Predicting the Development of Type 2 Diabetes in a Large Australian Cohort Using Machine-Learning Techniques: Longitudinal Survey Study

AWD-stacking: An enhanced ensemble learning model for predicting glucose levels

Accurate prediction of blood glucose levels is essential for type 1 diabetes optimizing insulin therapy and minimizing complications in patients with type 1 diabetes. Using ensemble learning algorithms is a promising approach. In this regard, this study proposes an improved stacking ensemble learning algorithm for predicting blood glucose level, in which three improved long short-term memory network models are used as the base model, and an improved nearest neighbor propagation clustering algorithm is adaptively weighted to this ensemble model. The OhioT1DM dataset is used to train and evaluate the performance of the proposed model. This study evaluated the performance of the proposed model using the Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and Matthews Correlation Coefficient (MCC) as the evaluation metrics. The experimental results demonstrate that the proposed model achieves an RMSE of 1.425 mg/dL, MAE of 0.721 mg/dL, and MCC of 0.982 mg/dL for a 30-minute prediction horizon(PH), RMSE of 3.212 mg/dL, MAE of 1.605 mg/dL, and MCC of 0.950 mg/dL for a 45-minute PH; and RMSE of 6.346 mg/dL, MAE of 3.232 mg/dL, and MCC of 0.930 mg/dL for a 60-minute PH. Compared with the best non-ensemble model StackLSTM, the RMSE and MAE were improved by up to 27.92% and 65.32%, respectively. Clarke Error Grid Analysis and critical difference diagram revealed that the model errors were within 10%. The model proposed in this study exhibits state-of-the-art predictive performance, making it suitable for clinical decision-making and of significant importance for the effective treatment of diabetes in patients.

A scoping review of artificial intelligence-based methods for diabetes risk prediction

The increasing prevalence of type 2 diabetes mellitus (T2DM) and its associated health complications highlight the need to develop predictive models for early diagnosis and intervention. While many artificial intelligence (AI) models for T2DM risk prediction have emerged, a comprehensive review of their advancements and challenges is currently lacking. This scoping review maps out the existing literature on AI-based models for T2DM prediction, adhering to the PRISMA extension for Scoping Reviews guidelines. A systematic search of longitudinal studies was conducted across four databases, including PubMed, Scopus, IEEE-Xplore, and Google Scholar. Forty studies that met our inclusion criteria were reviewed. Classical machine learning (ML) models dominated these studies, with electronic health records (EHR) being the predominant data modality, followed by multi-omics, while medical imaging was the least utilized. Most studies employed unimodal AI models, with only ten adopting multimodal approaches. Both unimodal and multimodal models showed promising results, with the latter being superior. Almost all studies performed internal validation, but only five conducted external validation. Most studies utilized the area under the curve (AUC) for discrimination measures. Notably, only five studies provided insights into the calibration of their models. Half of the studies used interpretability methods to identify key risk predictors revealed by their models. Although a minority highlighted novel risk predictors, the majority reported commonly known ones. Our review provides valuable insights into the current state and limitations of AI-based models for T2DM prediction and highlights the challenges associated with their development and clinical integration.

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.

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

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

Strikes and Gutters: Biomarkers and anthropometric measures for predicting diagnosed diabetes mellitus in adults in low- and middle-income countries

The management of diabetes necessitates the requirement of reliable health indices, specifically biomarkers and anthropometric measures, to detect the presence or absence of the disease. Nevertheless, limited robust empirical evidence exists regarding the optimal metrics for predicting diabetes in adults, particularly within low- and middle-income countries. This study investigates objective and subjective indices for screening diabetes in these countries.

METHODS

Data for this study was sourced from surveys conducted among adults (aged 18 years and above) in seventeen (17) countries. Self-reported diabetes status, fifty-four biomarkers, and twenty-six core and twenty-eight estimated anthropometric indices, including weight, waist circumference, body mass index, glycaemic triglycerides, and fasting blood glucose, were utilised to construct lasso regression models.

RESULTS

The study revealed variances in diabetes prediction outcomes across different countries. Central adiposity measures, fasting plasma glucose and glycaemic triglycerides demonstrated superior predictive capabilities for diabetes when compared to body mass index. Furthermore, fasting plasma or blood glucose, serving as a biomarker, emerged as the most accurate predictor of diabetes.

