Diabetes risk score: towards earlier detection of type 2 diabetes in general practice

Diabetes prediction model for unbalanced community follow-up data set based on optimal feature selection and scorecard

Objectives

Diabetes is a metabolic disease and early detection is crucial to ensuring a healthy life for people with prediabetes. Community care plays an important role in public health, but the association between community follow-up of key life characteristics and diabetes risk remains unclear. Based on the method of optimal feature selection and risk scorecard, follow-up data of diabetes patients are modeled to assess diabetes risk.

Methods

We conducted a study on the diabetes risk assessment model and risk scorecard using follow-up data from diabetes patients in Haizhu District, Guangzhou, from 2016 to 2023. The raw data underwent preprocessing and imbalance handling. Subsequently, features relevant to diabetes were selected and optimized to determine the optimal subset of features associated with community follow-up and diabetes risk. We established the diabetes risk assessment model. Furthermore, for a comprehensible and interpretable risk expression, the Weight of Evidence transformation method was applied to features. The transformed features were discretized using the quantile binning method to design the risk scorecard, mapping the model's output to five risk levels.

Results

In constructing the diabetes risk assessment model, the Random Forest classifier achieved the highest accuracy. The risk scorecard obtained an accuracy of 85.16%, precision of 87.30%, recall of 80.26%, and an F1 score of 83.27% on the unbalanced research dataset. The performance loss compared to the diabetes risk assessment model was minimal, suggesting that the binning method used for constructing the diabetes risk scorecard is reasonable, with very low feature information loss.

Conclusion

The methods provided in this article demonstrate effectiveness and reliability in the assessment of diabetes risk. The assessment model and scorecard can be directly applied to community doctors for large-scale risk identification and early warning and can also be used for individual self-examination to reduce risk factor levels.

Validation of prevalent diabetes risk scores based on non-invasively measured predictors in Ghanaian migrant and non-migrant populations - The RODAM study

Background

Non-invasive diabetes risk models are a cost-effective tool in large-scale population screening to identify those who need confirmation tests, especially in resource-limited settings.

Aims

This study aimed to evaluate the ability of six non-invasive risk models (Cambridge, FINDRISC, Kuwaiti, Omani, Rotterdam, and SUNSET model) to identify screen-detected diabetes (defined by HbA1c) among Ghanaian migrants and non-migrants.

Study design

A multicentered cross-sectional study.

Methods

This analysis included 4843 Ghanaian migrants and non-migrants from the Research on Obesity and Diabetes among African Migrants (RODAM) Study. Model performance was assessed using the area under the receiver operating characteristic curves (AUC), Hosmer-Lemeshow statistics, and calibration plots.

Results

All six models had acceptable discrimination (0.70 ≤ AUC <0.80) for screen-detected diabetes in the overall/combined population. Model performance did not significantly differ except for the Cambridge model, which outperformed Rotterdam and Omani models. Calibration was poor, with a consistent trend toward risk overestimation for screen-detected diabetes, but this was substantially attenuated by recalibration through adjustment of the original model intercept.

Conclusion

Though acceptable discrimination was observed, the original models were poorly calibrated among populations of African ancestry. Recalibration of these models among populations of African ancestry is needed before use.

Implementation status of prediction models for type 2 diabetes

Although a prediction model is expected to identify individuals who are at a high risk of type 2 diabetes, the implementation status of prediction models has not been well examined. Our review indicates that the implementation of predictive models in practice remains low despite the increase in models being developed.

Changes in Prediabetes Status Among Adults During a 6-Month Randomized Placebo-controlled Supplement Trial With Nutrition and Lifestyle Counselling and 6-Month Follow-up

OBJECTIVES

In this work, we present an exploratory within-trial analysis of the changing prevalence of prediabetes in response to nutrition and lifestyle counselling provided as part of a randomized placebo-controlled supplement trial with follow-up. We aimed to identify factors associated with changing glycemia status.

