Risk models and scores for type 2 diabetes: systematic review

The Role of the Gut Microbiota in Coronary Heart Disease

PURPOSE OF REVIEW

This review focuses on recent evidence examining the role gut microbiota play in coronary heart disease. It also provides a succinct overview of current and future therapies targeting the gut microbiota for coronary heart disease risk reduction.

RECENT FINDINGS

A consensus has been reached that differences exist in the gut microbiotas of patients with coronary heart disease. Studies have shown that the gut microbiota is associated with obesity, diabetes, dyslipidemia, and hypertension, which are risk factors for coronary heart disease. The gut microbiota is involved in mediating basic metabolic processes, such as cholesterol metabolism, uric acid metabolism, oxidative stress, and inflammatory reactions, through its metabolites, which can induce the development of atherosclerosis and coronary heart disease. Interfering with the composition of gut microbiota, supplementing probiotics, and fecal donation are active areas of research to potentially prevent and treat coronary heart disease. Gut microbiota are causally associated with coronary heart disease. We analyzed the gut microbiota's effects on risk factors for coronary heart disease and studied the effects of gut microbiota metabolites on coronary heart disease. Gut microbiota is a potential target for preventing and treating coronary heart disease.

Identifying Africans with undiagnosed diabetes: Fasting plasma glucose is similar to the hemoglobin A1C updated Atherosclerosis Risk in Communities diabetes prediction equation

AIMS

Seventy percent of Africans living with diabetes are undiagnosed. Identifying who should be referred for testing is critical. Therefore we evaluated the ability of the Atherosclerosis Risk in Communities (ARIC) diabetes prediction equation with A1C added (ARIC + A1C) to identify diabetes in 451 African-born blacks living in America (66% male; age 38 ± 10y (mean ± SD); BMI 27.5 ± 4.4 kg/m²).

METHODS

All participants denied a history of diabetes. OGTTs were performed. Diabetes diagnosis required 2-h glucose ≥200 mg/dL. The five non-invasive (Age, parent history of diabetes, waist circumference, height, systolic blood pressure) and four invasive variables (Fasting glucose (FPG), A1C, triglycerides (TG), HDL) were obtained. Four models were tested: Model-1: Full ARIC + A1C equation; Model-2: All five non-invasive variables with one invasive variable excluded at a time; Model-3: All five non-invasive variables with one invasive variable included at a time; Model-4: Each invasive variable singly. Area under the receiver operator characteristic curve (AROC) predicted diabetes. Youden Index identified optimal cut-points.

RESULTS

Diabetes occurred in 7% (30/451). Model-1, the full ARIC + A1C equation, AROC = 0.83. Model-2: With FPG excluded, AROC = 0.77 (P = 0.038), but when A1C, HDL or TG were excluded AROC remained unchanged. Model-3 with all non-invasive variables and FPG alone, AROC=0.87; but with A1C, TG or HDL included AROC declined to ≤0.76. Model-4: FPG as a single predictor, AROC = 0.87. A1C, TG, or HDL as single predictors all had AROC ≤ 0.74. Optimal cut-point for FPG was 100 mg/dL.

CONCLUSIONS

To detect diabetes, FPG performed as well as the nine-variable updated ARIC + A1C equation.

How to optimize the design and implementation of risk prediction tools: focus group with patients with IgA nephropathy

Background

IgA nephropathy (IgAN) is a common type of chronic immune-mediated kidney disease with variable risk of progression to end-stage kidney disease. Risk stratification helps clinicians weight the potential risks and benefits of immunosuppressive therapy for individual patients, and can inform patient-centred communication. No prior research examined barriers of risk predication tools (RPT) specific to IgAN. The purpose of this study was to explore determinants (facilitators, barriers) of RPT use from the patient perspective.

Methods

We conducted a single focus group with English-speaking adults aged 18 or older with biopsy-proven IgAN. We asked about how they would use an IgAN RPT, and how to improve its design and implementation. We analyzed the transcript using constant comparison to inductively derive themes, and complied with qualitative research reporting criteria.

Results

The 5 participants were Caucasian men who varied in age from 35 to 55. The glomerular filtration rate ranged from 29 to 71 mL/min/1.73m², and proteinuria ranged from 0.36 to 1.41 g/d. Participants identified both benefits and harms of the risk score. They said physicians should first ask patients for permission to use it. To make it more useful, participants offered suggestions to enhance RTP design: visual display, information on how to interpret the risk score, risk categories, health implications, modifiable risk factors, multiple scenarios, and comparison with similar patients. They offered additional suggestions to enhance RPT implementation: it should not replace patient-provider discussion, it should be accompanied by self-management education so that patients can take an active role in their health. Participants appreciated information from members of the multidisciplinary team in addition to physicians. Participants also said that physicians should monitor patient emotions or concerns on an ongoing basis.

Conclusions

Patients with IgAN identified numerous ways to enhance the design and use of an RPT. Others could use this information to design and implement RPTs for patients with other conditions, but should employ user-centred design to develop RPTs that address patient preferences.

Disease, Drugs and Dysbiosis: Understanding Microbial Signatures in Metabolic Disease and Medical Interventions

Since the discovery of the potential role for the gut microbiota in health and disease, many studies have gone on to report its impact in various pathologies. These studies have fuelled interest in the microbiome as a potential new target for treating disease Here, we reviewed the key metabolic diseases, obesity, type 2 diabetes and atherosclerosis and the role of the microbiome in their pathogenesis. In particular, we will discuss disease associated microbial dysbiosis; the shift in the microbiome caused by medical interventions and the altered metabolite levels between diseases and interventions. The microbial dysbiosis seen was compared between diseases including Crohn’s disease and ulcerative colitis, non-alcoholic fatty liver disease, liver cirrhosis and neurodegenerative diseases, Alzheimer’s and Parkinson’s. This review highlights the commonalities and differences in dysbiosis of the gut between diseases, along with metabolite levels in metabolic disease vs. the levels reported after an intervention. We identify the need for further analysis using systems biology approaches and discuss the potential need for treatments to consider their impact on the microbiome.

Association of Alcohol Intake With Hypertension in Type 2 Diabetes Mellitus: The ACCORD Trial

Background Heavy alcohol consumption has a well-established association with hypertension. However, doubt persists whether moderate alcohol consumption has a similar link. This relationship is not well-studied in patients with diabetes mellitus. We aimed to describe the association of alcohol consumption with prevalent hypertension in participants in the ACCORD (Action to Control Cardiovascular Risk in Diabetes) trial. Methods and Results Alcohol consumption was categorized as none, light (1-7 drinks/week), moderate (8-14 drinks/week), and heavy (≥15 drinks/week). Blood pressure was categorized using American College of Cardiology/American Heart Association guidelines as normal, elevated blood pressure, stage 1 hypertension, and stage 2 hypertension. Multivariable logistic regression was used to explore the association between alcohol consumption and prevalent hypertension. A total of 10 200 eligible participants were analyzed. Light alcohol consumption was not associated with elevated blood pressure or any stage hypertension. Moderate alcohol consumption was associated with elevated blood pressure, stage 1, and stage 2 hypertension (odds ratio [OR], 1.79; 95% CI, 1.04-3.11, P=0.03; OR, 1.66; 95% CI, 1.05-2.60, P=0.03; and OR, 1.62; 95% CI, 1.03-2.54, P=0.03, respectively). Heavy alcohol consumption was associated with elevated blood pressure, stage 1, and stage 2 hypertension (OR, 1.91; 95% CI, 1.17-3.12, P=0.01; OR, 2.49; 95% CI, 1.03-6.17, P=0.03; and OR, 3.04; 95% CI, 1.28-7.22, P=0.01, respectively). Conclusions Despite prior research, our findings show moderate alcohol consumption is associated with hypertension in patients with type 2 diabetes mellitus and elevated cardiovascular risk. We also note a dose-risk relationship with the amount of alcohol consumed and the degree of hypertension.

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.

A digital biomarker of diabetes from smartphone-based vascular signals

The global burden of diabetes is rapidly increasing, from 451 million people in 2019 to 693 million by 2045¹. The insidious onset of type 2 diabetes delays diagnosis and increases morbidity². Given the multifactorial vascular effects of diabetes, we hypothesized that smartphone-based photoplethysmography could provide a widely accessible digital biomarker for diabetes. Here we developed a deep neural network (DNN) to detect prevalent diabetes using smartphone-based photoplethysmography from an initial cohort of 53,870 individuals (the 'primary cohort'), which we then validated in a separate cohort of 7,806 individuals (the 'contemporary cohort') and a cohort of 181 prospectively enrolled individuals from three clinics (the 'clinic cohort'). The DNN achieved an area under the curve for prevalent diabetes of 0.766 in the primary cohort (95% confidence interval: 0.750-0.782; sensitivity 75%, specificity 65%) and 0.740 in the contemporary cohort (95% confidence interval: 0.723-0.758; sensitivity 81%, specificity 54%). When the output of the DNN, called the DNN score, was included in a regression analysis alongside age, gender, race/ethnicity and body mass index, the area under the curve was 0.830 and the DNN score remained independently predictive of diabetes. The performance of the DNN in the clinic cohort was similar to that in other validation datasets. There was a significant and positive association between the continuous DNN score and hemoglobin A1c (P ≤ 0.001) among those with hemoglobin A1c data. These findings demonstrate that smartphone-based photoplethysmography provides a readily attainable, non-invasive digital biomarker of prevalent diabetes.