CONCLUSIONS

These findings offer critical insights into both general and context-specific tools for diabetes screening. The study proposes that fasting plasma glucose and central adiposity indices should be considered as routine screening tools for diabetes, both in policy interventions and clinical practice. By identifying adults with or at higher risk of developing diabetes and implementing appropriate interventions, these screening tools possess the potential to mitigate diabetes-related complications in low- and middle-income countries.

Associations between the levels of circulating inflammatory adipokines and the risk of type 2 diabetes in Chinese male individuals: A case-control study

BACKGROUND

Whether the levels of circulating inflammatory adipokines affect the progression of type 2 diabetes (T2D) remains unclear. This study aimed to assess the association between circulating inflammatory adipokine levels and risk of T2D.

METHODS

This case-control study involved 130 individuals consisting of 66 healthy controls (Control group) and 64 patients with T2D (T2D group) in Lishui Municipal Central Hospital from January 2017 to June 2017. Multivariate logistic regression analysis was applied to assess the associations between circulating inflammatory adipokine levels and the risk of T2D.

RESULTS

There were significant differences in the levels of adiponectin (p = 0.013) and visfatin (p < 0.001) between the T2D and Control groups. In contrast, no significant differences in leptin (p = 0.113), TNF-α (p = 0.632), and IL-6 (p = 0.156) levels were found between the groups. Multivariate logistic regression indicated that elevated visfatin level was associated with an increased risk of T2D (OR: 3.543; 95% CI: 1.771-7.088; p < 0.001), while adiponectin (OR: 1.946; 95% CI: 0.925-4.094; p = 0.079), leptin (OR: 3.723; 95% CI: 0.788-17.583; p = 0.097), TNF-α (OR: 1.081; 95% CI: 0.911-1.281; p = 0.373), and IL-6 (OR: 0.878; 95% CI: 0.657-1.173; p = 0.379) were not associated with the risk of T2D.

CONCLUSIONS

This study found elevated visfatin levels are associated with an increased risk of T2D, while adiponectin, leptin, TNF-α, and IL-6 are not. These findings should be further verified by a large-scale prospective study.

Projected rapid growth in diabetes disease burden and economic burden in China: a spatio-temporal study from 2020 to 2030

Background

This study projects the trend of disease burden and economic burden of diabetes in 33 Chinese provinces and nationally during 2020-2030 and investigates its spatial disparities.

Methods

Time series prediction on the prevalence and disability-adjusted life-year (DALY) rates of diabetes was conducted using a Bayesian modelling approach in 2020-2030. The top-down method and the human capital method were used to predict the direct and indirect costs of diabetes for each Chinese province. Global and local spatial autocorrelation analyses were used to identify geographic clusters of low-or high-burden areas.

Findings

Diabetes prevalence in Chinese adults aged 20-79 years was projected to increase from 8.2% to 9.7% during 2020-2030. During the same period, the total costs of diabetes would increase from $250.2 billion to $460.4 billion, corresponding to an annual growth rate of 6.32%. The total costs of diabetes as a percentage of GDP would increase from 1.58% to 1.69% in China during 2020-2030, suggesting a faster growth in the economic burden of diabetes than China's economic growth. Consistently, the per-capita economic burden of diabetes would increase from $231 to $414 in China during 2020-2030, with an annual growth rate of 6.02%. High disease and economic burden areas were aggregated in Northeast and/or North China.

Interpretation

Our study projects a significant growth of disease and economic burden of diabetes in China during 2020-2030, with strong spatial aggregation in northern Chinese regions. The increase in the economic burden of diabetes will exceed that of GDP.

Funding

National Natural Science Foundation of China, Outstanding Young Scholars Funding.

Multidimensional Sleep and Cardiometabolic Risk Factors for Type 2 Diabetes: Examining Self-Report and Objective Dimensions of Sleep

Purpose:

The purpose of the study was to determine the association between objective and self-report measures of sleep and cardiometabolic risk factors for type 2 diabetes.