METHODS

Participants (n=401) in this clinical trial were adults with a body mass index (BMI) of ≥25 kg/m2 and prediabetes (defined by the American Diabetes Association as a fasting plasma glucose [FPG] of 5.6 to 6.9 mmol/L or a glycated hemoglobin [A1C] of 5.7% to 6.4%) within 6 months before trial entry. The trial consisted of a 6-month randomized intervention with 2 dietary supplements and/or placebo. At the same time, all participants received nutrition and lifestyle counselling. This was followed by a 6-month follow-up. Glycemia status was assessed at baseline and at 6 and 12 months.

RESULTS

At baseline, 226 participants (56%) met a threshold for prediabetes, including 167 (42%) with elevated FPG and 155 (39%) with elevated A1C. After the 6-month intervention, the prevalence of prediabetes decreased to 46%, driven by a reduction in prevalence of elevated FPG to 29%. The prevalence of prediabetes then increased to 51% after follow-up. Risk of prediabetes was associated with older age (odds ratio [OR], 1.05; p<0.01), BMI (OR, 1.06; p<0.05), and male sex (OR, 1.81; p=0.01). Participants who reverted to normoglycemia had greater weight loss and lower baseline glycemia.

CONCLUSIONS

Glycemia status can fluctuate over time and improvements can be gained from lifestyle interventions, with certain factors associated with a higher likelihood of reverting to normoglycemia.

Study protocol for development and validation of a single tool to assess risks of stroke, diabetes mellitus, myocardial infarction and dementia: DemNCD-Risk

INTRODUCTION

Current efforts to reduce dementia focus on prevention and risk reduction by targeting modifiable risk factors. As dementia and cardiometabolic non-communicable diseases (NCDs) share risk factors, a single risk-estimating tool for dementia and multiple NCDs could be cost-effective and facilitate concurrent assessments as compared with a conventional single approach. The aim of this study is to develop and validate a new risk tool that estimates an individual's risk of developing dementia and other NCDs including diabetes mellitus, stroke and myocardial infarction. Once validated, it could be used by the public and general practitioners.

METHODS AND ANALYSIS

Ten high-quality cohort studies from multiple countries were identified, which met eligibility criteria, including large representative samples, long-term follow-up, data on clinical diagnoses of dementia and NCDs, recognised modifiable risk factors for the four NCDs and mortality data. Pooled harmonised data from the cohorts will be used, with 65% randomly allocated for development of the predictive model and 35% for testing. Predictors include sociodemographic characteristics, general health risk factors and lifestyle/behavioural risk factors. A subdistribution hazard model will assess the risk factors' contribution to the outcome, adjusting for competing mortality risks. Point-based scoring algorithms will be built using predictor weights, internally validated and the discriminative ability and calibration of the model will be assessed for the outcomes. Sensitivity analyses will include recalculating risk scores using logistic regression.

ETHICS AND DISSEMINATION

Ethics approval is provided by the University of New South Wales Human Research Ethics Committee (UNSW HREC; protocol numbers HC200515, HC3413). All data are deidentified and securely stored on servers at Neuroscience Research Australia. Study findings will be presented at conferences and published in peer-reviewed journals. The tool will be accessible as a public health resource. Knowledge translation and implementation work will explore strategies to apply the tool in clinical practice.

A Data-Driven Approach to Refine Predictions of Differentiated Thyroid Cancer Outcomes: A Prospective Multicenter Study

CONTEXT

The risk stratification of patients with differentiated thyroid cancer (DTC) is crucial in clinical decision making. The most widely accepted method to assess risk of recurrent/persistent disease is described in the 2015 American Thyroid Association (ATA) guidelines. However, recent research has focused on the inclusion of novel features or questioned the relevance of currently included features.

OBJECTIVE

To develop a comprehensive data-driven model to predict persistent/recurrent disease that can capture all available features and determine the weight of predictors.

METHODS

In a prospective cohort study, using the Italian Thyroid Cancer Observatory (ITCO) database (NCT04031339), we selected consecutive cases with DTC and at least early follow-up data (n = 4773; median follow-up 26 months; interquartile range, 12-46 months) at 40 Italian clinical centers. A decision tree was built to assign a risk index to each patient. The model allowed us to investigate the impact of different variables in risk prediction.