Development and validation of a model for predicting incident type 2 diabetes using quantitative clinical data and a Bayesian logistic model: A nationwide cohort and modeling study

BACKGROUND

Obesity is closely related to the development of insulin resistance and type 2 diabetes (T2D). The prevention of T2D has become imperative to stem the rising rates of this disease. Weight loss is highly effective in preventing T2D; however, the at-risk pool is large, and a clinically meaningful metric for risk stratification to guide interventions remains a challenge. The objective of this study is to predict T2D risk using full-information continuous analysis of nationally sampled data from white and black American adults age ≥45 years.

METHODS AND FINDINGS

A sample of 12,043 black (33%) and white individuals from a population-based cohort, REasons for Geographic And Racial Differences in Stroke (REGARDS) (enrolled 2003-2007), was observed through 2013-2016. The mean participant age was 63.12 ± 8.62 years, and 43.7% were male. Mean BMI was 28.55 ± 5.61 kg/m2. Risk factors for T2D regularly recorded in the primary care setting were used to evaluate future T2D risk using Bayesian logistic regression. External validation was performed using 9,710 participants (19% black) from Atherosclerotic Risk in Communities (ARIC) (enrolled 1987-1989), observed through 1996-1998. The mean participant age in this cohort was 53.86 ± 5.65 years, and 44.6% were male. Mean BMI was 27.15 ± 4.92 kg/m2. Predictive performance was assessed using the receiver operating characteristic (ROC) curves and area under the curve (AUC) statistics. The primary outcome was incident T2D. By 2016 in REGARDS, there were 1,602 incident cases of T2D. Risk factors used to predict T2D progression included age, sex, race, BMI, triglycerides, high-density lipoprotein, blood pressure, and blood glucose. The Bayesian logistic model (AUC = 0.79) outperformed the Framingham risk score (AUC = 0.76), the American Diabetes Association risk score (AUC = 0.64), and a cardiometabolic disease system (using Adult Treatment Panel III criteria) (AUC = 0.75). Validation in ARIC was robust (AUC = 0.85). Main limitations include the limited generalizability of the REGARDS sample to black and white, older Americans, and no time to diagnosis for T2D.

CONCLUSIONS

Our results show that a Bayesian logistic model using full-information continuous predictors has high predictive discrimination, and can be used to quantify race- and sex-specific T2D risk, providing a new, powerful predictive tool. This tool can be used for T2D prevention efforts including weight loss therapy by allowing clinicians to target high-risk individuals in a manner that could be used to optimize outcomes.

Prediction models for childhood asthma: A systematic review

BACKGROUND

The inability to objectively diagnose childhood asthma before age five often results in both under-treatment and over-treatment of asthma in preschool children. Prediction tools for estimating a child's risk of developing asthma by school-age could assist physicians in early asthma care for preschool children. This review aimed to systematically identify and critically appraise studies which either developed novel or updated existing prediction models for predicting school-age asthma.

METHODS

Three databases (MEDLINE, Embase and Web of Science Core Collection) were searched up to July 2019 to identify studies utilizing information from children ≤5 years of age to predict asthma in school-age children (6-13 years). Validation studies were evaluated as a secondary objective.

RESULTS

Twenty-four studies describing the development of 26 predictive models published between 2000 and 2019 were identified. Models were either regression-based (n = 21) or utilized machine learning approaches (n = 5). Nine studies conducted validations of six regression-based models. Fifteen (out of 21) models required additional clinical tests. Overall model performance, assessed by area under the receiver operating curve (AUC), ranged between 0.66 and 0.87. Models demonstrated moderate ability to either rule in or rule out asthma development, but not both. Where external validation was performed, models demonstrated modest generalizability (AUC range: 0.62-0.83).

CONCLUSION

Existing prediction models demonstrated moderate predictive performance, often with modest generalizability when independently validated. Limitations of traditional methods have shown to impair predictive accuracy and resolution. Exploration of novel methods such as machine learning approaches may address these limitations for future school-age asthma prediction.

Performance and costs of multiple screening strategies for type 2 diabetes: two population-based studies in Shanghai, China

INTRODUCTION

To compare the performance and the costs of various assumed screening strategies for type 2 diabetes mellitus (T2DM) among Chinese adults, and identify an optimal one for the population.

RESEARCH DESIGN AND METHODS

Two multistage-sampling surveys were conducted in Shanghai, China, in 2009 and 2017. All participants were interviewed, had anthropometry, measured fasting plasma glucose (FPG), hemoglobin A1c (A1c) and/or postprandial glucose. The 1999 WHO diagnostic criteria was used to identify undiagnosed T2DM. A previously developed Chinese risk assessment system and a specific risk assessment system developed in this study were applied to calculate diabetes risk score (DRS) 1 and 2. Optimal screening strategies were selected based on the sensitivity, Youden index and the costs using the 2009 survey data as the training set and the 2017 survey data as the validation set. A twofold cross-validation was also performed.

RESULTS

Of numerous assumed strategies, FPG ≥5.6 mmol/L alone performed well (Youden index of 71.8%) and cost least (US$18.4 for each case detected), followed by the strategy of DRS2 ≥8 combining with FPG ≥5.6 mmol/L (Youden index of 71.7% and US$20.2 per case detected) and the strategy of DRS1 ≥17 combining with FPG ≥5.6 mmol/L (Youden index of 72.0% and US$21.6 per case detected). However, FPG alone resulted in more subjects requiring oral glucose tolerance test (OGTT) than did combining with DRS. The strategy of FPG ≥5.6 mmol/L combining with A1c ≥4.7% achieved a Youden index of 72.1%, but had a cost as high as US$48.8 for each case identified. Twofold cross-validation also supported the use of FPG alone, but with an optimal cut-off of 6.1 mmol/L.

CONCLUSIONS

Our results support the use of FPG alone in T2DM screening in Chinese adults. DRS may be used combining with FPG in populations with available electronic health records to reduce the number of OGTT and save costs of screening.

Lifestyle behavior and the risk of type 2 diabetes in the Seguimiento Universidad de Navarra (SUN) cohort

BACKGROUND AND AIMS

We prospectively assessed the association between a healthy lifestyle score (HLS) and the risk of type 2 diabetes mellitus (T2DM) in a Mediterranean cohort.

METHODS AND RESULTS

We followed up 11,005 participants initially free of diabetes diagnosis in the "Seguimiento Universidad de Navarra" (SUN) cohort. We evaluated the influence of lifestyle-related factors based on a score previously related to a lower risk of cardiovascular disease. Only one incident case of T2DM was found among those with a baseline BMI ≤22 kg/m². Therefore, we excluded the BMI item and restricted the analysis to participants with a baseline BMI >22 kg/m². We measured the baseline adherence of a HLS that included: never smoking, physical activity, Mediterranean diet adherence, moderate alcohol consumption, avoidance of binge drinking, low television exposure, taking a short nap, spending time with friends and working hours. Incident cases of T2DM were self-reported by participants and confirmed by a physician. Cox proportional-hazards regression models were fitted to assess the association between HLS and the incidence of T2DM. After a median follow-up of 12 years, 145 incident cases of T2DM were observed. Among participants with a BMI >22 kg/m², the highest category of HLS adherence (7-9 points) showed a significant 46% relatively decreased hazard of T2DM compared with the lowest category (0-4 points) (multivariable adjusted HR: 0.54; 95% CI: 0.30-0.99).

CONCLUSIONS

Higher adherence to a HLS, including some factors not typically studied, may reduce T2DM risk. Preventive efforts should preferentially focus on weight control. However, this score may promote a comprehensive approach to diabetes prevention beyond weight reduction.

A nomogram model for screening the risk of diabetes in a large-scale Chinese population: an observational study from 345,718 participants

Our study is major to establish and validate a simple type||diabetes mellitus (T2DM) screening model for identifying high-risk individuals among Chinese adults. A total of 643,439 subjects who participated in the national health examination had been enrolled in this cross-sectional study. After excluding subjects with missing data or previous medical history, 345,718 adults was included in the final analysis. We used the least absolute shrinkage and selection operator models to optimize feature selection, and used multivariable logistic regression analysis to build a predicting model. The results showed that the major risk factors of T2DM were age, gender, no drinking or drinking/time > 25 g, no exercise, smoking, waist-to-height ratio, heart rate, systolic blood pressure, fatty liver and gallbladder disease. The area under ROC was 0.811 for development group and 0.814 for validation group, and the p values of the two calibration curves were 0.053 and 0.438, the improvement of net reclassification and integrated discrimination are significant in our model. Our results give a clue that the screening models we conducted may be useful for identifying Chinses adults at high risk for diabetes. Further studies are needed to evaluate the utility and feasibility of this model in various settings.

A comparative study of microbial community and functions of type 2 diabetes mellitus patients with obesity and healthy people

The gut microbiota is crucial in the pathogenesis of type 2 diabetes mellitus (T2DM). However, the metabolism of T2DM patients is not well-understood. We aimed to identify the differences on composition and function of gut microbiota between T2DM patients with obesity and healthy people. In this study, 6 T2DM patients with obesity and 6 healthy volunteers were recruited, and metagenomic approach and bioinformatics analysis methods were used to understand the composition of the gut microbiota and the metabolic network. We found a decrease in the abundance of Firmicutes, Oribacterium, and Paenibacillus; this may be attributed to a possible mechanism and biological basis of T2DM; moreover, we identified three critical bacterial taxa, Bacteroides plebeius, Phascolarctobacterium sp. CAG207, and the order Acidaminococcales that can potentially be used for T2DM treatment. We also revealed the composition of the microbiota through functional annotation based on multiple databases and found that carbohydrate metabolism contributed greatly to the pathogenesis of T2DM. This study helps in elucidating the different metabolic roles of microbes in T2DM patients with obesity.