Methods:

This study examines data on Australian adults, collected as part of the Child Health CheckPoint study. Sleep was examined in terms of actigraphy-derived sleep duration, timing, efficiency and variability; and self-report trouble sleeping. Cardiometabolic risk factors for type 2 diabetes were examined in terms of body mass index and biomarkers of inflammation and dyslipidemia. Generalized estimating equations, adjusted for geographic clustering, were used to determine the association between measures of sleep and cardiometabolic risk factors.

Results:

Complete case analysis was conducted for 1017 parents (87% mothers). Both objective and self-report measures of sleep were significantly but weakly associated with cardiometabolic risk factors.

Conclusion:

Both objective and self-report measures of sleep are significantly associated with cardiometabolic risk factors for type 2 diabetes. Self-report troubled sleep is associated with poorer cardiometabolic health, independent of actigraphy-derived sleep parameters.

Incidence and risk factors of diabetes mellitus in the Chinese population: a dynamic cohort study

OBJECTIVE

Diabetes mellitus is a common condition often associated with an ageing population. However, only few longitudinal studies in China have investigated the incidence of diabetes and identified its risk factors. Therefore, this study aimed to investigate the incidence and risk factors of diabetes in Chinese people aged ≥45 years using the harmonised China Health and Retirement Longitudinal Study (CHARLS) data.

DESIGN

A dynamic cohort study.

SETTING

The harmonised CHARLS 2011-2018.

PARTICIPANTS

19 988 adults aged ≥45 years.

PRIMARY OUTCOME MEASURE

Incident diabetes from 2011 to 2018.

RESULTS

The harmonised CHARLS is a representative longitudinal survey of people aged ≥45 years. Using data extracted from the harmonised CHARLS, we calculated the incidence of diabetes and used a competing risk model to determine risk factors of diabetes. In 2011-2013, 2013-2015, 2015-2018, the crude incidence of diabetes among middle-aged and older people in China was 1403.21 (1227.09 to 1604.19), 1673.22 (1485.73 to 1883.92) and 3919.83 (3646.01 to 4213.30) per 100 000 person-years, respectively, with a significant increasing trend. There were no geographical variations in the incidence of diabetes. Age, obesity and alcohol consumption were associated with an increased risk of incident diabetes.

CONCLUSION

The incidence of diabetes increased annually, without any geographical differences. Age, obesity and alcohol consumption were found to be risk factors for incident diabetes.

Patient-Generated Data Analytics of Health Behaviors of People Living With Type 2 Diabetes: Scoping Review

Background

Complications due to type 2 diabetes (T2D) can be mitigated through proper self-management that can positively change health behaviors. Technological tools are available to help people living with, or at risk of developing, T2D to manage their condition, and such tools provide a large repository of patient-generated health data (PGHD). Analytics can provide insights into the health behaviors of people living with T2D.

Objective

The aim of this review is to investigate what can be learned about the health behaviors of those living with, or at risk of developing, T2D through analytics from PGHD.

Methods

A scoping review using the Arksey and O’Malley framework was conducted in which a comprehensive search of the literature was conducted by 2 reviewers. In all, 3 electronic databases (PubMed, IEEE Xplore, and ACM Digital Library) were searched using keywords associated with diabetes, behaviors, and analytics. Several rounds of screening using predetermined inclusion and exclusion criteria were conducted, after which studies were selected. Critical examination took place through a descriptive-analytical narrative method, and data extracted from the studies were classified into thematic categories. These categories reflect the findings of this study as per our objective.

Results

We identified 43 studies that met the inclusion criteria for this review. Although 70% (30/43) of the studies examined PGHD independently, 30% (13/43) combined PGHD with other data sources. Most of these studies used machine learning algorithms to perform their analysis. The themes identified through this review include predicting diabetes or obesity, deriving factors that contribute to diabetes or obesity, obtaining insights from social media or web-based forums, predicting glycemia, improving adherence and outcomes, analyzing sedentary behaviors, deriving behavior patterns, discovering clinical correlations from behaviors, and developing design principles.

Conclusions

The increased volume and availability of PGHD have the potential to derive analytical insights into the health behaviors of people living with T2D. From the literature, we determined that analytics can predict outcomes and identify granular behavior patterns from PGHD. This review determined the broad range of insights that can be examined through PGHD, which constitutes a unique source of data for these applications that would not be possible through the use of other data sources.