RESULTS

By ATA risk estimation, 2492 patients (52.2%) were classified as low, 1873 (39.2%) as intermediate, and 408 as high risk. The decision tree model outperformed the ATA risk stratification system: the sensitivity of high-risk classification for structural disease increased from 37% to 49%, and the negative predictive value for low-risk patients increased by 3%. Feature importance was estimated. Several variables not included in the ATA system significantly impacted the prediction of disease persistence/recurrence: age, body mass index, tumor size, sex, family history of thyroid cancer, surgical approach, presurgical cytology, and circumstances of the diagnosis.

CONCLUSION

Current risk stratification systems may be complemented by the inclusion of other variables in order to improve the prediction of treatment response. A complete dataset allows for more precise patient clustering.

Prevalence and Associations of Type 2 Diabetes Risk and Sociodemographic Factors in Saudi Arabia: A Web-Based Cross-Sectional Survey Study

Type 2 diabetes mellitus (T2DM) is a chronic disease with ever-increasing prevalence worldwide. In our study, we evaluated the prevalence of the risk of developing T2DM in Saudi Arabia and investigated associations between that risk and various sociodemographic characteristics. To those ends, a web-based cross-sectional survey of Saudi nationals without diabetes, all enrolled using snowball sampling, was conducted from January 2021 to January 2022. The risk of developing T2DM was evaluated using a validated risk assessment questionnaire (ARABRISK), and associations of high ARABRISK scores and sociodemographic variables were explored in multivariable logistic regression modeling. Of the 4559 participants, 88.1% were 18 to 39 years old, and 67.2% held a college or university degree. High ARABRISK scores were observed in 7.5% of the sample. Residing in a midsize city versus a large city was associated with a lower ARABRISK risk score (p = 0.007), as were having private instead of governmental insurance (p = 0.005), and being unemployed versus employed (p < 0.001). By contrast, being married (p < 0.001), divorced or widowed (p < 0.001), and/or retired (p < 0.001) were each associated with a higher ARABRISK score. A large representative study is needed to calculate the risk of T2DM among Saudi nationals.

New onset of type 2 diabetes after colorectal cancer diagnosis: Results from three prospective US cohort studies, systematic review, and meta-analysis

BACKGROUND

Limited data indicate that patients with colorectal cancer (CRC) are at higher risk of developing type 2 diabetes (T2D). We prospectively examined the risk of T2D between individuals with and without CRC in three large cohorts and conducted a meta-analysis.

METHODS

We assessed the diagnosis of CRC and T2D among 111,485 women from the Nurses' Health Study, 112,958 women from the Nurses' Health Study II, and 46,581 men from the Health Professionals Follow-up Study. We used multivariable Cox regression with time-varying covariates to calculate the hazard ratio (HR) of T2D in relation to CRC diagnosis. We further performed a systematic review and meta-analysis of cohort studies.

FINDINGS

Up to 36 years of follow-up (6.9 million person-years), we documented 3402 incident CRC cases and 26,469 T2D cases. Compared to non-CRC individuals, those with CRC were more likely to develop T2D (multivariable-adjusted HR 1.20, 95% CI 1.05-1.38). The association was most evident for individuals with fewer risk factors for T2D. In the meta-analysis of seven cohort studies (1,061,744 participants), CRC was associated with higher T2D risk (meta-analysis HR 1.21, 95% CI 1.11-1.31, I² = 57.9%). By CRC duration, a statistically significant association was observed in the first 10 years but not after 10 years of CRC diagnosis (≤5 years, meta-analysis HR 1.32, 95% CI 1.27-1.36; 5.1-10 years, 1.14 [1.04-1.25]; >10 years, 1.14 [0.91-1.37]).

INTERPRETATION

CRC was associated with increased T2D risk, especially in the first ten years after CRC diagnosis. Our findings highlight the importance of T2D prevention for CRC survivorship care.

FUNDING

NHS cohort infrastructure grant (UM1 CA186107), NHS program project grant that funds cancer research (P01 CA87969), NHS II cohort infrastructure grant (U01 CA176726), HPFS cohort infrastructure grant (U01 CA167552) and the Chinese Academy of Medical Sciences Innovation Fund for Medical Sciences (2021-I2M-1-010).