Addressing practical issues of predictive models translation into everyday practice and public health management: a combined model to predict the risk of type 2 diabetes improves incidence prediction and reduces the prevalence of missing risk predictions

INTRODUCTION

Many predictive models for incident type 2 diabetes (T2D) exist, but these models are not used frequently for public health management. Barriers to their application include (1) the problem of model choice (some models are applicable only to certain ethnic groups), (2) missing input variables, and (3) the lack of calibration. While (1) and (2) drives to missing predictions, (3) causes inaccurate incidence predictions. In this paper, a combined T2D risk model for public health management that addresses these three issues is developed.

RESEARCH DESIGN AND METHODS

The combined T2D risk model combines eight existing predictive models by weighted average to overcome the problem of missing incidence predictions. Moreover, the combined model implements a simple recalibration strategy in which the risk scores are rescaled based on the T2D incidence in the target population. The performance of the combined model was compared with that of the eight existing models using data from two test datasets extracted from the Multi-Ethnic Study of Atherosclerosis (MESA; n=1031) and the English Longitudinal Study of Ageing (ELSA; n=4820). Metrics of discrimination, calibration, and missing incidence predictions were used for the assessment.

RESULTS

The combined T2D model performed well in terms of both discrimination (concordance index: 0.83 on MESA; 0.77 on ELSA) and calibration (expected to observed event ratio: 1.00 on MESA; 1.17 on ELSA), similarly to the best-performing existing models. However, while the existing models yielded a large percentage of missing predictions (17%-45% on MESA; 63%-64% on ELSA), this was negligible with the combined model (0% on MESA, 4% on ELSA).

CONCLUSIONS

Leveraging on existing literature T2D predictive models, a simple approach based on risk score rescaling and averaging was shown to provide accurate and robust incidence predictions, overcoming the problem of recalibration and missing predictions in practical application of predictive models.

Benefit of lifestyle-based T2DM prevention is influenced by prediabetes phenotype

The prevention of type 2 diabetes mellitus (T2DM) is a target priority for the WHO and the United Nations and is a key priority in the 2018 Berlin Declaration, which is a global call for early actions related to T2DM. Health-care policies advocate that individuals at high risk of developing T2DM undertake lifestyle modification, irrespective of whether the prediabetes phenotype is defined by hyperglycaemia in the postprandial state (impaired glucose tolerance) and/or fasting state (impaired fasting glucose) or by intermediate HbA_1c levels. However, current evidence indicates that diabetes prevention programmes based on lifestyle change have not been successful in preventing T2DM in individuals with isolated impaired fasting glucose. We propose that further research is needed to identify effective lifestyle interventions for individuals with isolated impaired fasting glucose. Furthermore, we call for the identification of innovative approaches that better identify people with impaired glucose tolerance, who benefit from the currently available lifestyle-based diabetes prevention programmes.

Integrated biomarker for type 2 diabetes mellitus and impaired fasting glucose based on metabolomics analysis using ultra-high performance liquid chromatography quadrupole-Orbitrap high-resolution accurate mass spectrometry

RATIONALE

The prevalence of type 2 diabetes mellitus (T2DM) is increasing but its early diagnosis in high risk populations remains challenging using only fasting blood glucose (FBG) or hemoglobin A1c measurements. It is, therefore, important to search for an integrated biomarker for early diagnosis by determining metabolites associated with the progression of the disease.

METHODS

We recruited 149 participants (51 T2DM patients, 50 individuals with impaired fasting glucose (IFG) and 48 normal glucose tolerance subjects). Their serum samples were analyzed based on a metabolomics approach using ultra-high-performance liquid chromatography quadrupole-Orbitrap high-resolution accurate mass spectrometry (UHPLC/Q-Orbitrap HRMS). The changes in metabolites were profiled and evaluated using univariate and multivariate analyses. Furthermore, a biomarker model was established and the potential biomarkers were evaluated using binary logistic regression analysis and receiver operating characteristic analysis with AUC (area under the curve). Pathway analysis of differential metabolites was performed to reveal the important biological information.

RESULTS

Thirty-eight differential metabolites were identified as significantly associated with T2DM patients and 23 differential metabolites with IFG individuals, mainly amino acids, carnitines, and phospholipids. By evaluating 17 potential biomarkers, we defined a novel integrated biomarker consisting of 2-acetolactate, 2-hydroxy-2,4-pentadienoate, L-arabinose and L-glutamine. The AUCs of the integrated biomarker with IFG and T2DM patients were 0.874 and 0.994, respectively, which showed a superior diagnostic performance. The levels of 2-acetolactate and 2-hydroxy-2,4-pentadienoate were strongly positively correlated with FBG, while L-glutamine and L-arabinose were strongly negatively associated with FBG. After pathway analysis, it was suggested that the majority of the influenced metabolic pathways associated with diabetes referred to amino acid metabolism.

CONCLUSIONS

The integrated biomarker could diagnose IFG and T2DM with a superior diagnostic performance. This finding provides support for novel biomarkers in the diagnosis and treatment of diabetes.

Association of the Dietary-Based Diabetes-Risk Score (DDS) with the risk of gestational diabetes mellitus in the Seguimiento Universidad de Navarra (SUN) project

It is crucial to identify people at risk for type 2 diabetes mellitus (T2DM) and gestational diabetes mellitus (GDM) to implement preventive interventions in order to address these pandemics. A simple score exclusively based on dietary components, the Dietary-Based Diabetes-Risk Score (DDS) showed a strong inverse association with incident T2DM. The objective was to assess the association between DDS and the risk of GDM in a cohort of Spanish university graduates. The 'Seguimiento Universidad de Navarra' project is a prospective and dynamic cohort which included data of 3455 women who notified pregnancies between 1999 and 2012. The diagnosis of GDM is self-reported and further confirmed by physicians. A validated 136-item semi-quantitative FFQ was used to assess pre-gestational dietary habits. The development of the DDS was aimed to quantify the association between the adherence to this a priori dietary score and T2DM incidence. The score exclusively included dietary components (nine food groups with reported inverse associations with T2DM incidence and three food groups which reported direct associations with T2DM). Three categories of adherence to the DDS were assessed: low (11-24), intermediate (25-39) and high (40-60). The upper category showed an independent inverse association with the risk of incident GDM compared with the lowest category (multivariate-adjusted OR 0·48; 95 % CI 0·24, 0·99; P for linear trend: 0·01). Several sensitivity analyses supported the robustness of these results. These results reinforce the importance of pre-gestational dietary habits for reducing GDM and provide a brief tool to practically assess the relevant dietary habits in clinical practice.

Logistic regression has similar performance to optimised machine learning algorithms in a clinical setting: application to the discrimination between type 1 and type 2 diabetes in young adults

BACKGROUND

There is much interest in the use of prognostic and diagnostic prediction models in all areas of clinical medicine. The use of machine learning to improve prognostic and diagnostic accuracy in this area has been increasing at the expense of classic statistical models. Previous studies have compared performance between these two approaches but their findings are inconsistent and many have limitations. We aimed to compare the discrimination and calibration of seven models built using logistic regression and optimised machine learning algorithms in a clinical setting, where the number of potential predictors is often limited, and externally validate the models.

METHODS

We trained models using logistic regression and six commonly used machine learning algorithms to predict if a patient diagnosed with diabetes has type 1 diabetes (versus type 2 diabetes). We used seven predictor variables (age, BMI, GADA islet-autoantibodies, sex, total cholesterol, HDL cholesterol and triglyceride) using a UK cohort of adult participants (aged 18-50 years) with clinically diagnosed diabetes recruited from primary and secondary care (n = 960, 14% with type 1 diabetes). Discrimination performance (ROC AUC), calibration and decision curve analysis of each approach was compared in a separate external validation dataset (n = 504, 21% with type 1 diabetes).

RESULTS

Average performance obtained in internal validation was similar in all models (ROC AUC ≥ 0.94). In external validation, there were very modest reductions in discrimination with AUC ROC remaining ≥ 0.93 for all methods. Logistic regression had the numerically highest value in external validation (ROC AUC 0.95). Logistic regression had good performance in terms of calibration and decision curve analysis. Neural network and gradient boosting machine had the best calibration performance. Both logistic regression and support vector machine had good decision curve analysis for clinical useful threshold probabilities.

CONCLUSION

Logistic regression performed as well as optimised machine algorithms to classify patients with type 1 and type 2 diabetes. This study highlights the utility of comparing traditional regression modelling to machine learning, particularly when using a small number of well understood, strong predictor variables.

Application of Artificial Intelligence in Diabetes Education and Management: Present Status and Promising Prospect

Despite the rapid development of science and technology in healthcare, diabetes remains an incurable lifelong illness. Diabetes education aiming to improve the self-management skills is an essential way to help patients enhance their metabolic control and quality of life. Artificial intelligence (AI) technologies have made significant progress in transforming available genetic data and clinical information into valuable knowledge. The application of AI tech in disease education would be extremely beneficial considering their advantages in promoting individualization and full-course education intervention according to the unique pictures of different individuals. This paper reviews and discusses the most recent applications of AI techniques to various aspects of diabetes education. With the information and evidence collected, this review attempts to provide insight and guidance for the development of prospective, data-driven decision support platforms for diabetes management, with a focus on individualized patient management and lifelong educational interventions.