Usefulness of Machine Learning for Identification of Referable Diabetic Retinopathy in a Large-Scale Population-Based Study

Purpose: To development and validation of machine learning-based classifiers based on simple non-ocular metrics for detecting referable diabetic retinopathy (RDR) in a large-scale Chinese population–based survey.

Methods: The 1,418 patients with diabetes mellitus from 8,952 rural residents screened in the population-based Dongguan Eye Study were used for model development and validation. Eight algorithms [extreme gradient boosting (XGBoost), random forest, naïve Bayes, k-nearest neighbor (KNN), AdaBoost, Light GBM, artificial neural network (ANN), and logistic regression] were used for modeling to detect RDR in individuals with diabetes. The area under the receiver operating characteristic curve (AUC) and their 95% confidential interval (95% CI) were estimated using five-fold cross-validation as well as an 80:20 ratio of training and validation.

Results: The 10 most important features in machine learning models were duration of diabetes, HbA1c, systolic blood pressure, triglyceride, body mass index, serum creatine, age, educational level, duration of hypertension, and income level. Based on these top 10 variables, the XGBoost model achieved the best discriminative performance, with an AUC of 0.816 (95%CI: 0.812, 0.820). The AUCs for logistic regression, AdaBoost, naïve Bayes, and Random forest were 0.766 (95%CI: 0.756, 0.776), 0.754 (95%CI: 0.744, 0.764), 0.753 (95%CI: 0.743, 0.763), and 0.705 (95%CI: 0.697, 0.713), respectively.

Conclusions: A machine learning–based classifier that used 10 easily obtained non-ocular variables was able to effectively detect RDR patients. The importance scores of the variables provide insight to prevent the occurrence of RDR. Screening RDR with machine learning provides a useful complementary tool for clinical practice in resource-poor areas with limited ophthalmic infrastructure.

Artificial intelligence and diabetes technology: A review

Artificial intelligence (AI) is widely discussed in the popular literature and is portrayed as impacting many aspects of human life, both in and out of the workplace. The potential for revolutionizing healthcare is significant because of the availability of increasingly powerful computational platforms and methods, along with increasingly informative sources of patient data, both in and out of clinical settings. This review aims to provide a realistic assessment of the potential for AI in understanding and managing diabetes, accounting for the state of the art in the methodology and medical devices that collect data, process data, and act accordingly. Acknowledging that many conflicting definitions of AI have been put forth, this article attempts to characterize the main elements of the field as they relate to diabetes, identifying the main perspectives and methods that can (i) affect basic understanding of the disease, (ii) affect understanding of risk factors (genetic, clinical, and behavioral) of diabetes development, (iii) improve diagnosis, (iv) improve understanding of the arc of disease (progression and personal/societal impact), and finally (v) improve treatment.

Marriage contributes to higher obesity risk in China: findings from the China Health and Nutrition Survey

Background

To investigate the association between marriage and the prevalence of overweight and obesity in China.

Methods

We conducted cross-sectional and retrospective cohort analyses using a nationwide sample of 36,310 individuals from the China Health and Nutrition Survey [2004-2015].

Results

The prevalence of overweight and obesity increased from 28.7% to 36.7% and from 8.0% to 14.5% between 2004 and 2015, respectively. The cross-sectional analysis showed that married individuals were at a higher risk of being overweight (OR =2.18; 95% CI, 1.90-2.51) or obese (OR =1.95; 1.57-2.43) than never-married individuals. Divorced/widowed individuals were also at a greater risk of being overweight (OR =1.80; 1.51-2.13) or obese (OR =1.67; 1.28-2.17) than never-married individuals. Retrospective cohort analysis showed that individuals who married during the study were 1.55 (1.13-2.11) times more likely to be overweight than those who remained never-married. Compared to those who remained never-married, individuals who remained married were 1.71 (1.42-2.07) and 1.45 (1.11-1.89) times more likely to be overweight and obese. Individuals who became divorced or widowed were more likely to be overweight (RR =1.59; 1.18-2.15) or obese (RR =1.63; 1.08-2.46) than those who remained never-married. However, the risk of being overweight or obese among those who became divorced or widowed did not differ significantly from the risk among those who remained married.