Diabetes precision medicine: plenty of potential, pitfalls and perils but not yet ready for prime time

Rapid advances in technology and data science have the potential to improve the precision of preventive and therapeutic interventions, and enable the right treatment to be recommended, at the right time, to the right person. There are well-described examples of successful precision medicine approaches for monogenic conditions such as specific diets for phenylketonuria, and sulfonylurea treatments for certain types of MODY. However, the majority of chronic diseases are polygenic, and it is unlikely that the research strategies used for monogenic diseases will deliver similar changes to practice for polygenic traits. Type 2 diabetes, for example, is a multifactorial, heterogeneous, polygenic palette of metabolic disorders. In this non-systematic review I highlight limitations of the evidence, and the challenges that need to be overcome prior to implementation of precision medicine in the prevention and management of type 2 diabetes. Most precision medicine approaches are spuriously precise, overly complex and too narrowly focused on predicting blood glucose levels with a limited set of characteristics of individuals rather than the whole person and their context. Overall, the evidence to date is insufficient to justify widespread implementation of precision medicine approaches into routine clinical practice for type 2 diabetes. We need to retain a degree of humility and healthy scepticism when evaluating novel strategies, and to demand that existing evidence thresholds are exceeded prior to implementation.

External validation of non-invasive diabetes score in a 15-year prospective study

BACKGROUND

A novel scoring system called Non-invasive Diabetes Score (NDS) was developed. The model showed prominent discrimination and calibration in the original study population. However, before a new model could be adopted in clinical practice and acquire widespread use, it is necessary to confirm that it also performs well in external validations in different settings of people. The aim of this study was to investigate whether the novel user-friendly score predicting diabetes mellitus (DM) could have satisfying performance in predicting DM in Southwest China in a 15-year prospective cohort study.

METHODS

This prospective cohort study was carried out based on a general Chinese population of 711 individuals from 1992 to 2007. We excluded 24 of them at baseline because they were diabetics. The end point was DM, and the risk was calculated using the model formula.

RESULTS

During a follow-up of 15 years, 74 (10.77%) patients reached the end point. Evaluation of this model in our cohort, with Harrell's C-index of 0.662 (95% CI: 0.600-0.723) for the whole cohort and 0.695 (95% CI: 0.635-0.756) in sensitivity analysis, indicated the possibly helpful discrimination. The calibration capability in our cohort was useful that the observed incidence of diabetes mellitus was near the predicted.

CONCLUSIONS

Our external validation suggested NDS had possibly helpful discrimination and satisfying calibration for predicting DM during 15-year follow-up.

Non-invasive type 2 diabetes risk scores do not identify diabetes when the cause is β-cell failure: The Africans in America study

Background

Emerging data suggests that in sub-Saharan Africa β-cell-failure in the absence of obesity is a frequent cause of type 2 diabetes (diabetes). Traditional diabetes risk scores assume that obesity-linked insulin resistance is the primary cause of diabetes. Hence, it is unknown whether diabetes risk scores detect undiagnosed diabetes when the cause is β-cell-failure.

Aims

In 528 African-born Blacks living in the United States [age 38 ± 10 (Mean ± SE); 64% male; BMI 28 ± 5 kg/m²] we determined the: (1) prevalence of previously undiagnosed diabetes, (2) prevalence of diabetes due to β-cell-failure vs. insulin resistance; and (3) the ability of six diabetes risk scores [Cambridge, Finnish Diabetes Risk Score (FINDRISC), Kuwaiti, Omani, Rotterdam, and SUNSET] to detect previously undiagnosed diabetes due to either β-cell-failure or insulin resistance.