Agreement between Type 2 Diabetes Risk Scales in a Caucasian Population: A Systematic Review and Report

Early detection of people with undiagnosed type 2 diabetes (T2D) is an important public health concern. Several predictive equations for T2D have been proposed but most of them have not been externally validated and their performance could be compromised when clinical data is used. Clinical practice guidelines increasingly incorporate T2D risk prediction models as they support clinical decision making. The aims of this study were to systematically review prediction scores for T2D and to analyze the agreement between these risk scores in a large cross-sectional study of white western European workers. A systematic review of the PubMed, CINAHL, and EMBASE databases and a cross-sectional study in 59,042 Spanish workers was performed. Agreement between scores classifying participants as high risk was evaluated using the kappa statistic. The systematic review of 26 predictive models highlights a great heterogeneity in the risk predictors; there is a poor level of reporting, and most of them have not been externally validated. Regarding the agreement between risk scores, the DETECT-2 risk score scale classified 14.1% of subjects as high-risk, FINDRISC score 20.8%, Cambridge score 19.8%, the AUSDRISK score 26.4%, the EGAD study 30.3%, the Hisayama study 30.9%, the ARIC score 6.3%, and the ITD score 3.1%. The lowest agreement was observed between the ITD and the NUDS study derived score (κ = 0.067). Differences in diabetes incidence, prevalence, and weight of risk factors seem to account for the agreement differences between scores. A better agreement between the multi-ethnic derivate score (DETECT-2) and European derivate scores was observed. Risk models should be designed using more easily identifiable and reproducible health data in clinical practice.

Comparative analysis of screening models for undiagnosed diabetes in Mexico

BACKGROUND

It is estimated that 37% of Mexican adults have undiagnosed diabetes, and are therefore at high risk of developing the severe and devastating complications associated to it. In recent years, a variety of screening tools based on the characteristics of the adult Mexican population have been proposed in order to reduce the negative effects of the disease.

OBJECTIVES

To assess the performance of screening models to diagnose diabetes in the Mexican adult population and to propose a screening model based on HbA1c measurements.

MATERIALS AND METHODS

Data from the 2016 Halfway National Health and Nutrition Survey (NHNS) were used to assess the screening models and to develop and validate the proposed 2016 NHNS model, built using a multivariate logistic regression model. Explanatory variables included in the 2016 NHNS 2016 model were selected through a stepwise backward procedure, using sensitivity and specificity as performance indicators.

RESULTS

Of the screening models assessed, only the model based on the 2006 NHNS survey showed a performance consistent with previous reports. The proposed 2016 NHNS model included age, waist circumference, and systolic blood pressure as explanatory variables and showed a sensitivity of 0.72 and a specificity of 0.80 in the validation data set.

CONCLUSIONS

Age, waist circumference, and systolic blood pressure are variables of special importance for early detection of undiagnosed diabetes in Mexican adults. Based on the consistent performance of the 2006 NHNS model in different data sets, its use as a screening tool for adults with undiagnosed diabetes in Mexico is recommended.

FINDRISC in Latin America: a systematic review of diagnosis and prognosis models

This review aimed to assess whether the FINDRISC, a risk score for type 2 diabetes mellitus (T2DM), has been externally validated in Latin America and the Caribbean (LAC). We conducted a systematic review following the CHARMS (CHecklist for critical Appraisal and data extraction for systematic Reviews of prediction Modelling Studies) framework. Reports were included if they validated or re-estimated the FINDRISC in population-based samples, health facilities or administrative data. Reports were excluded if they only studied patients or at-risk individuals. The search was conducted in Medline, Embase, Global Health, Scopus and LILACS. Risk of bias was assessed with the PROBAST (Prediction model Risk of Bias ASsessment Tool) tool. From 1582 titles and abstracts, 4 (n=7502) reports were included for qualitative summary. All reports were from South America; there were slightly more women, and the mean age ranged from 29.5 to 49.7 years. Undiagnosed T2DM prevalence ranged from 2.6% to 5.1%. None of the studies conducted an independent external validation of the FINDRISC; conversely, they used the same (or very similar) predictors to fit a new model. None of the studies reported calibration metrics. The area under the receiver operating curve was consistently above 65.0%. All studies had high risk of bias. There has not been any external validation of the FINDRISC model in LAC. Selected reports re-estimated the FINDRISC, although they have several methodological limitations. There is a need for big data to develop-or improve-T2DM diagnostic and prognostic models in LAC. This could benefit T2DM screening and early diagnosis.

The triglyceride-glucose index, a predictor of type 2 diabetes development: A retrospective cohort study

AIMS

The triglycerides-glucose (TyG) index, the product of fasting plasma glucose (FPG) and triglycerides (TG) is a novel index. Many previous studies have reported that the TyG index might be a strong predictor of incident type 2 diabetes. We determined whether the TyG index could be a useful predictor for diabetes diagnosis and compared it to the FPG and TG as predictors of type 2 diabetes.

METHODS

A total of 617 subjects without baseline diabetes were examined and followed up for a median period of 9.2 years. We performed a mixed effect cox regression analysis to evaluate the risk of developing diabetes across the quartiles of the TyG index, calculated as ln[triglyceride (mg/dl)×FPG (mg/dl)/2], and plotted a receiver operating characteristic (ROC) curve to assess discrimination among TyG, FPG and TG.

RESULTS

During 4,871.56 person-years of follow-up, there were 163 incident cases of diabetes. The risk of diabetes increased across the quartiles of the TyG index. Those in the highest quartile of TyG had a higher risk of developing diabetes (adjusted HR 3.38 95% CI 2.38-4.8, ptrend<0.001) than those in the lowest quartile. The area under the curve (AUC) of the ROC plots were 0.79 (95% CI 0.74-0.83) for FPG, 0.64 (95% CI 0.60-0.69) for TyG and 0.59 (95% CI 0.54-0.64) for TG.

CONCLUSION

The TyG index was significantly associated with risk of incident diabetes and could be a valuable biomarker of developing diabetes. However, FPG appeared to be a more robust predictor of diabetes.

Evaluating the Performance of the Indian Diabetes Risk Score in Different Ethnic Groups

Aim: To evaluate the performance of Madras Diabetes Research Foundation-Indian Diabetes Risk Score (MDRF-IDRS) in different ethnic groups, including Indians, Hispanic, non-Hispanic whites, non-Hispanic blacks, and other American. Methods: The MDRF-IDRS is calculated based on a risk equation that includes age, waist circumference, family history of diabetes, and physical activity. The National Health and Nutrition Examination Survey data on American and Chennai Urban Rural Epidemiology Study data on Indians were used in this study. Study participants aged ≥20 years with and without type 2 diabetes were included. Performance of the MDRF-IDRS was assessed using sensitivity, specificity, positive predictive value, negative predictive value, and the area under the receiver operating characteristic curve (AUC) measures within each ethnic group. IDRSs' performance was then compared with existing noninvasive American diabetes risk scores. Results: Total number of participants included was 11,035 (2292 Indians and 8743 Americans). MDRF-IDRS (cutoff ≥60) performed well in Indians with an AUC, sensitivity, and specificity of 0.73, 80.2%, and 57.3%, respectively. MDRF-IDRS cutoff ≥70 had the highest discriminative performance among Hispanic, non-Hispanic whites, and non-Hispanic blacks with sensitivity and specificity of between 70.1%-86.9% and 61.2%-72.2%, respectively. The AUC for American was between 0.77 and 0.81 with the highest and lowest AUC in non-Hispanic black and non-Hispanic white, respectively. With a smaller number of variables, IDRS showed almost the same performance in predicting diabetes among American compared with the existing noninvasive American diabetes risk score. Conclusion: The MDRF-IDRS performs well among Indians and Americans, including Hispanic, non-Hispanic white, non-Hispanic black, and other American. It can be used as a screening tool to help in early diagnosis, management, and optimal control of diabetes mainly in mass screening programs in India and America.

Sociodemographic and lifestyle-related risk factors for identifying vulnerable groups for type 2 diabetes: a narrative review with emphasis on data from Europe

BACKGROUND

Type 2 diabetes mellitus (T2DM) comprises the vast majority of all diabetes cases in adults, with alarmingly increasing prevalence over the past few decades worldwide. A particularly heavy healthcare burden of diabetes is noted in Europe, where 8.8% of the population aged 20-79 years is estimated to have diabetes according to the International Diabetes Federation. Multiple risk factors are implicated in the pathogenesis of T2DM with complex underlying interplay and intricate gene-environment interactions. Thus, intense research has been focused on studying the role of T2DM risk factors and on identifying vulnerable groups for T2DM in the general population which can then be targeted for prevention interventions.

METHODS

For this narrative review, we conducted a comprehensive search of the existing literature on T2DM risk factors, focusing on studies in adult cohorts from European countries which were published in English after January 2000.

