specificity 0.974, F1 score=0.590). Cost-sensitive learning and the ensembled synthetic minority oversampling technique improved the sensitivity of the baseline systems substantially (by 0.123 to 0.728 absolute gains). Our results show that a variety of features contributed to the best performance of HypoDetect.

CONCLUSIONS

Despite the challenge of data imbalance, HypoDetect achieved promising results for the task of detecting hypoglycemia incidents from secure messages. The system has a great potential to facilitate early detection and treatment of hypoglycemia.

Developing a model to predict unfavourable treatment outcomes in patients with tuberculosis and human immunodeficiency virus co-infection in Delhi, India

BACKGROUND

Tuberculosis (TB) patients with human immunodeficiency virus (HIV) co-infection have worse TB treatment outcomes compared to patients with TB alone. The distribution of unfavourable treatment outcomes differs by socio-demographic and clinical characteristics, allowing for early identification of patients at risk.

OBJECTIVE

To develop a statistical model that can provide individual probabilities of unfavourable outcomes based on demographic and clinical characteristics of TB-HIV co-infected patients.

METHODOLOGY

We used data from all TB patients with known HIV-positive test results (aged ≥15 years) registered for first-line anti-TB treatment (ATT) in 2015 under the Revised National TB Control Programme (RNTCP) in Delhi, India. We included variables on demographics and pre-treatment clinical characteristics routinely recorded and reported to RNTCP and the National AIDS Control Organization. Binomial logistic regression was used to develop a statistical model to estimate probabilities of unfavourable TB treatment outcomes (i.e., death, loss to follow-up, treatment failure, transfer out of program, and a switch to drug-resistant regimen).

RESULTS

Of 55,260 TB patients registered for ATT in 2015 in Delhi, 928 (2%) had known HIV-positive test results. Of these, 816 (88%) had drug-sensitive TB and were ≥15 years. Among 816 TB-HIV patients included, 157 (19%) had unfavourable TB treatment outcomes. We developed a model for predicting unfavourable outcomes using age, sex, disease classification (pulmonary versus extra-pulmonary), TB treatment category (new or previously treated case), sputum smear grade, known HIV status at TB diagnosis, antiretroviral treatment at TB diagnosis, and CD4 cell count at ATT initiation. The chi-square p-value for model calibration assessed using the Hosmer-Lemeshow test was 0.15. The model discrimination, measured as the area under the receiver operator characteristic (ROC) curve, was 0.78.

CONCLUSION

The model had good internal validity, but should be validated with an independent cohort of TB-HIV co-infected patients to assess its performance before clinical or programmatic use.

Droplet digital PCR-based circulating microRNA detection serve as a promising diagnostic method for gastric cancer

BACKGROUND

Novel non-invasive biomarkers for gastric cancer (GC) are needed, because the present diagnostic methods for GC are either invasive or insensitive and non-specific in clinic. The presence of stable circulating microRNAs (miRNAs) in plasma suggested a promising role as GC biomarkers.

METHODS

Based on the quantitative droplet digital PCR (ddPCR), four miRNAs (miR-21, miR-93, miR-106a and miR-106b) related to the presence of GC were identified in plasma from a training cohort of 147 participants and a validation cohort of 28 participants.

RESULTS

All circulating miRNA levels were significantly higher in the plasma of GC patients compared to healthy controls (P < 0.05). Through a combination of four miRNAs by logistic regression model, receiver operating characteristic (ROC) analyses yielded the highest AUC value of 0.887 in discriminating GC patients from healthy volunteers. Furthermore, miR-21, miR-93 and miR-106b levels were significantly related to an advanced TNM stage in GC patients. ROC analyses of the combined miRNA panel also showed the highest AUC value of 0.809 in discriminating GC patients with TNM stage I and II from stage III and IV. Through combining four miRNAs and clinical parameters, a classical random forest model was established in the training stage. In the validation cohort, it correctly discriminated 23 out of 28 samples in the blinded phase (false rate, 17.8%).

CONCLUSIONS

Using the ddPCR technique, circulating miR-21, miR-93, miR-106a and miR-106b could be used as diagnostic plasma biomarkers in gastric cancer patients.

The New Possibilities from "Big Data" to Overlooked Associations Between Diabetes, Biochemical Parameters, Glucose Control, and Osteoporosis

PURPOSE OF REVIEW

To review current practices and technologies within the scope of "Big Data" that can further our understanding of diabetes mellitus and osteoporosis from large volumes of data. "Big Data" techniques involving supervised machine learning, unsupervised machine learning, and deep learning image analysis are presented with examples of current literature.

RECENT FINDINGS

Supervised machine learning can allow us to better predict diabetes-induced osteoporosis and understand relative predictor importance of diabetes-affected bone tissue. Unsupervised machine learning can allow us to understand patterns in data between diabetic pathophysiology and altered bone metabolism. Image analysis using deep learning can allow us to be less dependent on surrogate predictors and use large volumes of images to classify diabetes-induced osteoporosis and predict future outcomes directly from images. "Big Data" techniques herald new possibilities to understand diabetes-induced osteoporosis and ascertain our current ability to classify, understand, and predict this condition.