Conclusions

Marriage contributes to an increased risk of overweight and obesity in China; however, this risk is not significantly reduced by exiting a marriage.

Spatial Analysis of Incidence of Diagnosed Type 2 Diabetes Mellitus and Its Association With Obesity and Physical Inactivity

OBJECTIVES

To investigate the spatial distribution of 10-year incidence of diagnosed type 2 diabetes mellitus (T2DM) and its association with obesity and physical inactivity at a reginal level breakdown.

METHODS

Demographic, behavioral, medical and pharmaceutical and diagnosed T2DM incidence data were collected from a cohort of 232,064 participants who were free of diabetes at enrolment in the 45 and Up Study, conducted in the state of New South Wales (NSW), Australia. We examined the geographical trend and correlation between obesity prevalence, physical inactivity rate and age-and-gender-adjusted cumulative incidence of T2DM, aggregated based on geographical regions.

RESULT

The T2DM incidence, prevalence of obesity and physical inactivity rate at baseline were 6.32%, 20.24%, and 18.7%, respectively. The spatial variation of T2DM incidence was significant (Moran's I=0.52; p<0.01), with the lowest incidence of 2.76% in Richmond Valley-Coastal and the highest of 12.27% in Mount Druitt. T2DM incidence was significantly correlated with the prevalence of obesity (Spearman r=0.62, p<0.001), percentage of participants having five sessions of physical activities or less per week (r=0.79, p<0.001) and percentage of participants walked to work (r=-0.44, p<0.001). The geographical variations in obesity prevalence and physical inactivity rate resembled the geographical variation in the incidence of T2DM.

CONCLUSION

The spatial distribution of T2DM incidence is significantly associated with the geographical prevalence of obesity and physical inactivity rate. Regional campaigns advocating the importance of physical activities in response to the alarming T2DM epidemic should be promoted.

Predicting the diagnosis of HIV and sexually transmitted infections among men who have sex with men using machine learning approaches

OBJECTIVES

We aimed to develop machine learning models and evaluate their performance in predicting HIV and sexually transmitted infections (STIs) diagnosis based on a cohort of Australian men who have sex with men (MSM).

METHODS

We collected clinical records of 21,273 Australian MSM during 2011-2017. We compared accuracies for predicting HIV and STIs (syphilis, gonorrhoea, chlamydia) diagnosis using four machine learning approaches against a multivariable logistic regression (MLR) model.

RESULTS

Machine learning approaches consistently outperformed MLR. Gradient boosting machine (GBM) achieved the highest area under the receiver operator characteristic curve for HIV (76.3%) and STIs (syphilis, 85.8%; gonorrhoea, 75.5%; chlamydia, 68.0%), followed by extreme gradient boosting (71.1%, 82.2%, 70.3%, 66.4%), random forest (72.0%, 81.9%, 67.2%, 64.3%), deep learning (75.8%, 81.0%, 67.5%, 65.4%) and MLR (69.8%, 80.1%, 67.2%, 63.2%). GBM models demonstrated the ten greatest predictors collectively explained 62.7-73.6% of variations in predicting HIV/STIs. STIs symptoms, past syphilis infection, age, time living in Australia, frequency of condom use with casual male sexual partners during receptive anal sex and the number of casual male sexual partners in the past 12 months were most commonly identified predictors.

CONCLUSIONS

Machine learning approaches are advantageous over multivariable logistic regression models in predicting HIV/STIs diagnosis.

Moving Health Literacy Research and Practice towards a Vision of Equity, Precision and Transparency

Over the past two decades, health literacy research has gained increasing attention in global health initiatives to reduce health disparities. While it is well-documented that health literacy is associated with health outcomes, most findings are generated from cross-sectional data. Along with the increasing importance of health literacy in policy, there is a lack of specificity and transparency about how to improve health literacy in practice. In this study, we are calling for a shift of current research paradigms from judging health literacy levels towards observing how health literacy skills are developed over the life course and practised in the real world. This includes using a life-course approach, integrating the rationale of precision public health, applying open science practice, and promoting actionable knowledge translation strategies. We show how a greater appreciation for these paradigms promises to advance health literacy research and practice towards an equitable, precise, transparent, and actionable vision.