RESULTS

Multiple lifestyle-related and sociodemographic factors were identified as related to high T2DM risk, including age, ethnicity, family history, low socioeconomic status, obesity, metabolic syndrome and each of its components, as well as certain unhealthy lifestyle behaviors. As Europe has an increasingly aging population, multiple migrant and ethnic minority groups and significant socioeconomic diversity both within and across different countries, this review focuses not only on modifiable T2DM risk factors, but also on the impact of pertinent demographic and socioeconomic factors.

CONCLUSION

In addition to other T2DM risk factors, low socioeconomic status can significantly increase the risk for prediabetes and T2DM, but is often overlooked. In multinational and multicultural regions such as Europe, a holistic approach, which will take into account both traditional and socioeconomic/socioecological factors, is becoming increasingly crucial in order to implement multidimensional public health programs and integrated community-based interventions for effective T2DM prevention.

Logistic regression was as good as machine learning for predicting major chronic diseases

OBJECTIVE

To evaluate the performance of machine learning (ML) algorithms and to compare them with logistic regression for the prediction of risk of cardiovascular diseases (CVDs), chronic kidney disease (CKD), diabetes (DM), and hypertension (HTN) and in a prospective cohort study using simple clinical predictors.

STUDY DESIGN AND SETTING

We conducted analyses in a population-based cohort study in Asian adults (n = 6,762). Five different ML models were considered-single-hidden-layer neural network, support vector machine, random forest, gradient boosting machine, and k-nearest neighbor-and were compared with standard logistic regression.

RESULTS

The incidences at 6 years of CVD, CKD, DM, and HTN cases were 4.0%, 7.0%, 9.2%, and 34.6%, respectively. Logistic regression reached the highest area under the receiver operating characteristic curve for CKD (0.905 [0.88, 0.93]) and DM (0.768 [0.73, 0.81]) predictions. For CVD and HTN, the best models were neural network (0.753 [0.70, 0.81]) and support vector machine (0.780 [0.747, 0.812]), respectively. However, the differences with logistic regression were small (less than 1%) and nonsignificant. Logistic regression, gradient boosting machine, and neural network were systematically ranked among the best models.

CONCLUSION

Logistic regression yields as good performance as ML models to predict the risk of major chronic diseases with low incidence and simple clinical predictors.

The Causal Relationship of Circulating Triglyceride and Glycated Hemoglobin: A Mendelian Randomization Study

CONTEXT

The association between circulating triglyceride (TG) and glycated hemoglobin A1c (HbA1c), a biomarker for type 2 diabetes, has been widely addressed, but the causal direction of the relationship is still ambiguous.

OBJECTIVE

To confirm the causal relationship between TG and HbA1c by using bidirectional and 2-step Mendelian randomization (MR) approaches.

METHODS

We carried out a bidirectional MR approach using the summarized results from the public database to examine any potential causal effects between serum TG and HbA1c in 16 000 individuals of the Taiwan Biobank cohort. We used the MR estimate and the MR inverse variance-weighted method to reveal that relationship between TG and HbA1c. To further determine whether the DNA methylation at specific sequences mediate the causal pathway between TG and HbA1c, using the 2-step MR approach.

RESULTS

We identified that a single-unit increase in TG measured via log transformation of mg/dL data was associated with a significant increase of 10 units of HbA1c (95% CI = 1.05-18.95, P = 0.029). In contrast, the genetic determinants of HbA1c do not contribute to the amount of circulating TG (beta = 1.75, 95% CI = -11.50 to 14.90). Sensitivity analyses, included the weighted-median approach and MR-Egger regression, were performed to confirm no pleiotropic effect among these instrumental variables. Furthermore, we identified the genetic variant, rs1823200, is associated with both methylation of the CpG site adjacent to CADPS gene and HbA1c level.

CONCLUSION

Our study suggests that higher circulating TG can have an affect on genomic methylation status, ultimately causing elevated level of circulating HbA1c.

Validation of Seven Type 2 Diabetes Mellitus Risk Scores in a Population-Based Cohort: The CoLaus Study

AIM

To assess the validity of seven type 2 diabetes mellitus (T2DM) risk scores in predicting the 10-year incidence of T2DM in a Swiss population-based study.

METHODS

The prospective study included 5131 participants (55% women, age range 35 to 75 years) living in Lausanne, Switzerland. The baseline survey was conducted between 2003 and 2006, and the average follow-up was 10.9 years. Five clinically-based scores (the Balkau, Kahn clinical, Griffin, Swiss Diabetes Association [SDAS], and Finnish Diabetes Risk Score [FINDRISC]) and two clinically and biologically based scores (the Kahn CB and Wilson) were tested.

RESULTS

405 (7.9%) participants developed T2DM. The overall prevalence of participants at high risk ranged from 13.7% for the Griffin score to 43.3% for the Balkau score. The prevalence of participants at high risk among those who developed T2DM ranged from 34.6% for the Griffin score to 82.0% for the Kahn CB score. The Kahn CB score had the highest area under the ROC (value and 95% confidence interval: 0.866 [0.849-0.883]), followed by the FINDRISC (0.818 [0.798-0.838]), while the Griffin score had the lowest (0.740 [0.718-0.762]). Sensitivities and specificities were above 70%, except for the Griffin and the Kahn C scores (for sensitivity) and the Balkau score (for specificity). The numbers needed to screen ranged from 15.5 for the Kahn CB score to 36.7 for the Griffin score.

CONCLUSION

The Kahn CB and the FINDRISC scores performed the best out of all the scores. The FINDRISC score could be used in an epidemiological setting, while the need for blood sampling for the Kahn CB score restricts its use to a more clinical setting.

Changes in metabolic syndrome and its components and the risk of type 2 diabetes: a nationwide cohort study

We investigated the relationship of changes in Metabolic syndrome (MetS) and its components with the risk of type 2 diabetes (T2D) in South Korea. Records of 10,806,716 adults aged ≥ 20 years without a history of T2D between 2009 and 2015 were retrieved from database of the South Korean National Health Insurance Service and analyzed. Changes in metabolic components were monitored over a two-year period with follow-up occurring at an average of 4.087 years. During the follow-up period, 848,859 individuals were diagnosed with T2D. The risk of diabetes was lowered with a decrease in the number of MetS components at baseline and the second visit (p for trend <0.0001). Multivariable-adjusted HRs for incident diabetes were 0.645 among individuals with reduced number of MetS components, 0.54 for those with improvement in elevated fasting glucose, 0.735 for those with improvement in elevated triglycerides, 0.746 for those with improvement in elevated blood pressure, 0.763 for those with improvement in reduced HDL-cholesterol, and 0.92 for those with improvement in abdominal obesity compared with those manifesting them at both time points. In conclusion, changes in metabolic syndrome and its components were significantly associated with the development of T2D. Improvement in MetS and its components attenuated the risk of diabetes.

Predicting diabetes clinical outcomes using longitudinal risk factor trajectories

BACKGROUND

The ubiquity of electronic health records (EHR) offers an opportunity to observe trajectories of laboratory results and vital signs over long periods of time. This study assessed the value of risk factor trajectories available in the electronic health record to predict incident type 2 diabetes.

STUDY DESIGN AND METHODS

Analysis was based on a large 13-year retrospective cohort of 71,545 adult, non-diabetic patients with baseline in 2005 and median follow-up time of 8 years. The trajectories of fasting plasma glucose, lipids, BMI and blood pressure were computed over three time frames (2000-2001, 2002-2003, 2004) before baseline. A novel method, Cumulative Exposure (CE), was developed and evaluated using Cox proportional hazards regression to assess risk of incident type 2 diabetes. We used the Framingham Diabetes Risk Scoring (FDRS) Model as control.

RESULTS

The new model outperformed the FDRS Model (.802 vs .660; p-values <2e-16). Cumulative exposure measured over different periods showed that even short episodes of hyperglycemia increase the risk of developing diabetes. Returning to normoglycemia moderates the risk, but does not fully eliminate it. The longer an individual maintains glycemic control after a hyperglycemic episode, the lower the subsequent risk of diabetes.

CONCLUSION

Incorporating risk factor trajectories substantially increases the ability of clinical decision support risk models to predict onset of type 2 diabetes and provides information about how risk changes over time.

Diagnostic accuracy of the Finnish Diabetes Risk Score for the prediction of undiagnosed type 2 diabetes, prediabetes, and metabolic syndrome in the Lebanese University

BACKGROUND

Risk scores were mainly proved to predict undiagnosed type 2 diabetes mellitus (UT2DM) in a non-invasive manner and to guide earlier clinical treatment. The objective of the present study was to assess the performance of the Finnish Diabetes Risk Score (FINDRISC) for detecting three outcomes: UT2DM, prediabetes, and the metabolic syndrome (MS).

METHODS

This was a prospective, cross-sectional study during which employees aged between 30 and 64, with no known diabetes and working within the faculties of the Lebanese University (LU) were conveniently recruited. Participants completed the FINDRISC questionnaire and their glucose levels were examined using both fasting blood glucose (FBG) and oral glucose tolerance tests (OGTT). Furthermore, they underwent lipid profile tests with anthropometry.

RESULTS

Of 713 subjects, 397 subjects (55.2% female; 44.8% male) completed the blood tests and thus were considered as the sample population. 7.6% had UT2DM, 22.9% prediabetes and 35.8% had MS, where men had higher prevalence than women for these 3 outcomes (P = 0.001, P = 0.003 and P = 0.001) respectively. The AUROC value with 95% Confidence Interval (CI) for detecting UT2DM was 0.795 (0.822 in men and 0.725 in women), 0.621(0.648 in men and 0.59 in women) for prediabetes and 0.710 (0.734 in men and 0.705 in women) for MS. The correspondent optimal cut-off point for UT2DM was 11.5 (sensitivity = 83.3% and specificity = 61.3%), 9.5 for prediabetes (sensitivity = 73.6% and specificity = 43.1%) and 10.5 (sensitivity = 69.7%; specificity = 56.5%) for MS.