Methods

Diabetes was diagnosed by glucose criteria of the OGTT and/or HbA1c ≥ 6.5%. Insulin resistance was defined by the lowest quartile of the Matsuda index (≤ 2.04). Diabetes due to β-cell-failure required diagnosis of diabetes in the absence of insulin resistance. Demographics, body mass index (BMI), waist circumference, visceral adipose tissue (VAT), family medical history, smoking status, blood pressure, antihypertensive medication, and blood lipid profiles were obtained. Area under the Receiver Operator Characteristics Curve (AROC) estimated sensitivity and specificity of each continuous score. AROC criteria were: Outstanding: >0.90; Excellent: 0.80-0.89; Acceptable: 0.70-0.79; Poor: 0.50-0.69; and No Discrimination: 0.50.

Results

Prevalence of diabetes was 9% (46/528). Of the diabetes cases, β-cell-failure occurred in 43% (20/46) and insulin resistance in 57% (26/46). The β-cell-failure group had lower BMI (27 ± 4 vs. 31 ± 5 kg/m² P < 0.001), lower waist circumference (91 ± 10 vs. 101 ± 10cm P < 0.001) and lower VAT (119 ± 65 vs. 183 ± 63 cm³, P < 0.001). Scores had indiscriminate or poor detection of diabetes due to β-cell-failure (FINDRISC AROC = 0.49 to Cambridge AROC = 0.62). Scores showed poor to excellent detection of diabetes due to insulin resistance, (Cambridge AROC = 0.69, to Kuwaiti AROC = 0.81).

Conclusions

At a prevalence of 43%, β-cell-failure accounted for nearly half of the cases of diabetes. All six diabetes risk scores failed to detect previously undiagnosed diabetes due to β-cell-failure while effectively identifying diabetes when the etiology was insulin resistance. Diabetes risk scores which correctly classify diabetes due to β-cell-failure are urgently needed.

Early prediction of diabetes by applying data mining techniques: A retrospective cohort study

BACKGROUND

Saudi Arabia ranks 7th globally in terms of diabetes prevalence, and its prevalence is expected to reach 45.36% by 2030. The cost of diabetes is expected to increase to 27 billion Saudi riyals in cases where undiagnosed individuals are also documented. Prevention and early detection can effectively address these challenges.

OBJECTIVE

To improve healthcare services and assist in building predictive models to estimate the probability of diabetes in patients.

METHODS

A chart review, which was a retrospective cohort study, was conducted at the National Guard Health Affairs in Riyadh, Saudi Arabia. Data were collected from 5 hospitals using National Guard Health Affairs databases. We used 38 attributes of 21431 patients between 2015 and 2019. The following phases were performed: (1) data collection, (2) data preparation, (3) data mining and model building, and (4) model evaluation and validation. Subsequently, 6 algorithms were compared with and without the synthetic minority oversampling technique.

RESULTS

The highest performance was found in the Bayesian network, which had an area under the curve of 0.75 and 0.71.

CONCLUSION

Although the results were acceptable, they could be improved. In this context, missing data owing to technical issues played a major role in affecting the performance of our model. Nevertheless, the model could be used in prevention, health monitoring programs, and as an automated mass population screening tool without the need for extra costs compared to traditional methods.

Oral glucose tolerance testing as a complement to fasting plasma glucose in screening for type 2 diabetes: population-based cross-sectional analyses of 146 000 health examinations in Västerbotten, Sweden

OBJECTIVE

To assess the effect of adding an oral glucose tolerance test (OGTT) to fasting plasma glucose (FPG) in terms of detection of type 2 diabetes (T2D) and impaired glucose tolerance (IGT).

DESIGN

Retrospective analysis of serial cross-sectional screening study.

SETTING

Population-based health examinations within primary care in Västerbotten County, Sweden.

PARTICIPANTS

Individuals aged 40- 50 and 60 years with participation from 1985 to 2017. Those with previously diagnosed diabetes and FPG≥7 mmol/L were excluded.

PRIMARY AND SECONDARY OUTCOME MEASURES

Prevalence of hyperglycaemia on the OGTT (IGT and T2D defined as 2-hour postload capillary plasma glucose of 8.9-12.1 mmol/L and ≥12.2 mmol/L, respectively). Analyses were further stratified by age, sex and risk factor burden to identify groups at high or low risk of IGT and T2D on testing. The numbers needed to screen (NNS) to prevent one case of T2D through detection and treatment of IGT was estimated, combining prevalence numbers with average progression rates and intervention effects from previous meta-analyses.

RESULTS

The prevalence of IGT ranged from 0.9% (95% CI 0.7% to 1.1%) to 29.6% (95% CI 27.4% to 31.7%), and the prevalence of T2D ranged from 0.06% (95% CI 0.02% to 0.11%) to 7.0% (95% CI 5.9% to 8.3%), depending strongly on age, sex and risk factor burden. The estimated NNS to prevent one case of T2D through detection and lifestyle treatment of IGT ranged from 1332 among 40-year-old men without risk factors, to 39 among 60-year-old women with all risk factors combined.

CONCLUSIONS

The prevalence of hyperglycaemia on OGTT is highly dependent on age, sex and risk factor burden; OGTT should be applied selectively to high-risk groups to avoid unnecessary testing in the general population.

Development and Validation of a Risk Score Screening Tool to Identify People at Risk for Hypertension in Shanghai, China

Purpose

This study aimed to develop a screening tool based on a risk scoring approach that could identify individuals at high risk for hypertension in Shanghai, China.

Methods

A total of 3147 respondents from the 2013 Shanghai Chronic Disease and Risk Factor Surveillance were randomly divided into the derivation group and validation group. The coefficients obtained from multivariable logistic regression were used to assign a score to each variable category. The receiver operating characteristic (ROC) curve was used to find the optimal cut-off point and to evaluate the screening performance.

Results

Age, family history of hypertension, having diabetes, having dyslipidemia, body mass index, and having abdominal obesity contributed to the risk score. The area under the ROC curve was 0.817 (95% CI: 0.797–0.836). The optimal cut-off value of 20 had a sensitivity of 83.4%, and a specificity of 64.3%, demonstrating good performance.

Conclusion

We developed a simple and valid screening tool to identify individuals at risk for hypertension. Early detection could be beneficial for high-risk groups to better manage their conditions and delay the progression of hypertension and related complications.

A systematic review of diabetes risk assessment tools in sub-Saharan Africa

Objectives

To systematically review all current studies on diabetes risk assessment tools used in SSA to diagnose diabetes in symptomatic and asymptomatic patients.

Methods

Tools were identified through a systematic search of PubMed, Ovid, Google Scholar, and the Cochrane Library for articles published from January 2010 to January 2020. The search included articles reporting the use of diabetes risk assessment tool to detect individuals with type 2 diabetes in SSA. A standardized protocol was used for data extraction (registry #177726).

Results

Of the 825 articles identified, 39 articles met the inclusion criteria, and three articles reported tools used in SSA population but developed for the Western population. None was validated in SSA population. All but three articles were observational studies (136 and 58,657 study participants aged between the ages of 15 and 85 years). The Finnish Medical Association risk tool, World Health Organization (WHO) STEPS instrument, General Practice Physical Activity Questionnaire (GPPAQ), Rapid Eating and Activity Assessment for Patients (REAP), and an anthropometric tool were the most frequently used non-invasive tools in SSA. The accuracy of the tools was measured using sensitivity, specificity, or area under the receiver operating curve. The anthropometric predictor variables identified included age, body mass index, waist circumference, positive family of diabetes, and activity levels.

Conclusions

This systematic review demonstrated a paucity of validated diabetes risk assessment tools for SSA. There remains a need for the development and validation of a tool for the rapid identification of diabetes for targeted interventions.

Assessment of a Manual Method versus an Automated, Probability-Based Algorithm to Identify Patients at High Risk for Pharmacogenomic Adverse Drug Outcomes in a University-Based Health Insurance Program