CONCLUSION

The FINDRISC can be considered a simple, quick, inexpensive, and non-invasive instrument to use in a Lebanese community of working people who are unaware of their health status and who usually report being extremely busy because of their daily hectic work for the screening of UT2DM and MS. However, it poorly screens for prediabetes in this context.

Heritability and Genetics of Type 2 Diabetes Mellitus in Sub-Saharan Africa: A Systematic Review and Meta-Analysis

OBJECTIVES

Sub-Saharan Africa (SSA) is observing an accelerating prevalence rate of type 2 diabetes mellitus (T2DM) influenced by gene-environment interaction of modifiable and nonmodifiable factors. We conducted a systematic review and meta-analysis on the heritability and genetic risk of T2DM in SSA.

METHODS

We reviewed all published articles on T2DM in SSA between January 2000 and December 2019 and available in PubMed, Scopus, and Web of Science. Studies that reported on the genetics and/or heritability of T2DM or indicators of glycaemia were included. Data extracted included the study design, records of family history, pattern and characteristics of inheritance, genetic determinants, and effects estimates.

RESULTS

The pattern and characteristics of T2DM heritability in SSA are preference for maternal aggregation, higher among first degree compared to second-degree relatives; early age-onset (<50 years), and inherited abnormalities of beta-cell function/mass. The overall prevalence of T2DM was 28.2% for the population with a positive family history (PFH) and 11.2% for the population with negative family history (NFH). The pooled odds ratio of the impact of PFH on T2DM was 3.29 (95% CI: 2.40-4.52). Overall, 28 polymorphisms in 17 genes have been investigated in relation with T2DM in SSA. Almost all studies used the candidate gene approach with most (45.8%) of genetic studies published between 2011 and 2015. Polymorphisms in ABCC8, Haptoglobin, KCNJ11, ACDC, ENPP1, TNF-α, and TCF7L2 were found to be associated with T2DM, with overlapping effect on specific cardiometabolic traits. Genome-wide studies identified ancestry-specific signals (AGMO-rs73284431, VT11A-rs17746147, and ZRANB3) and TCF7L2-rs7903146 as the only transferable genetic risk variants to SSA population. TCF7L2-rs7903146 polymorphism was investigated in multiple studies with consistent effects and low-moderate statistical heterogeneity. Effect sizes were modestly strong [odds ratio = 6.17 (95% CI: 2.03-18.81), codominant model; 2.27 (95% CI: 1.50-3.44), additive model; 1.75 (95% CI: 1.18-2.59), recessive model]. Current evidence on the heritability and genetic markers of T2DM in SSA populations is limited and largely insufficient to reliably inform the genetic architecture of T2DM across SSA regions.

Sex-Specific Associations of Circulating Uric Acid with Risk of Diabetes Incidence: A Population-Based Cohort Study from Sweden

OBJECTIVE

To explore the longitudinal, as well as sex-specific, associations between circulating uric acid (UA) and diabetes incidence.

METHODS

A cohort study of the Malmö Diet Cancer-cardiovascular Cohort (Malmö, Sweden) consisting of 3140 individuals without diabetes at baseline, was followed up until the end of 2018. Incident diabetes cases were identified by linking to local and national diabetes registers. Cox proportional hazard regression was used to assess plasma UA levels in relation to diabetes incidence with adjustment for established confounders.

RESULTS

At baseline, with increasing levels of UA, subjects were more likely to be older and have significantly higher body mass index, waist circumference, triglycerides, C-reactive protein, fasting glucose and 2-h plasma glucose postoral glucose tolerance test, and lower levels of high-density lipoprotein. During a mean follow-up period of 8.09±2.24 years, 315 (10.0%) participants developed diabetes, and diabetes incidence rates were 7.89, 9.48 and 18.11 per 1000 person-years for subjects in the 1st, 2nd, and 3rd tertiles of UA, respectively (log-rank test: p<0.001). With adjustment for potential confounders, elevated UA levels were significantly associated with increased risks of diabetes incidence, with the adjusted hazard ratio (HR) (95% confidence interval) for per standard deviation increment of UA of 1.22 (1.08-1.39, p=0.002). Compared with the 1st tertile of UA, the 3rd tertile showed significantly increased risk of diabetes incidence with the adjusted HR of 1.74 (1.24-2.45, p=0.002), and there was a significant trend between increasing tertiles of UA and diabetes incidence (trend test: p<0.001). Stratified analyses showed that elevated circulating UA levels were independently associated with increased risks of diabetes incidence in men but not in women, although the interaction between sex and UA was not statistically significant.

CONCLUSION

Elevated circulating UA was independently associated with increased risk of diabetes incidence, especially for men.

Can risk be predicted? An umbrella systematic review of current risk prediction models for cardiovascular diseases, diabetes and hypertension

OBJECTIVE

To provide an overview of the currently available risk prediction models (RPMs) for cardiovascular diseases (CVDs), diabetes and hypertension, and to compare their effectiveness in proper recognition of patients at risk of developing these diseases.

DESIGN

Umbrella systematic review.

DATA SOURCES

PubMed, Scopus, Cochrane Library.

ELIGIBILITY CRITERIA

Systematic reviews or meta-analysis examining and comparing performances of RPMs for CVDs, hypertension or diabetes in healthy adult (18-65 years old) population, published in English language.

DATA EXTRACTION AND SYNTHESIS

Data were extracted according to the following parameters: number of studies included, intervention (RPMs applied/assessed), comparison, performance, validation and outcomes. A narrative synthesis was performed. Data were reported according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines.

STUDY SELECTION

3612 studies were identified. After title/abstract screening and removal of duplicate articles, 37 studies met the eligibility criteria. After reading the full text, 13 were deemed relevant for inclusion. Three further papers from the reference lists of these articles were then added.

STUDY APPRAISAL

The methodological quality of the included studies was assessed using the AMSTAR tool.

RISK OF BIAS IN INDIVIDUAL STUDIES

Risk of Bias evaluation was carried out using the ROBIS tool.

RESULTS

Sixteen studies met the inclusion criteria: six focused on diabetes, two on hypertension and eight on CVDs. Globally, prediction models for diabetes and hypertension showed no significant difference in effectiveness. Conversely, some promising differences among prediction tools were highlighted for CVDs. The Ankle-Brachial Index, in association with the Framingham tool, and QRISK scores provided some evidence of a certain superiority compared with Framingham alone.

LIMITATIONS

Due to the significant heterogeneity of the studies, it was not possible to perform a meta-analysis. The electronic search was limited to studies in English and to three major international databases (MEDLINE/PubMed, Scopus and Cochrane Library), with additional works derived from the reference list of other studies; grey literature with unpublished documents was not included in the search. Furthermore, no assessment of potential adverse effects of RPMs was carried out.

CONCLUSIONS

Consistent evidence is available only for CVD prediction: the Framingham score, alone or in combination with the Ankle-Brachial Index, and the QRISK score can be confirmed as the gold standard. Further efforts should not be concentrated on creating new scores, but rather on performing external validation of the existing ones, in particular on high-risk groups. Benefits could be further improved by supplementing existing models with information on lifestyle, personal habits, family and employment history, social network relationships, income and education.

PROSPERO REGISTRATION NUMBER

CRD42018088012.

Predicting long-term type 2 diabetes with support vector machine using oral glucose tolerance test

Diabetes is a large healthcare burden worldwide. There is substantial evidence that lifestyle modifications and drug intervention can prevent diabetes, therefore, an early identification of high risk individuals is important to design targeted prevention strategies. In this paper, we present an automatic tool that uses machine learning techniques to predict the development of type 2 diabetes mellitus (T2DM). Data generated from an oral glucose tolerance test (OGTT) was used to develop a predictive model based on the support vector machine (SVM). We trained and validated the models using the OGTT and demographic data of 1,492 healthy individuals collected during the San Antonio Heart Study. This study collected plasma glucose and insulin concentrations before glucose intake and at three time-points thereafter (30, 60 and 120 min). Furthermore, personal information such as age, ethnicity and body-mass index was also a part of the data-set. Using 11 OGTT measurements, we have deduced 61 features, which are then assigned a rank and the top ten features are shortlisted using minimum redundancy maximum relevance feature selection algorithm. All possible combinations of the 10 best ranked features were used to generate SVM based prediction models. This research shows that an individual’s plasma glucose levels, and the information derived therefrom have the strongest predictive performance for the future development of T2DM. Significantly, insulin and demographic features do not provide additional performance improvement for diabetes prediction. The results of this work identify the parsimonious clinical data needed to be collected for an efficient prediction of T2DM. Our approach shows an average accuracy of 96.80% and a sensitivity of 80.09% obtained on a holdout set.

Machine Learning to Predict the Risk of Incident Heart Failure Hospitalization Among Patients With Diabetes: The WATCH-DM Risk Score

OBJECTIVE

To develop and validate a novel, machine learning-derived model to predict the risk of heart failure (HF) among patients with type 2 diabetes mellitus (T2DM).

RESEARCH DESIGN AND METHODS

Using data from 8,756 patients free at baseline of HF, with <10% missing data, and enrolled in the Action to Control Cardiovascular Risk in Diabetes (ACCORD) trial, we used random survival forest (RSF) methods, a nonparametric decision tree machine learning approach, to identify predictors of incident HF. The RSF model was externally validated in a cohort of individuals with T2DM using the Antihypertensive and Lipid-Lowering Treatment to Prevent Heart Attack Trial (ALLHAT).

RESULTS

Over a median follow-up of 4.9 years, 319 patients (3.6%) developed incident HF. The RSF models demonstrated better discrimination than the best performing Cox-based method (C-index 0.77 [95% CI 0.75-0.80] vs. 0.73 [0.70-0.76] respectively) and had acceptable calibration (Hosmer-Lemeshow statistic χ² = 9.63, P = 0.29) in the internal validation data set. From the identified predictors, an integer-based risk score for 5-year HF incidence was created: the WATCH-DM (Weight [BMI], Age, hyperTension, Creatinine, HDL-C, Diabetes control [fasting plasma glucose], QRS Duration, MI, and CABG) risk score. Each 1-unit increment in the risk score was associated with a 24% higher relative risk of HF within 5 years. The cumulative 5-year incidence of HF increased in a graded fashion from 1.1% in quintile 1 (WATCH-DM score ≤7) to 17.4% in quintile 5 (WATCH-DM score ≥14). In the external validation cohort, the RSF-based risk prediction model and the WATCH-DM risk score performed well with good discrimination (C-index = 0.74 and 0.70, respectively), acceptable calibration (P ≥0.20 for both), and broad risk stratification (5-year HF risk range from 2.5 to 18.7% across quintiles 1-5).

CONCLUSIONS

We developed and validated a novel, machine learning-derived risk score that integrates readily available clinical, laboratory, and electrocardiographic variables to predict the risk of HF among outpatients with T2DM.

Risk scores for type 2 diabetes mellitus in Latin America: a systematic review of population-based studies

AIM

To summarize the evidence on diabetes risk scores for Latin American populations.

METHODS

A systematic review was conducted (CRD42019122306) looking for diagnostic and prognostic models for type 2 diabetes mellitus among randomly selected adults in Latin America. Five databases (LILACS, Scopus, MEDLINE, Embase and Global Health) were searched. type 2 diabetes mellitus was defined using at least one blood biomarker and the reports needed to include information on the development and/or validation of a multivariable regression model. Risk of bias was assessed using the PROBAST guidelines.

RESULTS

Of the 1500 reports identified, 11 were studied in detail and five were included in the qualitative analysis. Two reports were from Mexico, two from Peru and one from Brazil. The number of diabetes cases varied from 48 to 207 in the derivations models, and between 29 and 582 in the validation models. The most common predictors were age, waist circumference and family history of diabetes, and only one study used oral glucose tolerance test as the outcome. The discrimination performance across studies was ~ 70% (range: 66-72%) as per the area under the receiving-operator curve, the highest metric was always the negative predictive value. Sensitivity was always higher than specificity.

CONCLUSION

There is no evidence to support the use of one risk score throughout Latin America. The development, validation and implementation of risk scores should be a research and public health priority in Latin America to improve type 2 diabetes mellitus screening and prevention.

Machine Learning For Tuning, Selection, And Ensemble Of Multiple Risk Scores For Predicting Type 2 Diabetes

Background

This study proposes the use of machine learning algorithms to improve the accuracy of type 2 diabetes predictions using non-invasive risk score systems.

Methods

We evaluated and compared the prediction accuracies of existing non-invasive risk score systems using the data from the REACTION study (Risk Evaluation of Cancers in Chinese Diabetic Individuals: A Longitudinal Study). Two simple risk scores were established on the bases of logistic regression. Machine learning techniques (ensemble methods) were used to improve prediction accuracies by combining the individual score systems.

Results

Existing score systems from Western populations performed worse than the scores from Eastern populations in general. The two newly established score systems performed better than most existing scores systems but a little worse than the Chinese score system. Using ensemble methods with model selection algorithms yielded better prediction accuracy than all the simple score systems.

Conclusion

Our proposed machine learning methods can be used to improve the accuracy of screening the undiagnosed type 2 diabetes and identifying the high-risk patients.

Identifying hotspots of type 2 diabetes risk using general practice data and geospatial analysis: an approach to inform policy and practice

The prevalence of type 2 diabetes (T2D) is increasing worldwide and there is a need to identify communities with a high-risk profile and to develop appropriate primary care interventions. This study aimed to predict future T2D risk and identify community-level geographic variations using general practices data. The Australian T2D risk assessment (AUSDRISK) tool was used to calculate the individual T2D risk scores using 55693 clinical records from 16 general practices in west Adelaide, South Australia, Australia. Spatial clusters and potential 'hotspots' of T2D risk were examined using Local Moran's I and the Getis-Ord Gi* techniques. Further, the correlation between T2D risk and the socioeconomic status of communities were mapped. Individual risk scores were categorised into three groups: low risk (34.0% of participants), moderate risk (35.2% of participants) and high risk (30.8% of participants). Spatial analysis showed heterogeneity in T2D risk across communities, with significant clusters in the central part of the study area. These study results suggest that routinely collected data from general practices offer a rich source of data that may be a useful and efficient approach for identifying T2D hotspots across communities. Mapping aggregated T2D risk offers a novel approach to identifying areas of unmet need.

Importance of Recalibrating Models for Type 2 Diabetes Onset Prediction: Application of the Diabetes Population Risk Tool on the Health and Retirement Study

A timely prediction of type 2 diabetes (T2D) onset is important for early intervention to prevent, or at least postpone, its incidence. Several models to predict T2D onset according to individual risk factors were proposed. However, their practical applicability is limited by the fact that they often perform suboptimally when applied to a different population. A solution to overcome this limitation is model recalibration, which consists in updating the model parameters. The aim of this work is to demonstrate the benefits of T2D predictive model recalibration. For the purpose, we considered as case study the Diabetes Population Risk Tool (DPoRT), originally tuned for the Canadian population, and we applied it to data collected in older Americans in the Health and Retirement Study (HRS). A subset of 30,274 subjects was extracted from HRS and divided into a training (N=24,219) and a test set (N=6,055) stratifying for sex and diabetes incidence. The DPoRT was recalibrated by re-estimating all model coefficients on the training set, and then assessed on the test set by comparing the performance of recalibrated vs original model. Model discriminatory ability and calibration were assessed by the concordance index (C-index) and the expected to observed event probability ratio (E/O), respectively. Results show that the recalibrated DPoRT presents similar discriminatory ability to the original model, with C-index equal to 0.68 vs. 0.67 in men, 0.73 vs. 0.73 in women, and better calibration than the original model, with E/O ratio equal to 0.75 vs. 4.57 in men, 0.81 vs. 2.53 in women. Results confirm that recalibration is a key step to be performed before the application of predictive models to different populations in order to guarantee an accurate prediction of diabetes incidence.

Development and multi-cohort validation of a clinical score for predicting type 2 diabetes mellitus

Background and aims

Many countries lack resources to identify patients at risk of developing Type 2 diabetes mellitus (diabetes). We aimed to develop and validate a diabetes risk score based on easily accessible clinical data.

Methods

Prospective study including 5277 participants (55.0% women, 51.8±10.5 years) free of diabetes at baseline. Comparison with two other published diabetes risk scores (Balkau and Kahn clinical, respectively 5 and 8 variables) and validation on three cohorts (Europe, Iran and Mexico) was performed.

Results

After a mean follow-up of 10.9 years, 405 participants (7.7%) developed diabetes. Our score was based on age, gender, waist circumference, diabetes family history, hypertension and physical activity. The area under the curve (AUC) was 0.772 for our score, vs. 0.748 (p<0.001) and 0.774 (p = 0.668) for the other two. Using a 13-point threshold, sensitivity, specificity, positive and negative predictive values (95% CI) of our score were 60.5 (55.5–65.3), 77.1 (75.8–78.2), 18.0 (16.0–20.1) and 95.9 (95.2–96.5) percent, respectively. Our score performed equally well or better than the other two in the Iranian [AUC 0.542 vs. 0.564 (p = 0.476) and 0.513 (p = 0.300)] and Mexican [AUC 0.791 vs. 0.672 (p<0.001) and 0.778 (p = 0.575)] cohorts. In the European cohort, it performed similarly to the Balkau score but worse than the Kahn clinical [AUC 0.788 vs. 0.793 (p = 0.091) and 0.816 (p<0.001)]. Diagnostic capacity of our score was better than the Balkau score and comparable to the Kahn clinical one.

Conclusion

Our clinically-based score shows encouraging results compared to other scores and can be used in populations with differing diabetes prevalence.

Risk Behavior Not Associated with Self-Perception of PrEP Candidacy: Implications for Designing PrEP Services

In a study of sexually-active HIV-negative men who have sex with men (MSM) in China, we compared behavioral indication for pre-exposure prophylaxis (PrEP) based on risk criteria to self-perception of PrEP candidacy (SPC) and explored factors associated with SPC. Of 708 MSM surveyed, 323 (45.6%) were behaviorally-indicated for PrEP, among whom 42.1% self-perceived as appropriate PrEP candidates. In a multivariable model we found no association between sexual behavior nor HIV risk perception and SPC but found that higher perceived benefits of PrEP, increased frequency of HIV testing, and low condom use self-efficacy were positively-associated with SPC. In a sub-analysis restricted to MSM behaviorally-indicated for PrEP, relationship-factors were also significant. Our findings suggest that PrEP implementers should look beyond risk criteria to consider shared decision-making tools that support individuals to assess whether they are appropriate PrEP candidates based on their existing HIV prevention strategies, sexual health goals, and relationship dynamics.