We compared patient cohorts selected for pharmacogenomic testing using a manual method or automated algorithm in a university-based health insurance network. The medication list was compiled from claims data during 4th quarter 2018. The manual method selected patients by number of medications by the health system’s list of medications for pharmacogenomic testing. The automated method used YouScript’s pharmacogenetic interaction probability (PIP) algorithm to select patients based on the probability that testing would result in detection of one or more clinically significant pharmacogenetic interactions. A total of 6916 patients were included. Patient cohorts selected by each method differed substantially, including size (manual n = 218, automated n = 286) and overlap (n = 41). The automated method was over twice as likely to identify patients where testing may reveal a clinically significant pharmacogenetic interaction than the manual method (62% vs. 29%, p < 0.0001). The manual method captured more patients with significant drug–drug or multi-drug interactions (80.3% vs. 40.2%, respectively, p < 0.0001), higher average number of significant drug interactions per patient (3.3 vs. 1.1, p < 0.0001), and higher average number of unique medications per patient (9.8 vs. 7.4, p < 0.0001). It is possible to identify a cohort of patients who would likely benefit from pharmacogenomic testing using manual or automated methods.

The predicting value of resting heart rate to identify undiagnosed diabetes in Korean adult: Korea National Health and Nutrition Examination Survey

OBJECTIVES

The purpose of this study was (1) to examine whether the addition of resting heart rate (RHR) to the existing undiagnosed diabetes mellitus (UnDM) prediction model would improve predictability, and (2) to develop and validate UnDM prediction models by using only easily assessable variables such as gender, RHR, age, and waist circumference (WC).

METHODS

Korea National Health and Nutrition Examination Survey (KNHANES) 2010, 2012, 2014, 2016 data were used to develop the model (model building set, n=19,675), while the data from 2011, 2013, 2015, 2017 were used to validate the model (validation set, n=19,917). UnDM was defined as a fasting glucose level ≥126 mg/dL or glycated hemoglobin ≥6.5%; however, doctors have not diagnosed it. Statistical package for the social sciences logistic regression analysis was used to determine the predictors of UnDM.

RESULTS

RHR, age, and WC were associated with UnDM. When RHR was added to the existing model, sensitivity was reduced (86 vs. 73%), specificity was increased (49 vs. 65%), and a higher Youden index (35 vs. 38) was expressed. When only gender, RHR, age, and WC were used in the model, a sensitivity, specificity, and Youden index of 70%, 67%, and 37, respectively, were observed.

CONCLUSIONS

Adding RHR to the existing UnDM prediction model improved specificity and the Youden index. Furthermore, when the prediction model only used gender, RHR, age, and WC, the outcomes were not inferior to those of the existing prediction model.

Development and validation of a nomogram for assessing risk of isolated high 2-hour plasma glucose

A tool was constructed to assess need of an oral glucose tolerance test (OGTT) in patients whose fasting plasma glucose (FPG) and hemoglobin A1c (HbA1c) are normal. Data was collected from the longitudinal REACTION study conducted from June to November 2011 (14,686 subjects, aged ≥ 40 y). In people without a prior history of diabetes, isolated high 2-hour plasma glucose was defined as 2-hour plasma glucose ≥ 11.1 mmol/L, FPG < 7.0 mmol/L, and HbA1c < 6.5%. A predictive nomogram for high 2-hour plasma glucose was developed via stepwise logistic regression. Discrimination and calibration of the nomogram were evaluated by the area under the receiver operating characteristic curve (AUC) and Hosmer-Lemeshow test; performance was externally validated in Northeast China. Parameters in the model included gender, age, drinking status, marriage status, history of hypertension and hyperlipidemia, waist-to-hip ratio, FPG, and HbA1c. All variables were noninvasive, except FPG and HbA1c. The AUC of the nomogram for isolated high 2-hour plasma glucose was 0.759 (0.727-0.791) in the development dataset. The AUCs of the internal and externally validation datasets were 0.781 (0.712-0.833) and 0.803 (0.778-0.829), respectively. Application of the nomogram during the validation study showed good calibration, and the decision curve analysis indicated that the nomogram was clinically useful. This practical nomogram model may be a reliable screening tool to detect isolated high 2-hour plasma glucose for individualized assessment in patients with normal FPG and HbA1c. It should simplify clinical practice, and help clinicians in decision-making.

Modification of cardiovascular disease risk by health behaviour change following type 2 diabetes diagnosis

AIMS

Among adults with type 2 diabetes (T2D), unhealthy behaviours are associated with increased risk of cardiovascular disease (CVD) events. To date, little research has considered whether healthy changes in behaviours following T2D diagnosis reduce CVD risk.