Risk models and scores for metabolic syndrome: systematic review protocol

INTRODUCTION

Metabolic syndrome 'a clustering of risk factors which includes hypertension central obesity, impaired glucose metabolism with insulin resistance and dyslipidaemia' affects approximately 20%-25% of the global adult population. Individuals with metabolic syndrome have two to threefold risk of developing cardiovascular disease and a fivefold risk of developing developing diabetes and death from all causes. Although there is rapid proliferation of risk scores for predicting the risk of developing metabolic syndrome later in life, yet, these are seldom used in the practice. Therefore, the purpose of this review is to determine the performance of risk models and scores for predicting the metabolic syndrome.

METHODS AND ANALYSIS

Articles will be sought for from electronic databases (MEDLINE, CINAHL, PubMed and Web of Science) as well as the Cochrane Library. Further manual search of reference lists and grey literatures will be conducted. The search will cover from the start of indexing to 3 October 2018. Identified studies will be included if they fulfil the study selection criteria. Quality of studies will be appraised using suitable criteria for the risk models. The risk scores in the final sample of the review will be ranked/prioritised based on previous quality criteria for prognostic risk models. Lastly, the impact of the models will be ascertained by tracking citations on Google Scholar.

ETHICS AND DISSEMINATION

This study does not require formal ethical approval as primary data will not be collected. The results will be disseminated through a peer-reviewed publication and relevant conference presentations.

PROSPERO REGISTRATION NUMBER

CRD42019139326.

Building Risk Prediction Models for Type 2 Diabetes Using Machine Learning Techniques

Introduction

As one of the most prevalent chronic diseases in the United States, diabetes, especially type 2 diabetes, affects the health of millions of people and puts an enormous financial burden on the US economy. We aimed to develop predictive models to identify risk factors for type 2 diabetes, which could help facilitate early diagnosis and intervention and also reduce medical costs.

Methods

We analyzed cross-sectional data on 138,146 participants, including 20,467 with type 2 diabetes, from the 2014 Behavioral Risk Factor Surveillance System. We built several machine learning models for predicting type 2 diabetes, including support vector machine, decision tree, logistic regression, random forest, neural network, and Gaussian Naive Bayes classifiers. We used univariable and multivariable weighted logistic regression models to investigate the associations of potential risk factors with type 2 diabetes.

Results

All predictive models for type 2 diabetes achieved a high area under the curve (AUC), ranging from 0.7182 to 0.7949. Although the neural network model had the highest accuracy (82.4%), specificity (90.2%), and AUC (0.7949), the decision tree model had the highest sensitivity (51.6%) for type 2 diabetes. We found that people who slept 9 or more hours per day (adjusted odds ratio [aOR] = 1.13, 95% confidence interval [CI], 1.03–1.25) or had checkup frequency of less than 1 year (aOR = 2.31, 95% CI, 1.86–2.85) had higher risk for type 2 diabetes.

Conclusion

Of the 8 predictive models, the neural network model gave the best model performance with the highest AUC value; however, the decision tree model is preferred for initial screening for type 2 diabetes because it had the highest sensitivity and, therefore, detection rate. We confirmed previously reported risk factors and also identified sleeping time and frequency of checkup as 2 new potential risk factors related to type 2 diabetes.

Which clinical and biochemical predictors should be used to screen for diabetes in patients with serious mental illness receiving antipsychotic medication? A large observational study

OBJECTIVE

We aimed to investigate which clinical and metabolic tests offer optimal accuracy and acceptability to help diagnose diabetes among a large sample of people with serious mental illness in receipt of antipsychotic medication.

METHODS

A prospective observational study design of biochemical and clinical factors was used. Biochemical measures were fasting glucose, insulin and lipids, oral glucose tolerance testing (OGTT), hemoglobin A1c, and insulin resistance assessed with the homeostatic model (HOMA-IR) were determined in a consecutive cohort of 798 adult psychiatric inpatients receiving antipsychotics. Clinical variables were gender, age, global assessment of functioning (GAF), mental health clinicians' global impression (CGI), duration of severe mental illness, height, weight, BMI and waist/hip ratio. In addition, we calculated the risk using combined clinical predictors using the Leicester Practice Risk Score (LPRS) and the Topics Diabetes Risk Score (TDRS). Diabetes was defined by older criteria (impaired fasting glucose (IFG) or OGTT) as well as2010 criteria (IFG or OGTT or Glycated haemoglobin (HBA1c)) at conventional cut-offs.

RESULTS

Using the older criteria, 7.8% had diabetes (men: 6.3%; women: 10.3%). Using the new criteria, 10.2% had diabetes (men: 8.2%, women: 13.2%), representing a 30.7% increase (p = 0.02) in the prevalence of diabetes. Regarding biochemical predictors, conventional OGTT, IFG, and HbA1c thresholds used to identify newly defined diabetes missed 25%, 50% and 75% of people with diabetes, respectively. The conventional HBA1c cut-point of ≥6.5% (48 mmol/mol) missed 7 of 10 newly defined cases of diabetes while a cut-point of ≥5.7% improved sensitivity from 44.4% to up to 85%. Specific algorithm approaches offered reasonable accuracy. Unfortunately no single clinical factor was able to accurately rule-in a diagnosis of diabetes. Three clinical factors were able to rule-out diabetes with good accuracy namely: BMI, waist/hip ratio and height. A BMI < 30 had a 92% negative predictive value in ruling-out diabetes. Of those not diabetic, 20% had a BMI ≥ 30. However, for complete diagnosis a specific biochemical protocol is still necessary.

CONCLUSIONS

Patients with SMI maintained on antipsychotic medication cannot be reliably screened for diabetes using clinical variables alone. Accurate assessment requires a two-step algorithm consisting of HBA1c ≥5.7% followed by both FG and OGTT which does not require all patients to have OGTT and FG.

Methodological standards for the development and evaluation of clinical prediction rules: a review of the literature

Clinical prediction rules (CPRs) that predict the absolute risk of a clinical condition or future outcome for individual patients are abundant in the medical literature; however, systematic reviews have demonstrated shortcomings in the methodological quality and reporting of prediction studies. To maximise the potential and clinical usefulness of CPRs, they must be rigorously developed and validated, and their impact on clinical practice and patient outcomes must be evaluated. This review aims to present a comprehensive overview of the stages involved in the development, validation and evaluation of CPRs, and to describe in detail the methodological standards required at each stage, illustrated with examples where appropriate. Important features of the study design, statistical analysis, modelling strategy, data collection, performance assessment, CPR presentation and reporting are discussed, in addition to other, often overlooked aspects such as the acceptability, cost-effectiveness and longer-term implementation of CPRs, and their comparison with clinical judgement. Although the development and evaluation of a robust, clinically useful CPR is anything but straightforward, adherence to the plethora of methodological standards, recommendations and frameworks at each stage will assist in the development of a rigorous CPR that has the potential to contribute usefully to clinical practice and decision-making and have a positive impact on patient care.

What do healthcare professionals need to turn risk models for type 2 diabetes into usable computerized clinical decision support systems? Lessons learned from the MOSAIC project

Background

To understand user needs, system requirements and organizational conditions towards successful design and adoption of Clinical Decision Support Systems for Type 2 Diabetes (T2D) care built on top of computerized risk models.

Methods

The holistic and evidence-based CEHRES Roadmap, used to create eHealth solutions through participatory development approach, persuasive design techniques and business modelling, was adopted in the MOSAIC project to define the sequence of multidisciplinary methods organized in three phases, user needs, implementation and evaluation. The research was qualitative, the total number of participants was ninety, about five-seventeen involved in each round of experiment.

Results

Prediction models for the onset of T2D are built on clinical studies, while for T2D care are derived from healthcare registries. Accordingly, two set of DSSs were defined: the first, T2D Screening, introduces a novel routine; in the second case, T2D Care, DSSs can support managers at population level, and daily practitioners at individual level. In the user needs phase, T2D Screening and solution T2D Care at population level share similar priorities, as both deal with risk-stratification. End-users of T2D Screening and solution T2D Care at individual level prioritize easiness of use and satisfaction, while managers prefer the tools to be available every time and everywhere. In the implementation phase, three Use Cases were defined for T2D Screening, adapting the tool to different settings and granularity of information. Two Use Cases were defined around solutions T2D Care at population and T2D Care at individual, to be used in primary or secondary care. Suitable filtering options were equipped with “attractive” visual analytics to focus the attention of end-users on specific parameters and events. In the evaluation phase, good levels of user experience versus bad level of usability suggest that end-users of T2D Screening perceived the potential, but they are worried about complexity. Usability and user experience were above acceptable thresholds for T2D Care at population and T2D Care at individual.

Conclusions

By using a holistic approach, we have been able to understand user needs, behaviours and interactions and give new insights in the definition of effective Decision Support Systems to deal with the complexity of T2D care.

Electronic supplementary material

The online version of this article (10.1186/s12911-019-0887-8) contains supplementary material, which is available to authorized users.