METHODS

A cohort of 867 adults with screen-detected T2D, participating in the Anglo-Danish-Dutch Study of Intensive Treatment in People with Screen-Detected Diabetes in Primary Care (ADDITION)-Cambridge trial, were followed for 10 years for incidence of CVD events. Diet, alcohol consumption, moderate/vigorous physical activity and smoking were assessed by questionnaire at the time of T2D screening and 1 year later. We estimated associations between health behaviours and CVD using Cox regression. We assessed modification of the associations by behaviour change in the year following T2D diagnosis.

RESULTS

Smoking [hazard ratio (HR): 1.73 (95% CI: 1.04, 2.87)] and high fat intake [HR: 1.70 (95% CI: 1.02, 2.85)] were associated with a higher hazard of CVD, while high plasma vitamin C [HR: 0.44 (95% CI: 0.22, 0.87)] and high fibre intake [HR: 0.60 (95% CI: 0.36, 0.99)] were associated with a lower hazard of CVD. Reduction in fat intake following T2D diagnosis modified associations with CVD. In particular, among those with the highest fat intake, decreasing intake attenuated the association with CVD [HR: 0.75 (95% CI: 0.36, 1.56)].

CONCLUSION

Following T2D diagnosis, decreasing fat intake was associated with lower long-term CVD risk. This evidence may raise concerns about low-carbohydrate, high-fat diets to achieve weight loss following T2D diagnosis. Further research considering the sources of fat is needed to inform dietary recommendations.

TRIAL REGISTRATION

This trial is registered as ISRCTN86769081. Retrospectively registered on 15 December 2006.

Relevance of anthropometric measurements as predictors of prevalent diabetes type 2: a cross-sectional study on a Norwegian population

OBJECTIVES

The objective was to determine the predictive potential of anthropometric indices to screen prevalent diabetes mellitus type 2 in a Norwegian population.

DESIGN

This is a cross-sectional design to determine the potential association of waist-to-height ratio (WHtR), waist-to-hip ratio (WHR), waist circumference (WC) and body mass index (BMI) with prevalent diabetes mellitus type 2 through logistic regression analysis. Receiver operating characteristic (ROC) curves were used to determine the predictive potential of the anthropometric indices. Youden's index was applied to determine the optimal cut-off points for each anthropometric index.

SETTING

This study used cross-sectional data from the populations-based Health Study in Nord-Trøndelag which invited all citizens in the county above 20 years of age.

PARTICIPANTS

This study included all those who were non-pregnant and had complete data (N=50 042), 98.5% of the participants. The sample is to be considered representative for the population of Norway.

PRIMARY AND SECONDARY OUTCOME MEASURES

OR and ROC of the potential association between diabetes mellitus type 2 and anthropometric indices were the main planned and performed outcome measures.

RESULTS

The results suggest that the anthropometric indices performed differently within the Norwegian population with WHR and WHtR being the stronger predictor with (ROC) of 0.746 (0.735 to 0.757) and 0.741 (0.730 to 0.752). The predictive potential for the investigated anthropometric indices was generally stronger for women than men.

CONCLUSION

Anthropometric indices of size BMI and the highly correlated WC are less associated with prevalent diabetes mellitus type 2 than WHR (WC adjusted for hip circumference) or WHtR (WC adjusted for height) in a Norwegian population.

Choice of HbA1c threshold for identifying individuals at high risk of type 2 diabetes and implications for diabetes prevention programmes: a cohort study

BACKGROUND

Type 2 diabetes (T2D) is common and increasing in prevalence. It is possible to prevent or delay T2D using lifestyle intervention programmes. Entry to these programmes is usually determined by a measure of glycaemia in the 'intermediate' range. This paper investigated the relationship between HbA1c and future diabetes risk and determined the impact of varying thresholds to identify those at high risk of developing T2D.

METHODS

We studied 4227 participants without diabetes aged ≥ 40 years recruited to the Exeter 10,000 population cohort in South West England. HbA1c was measured at study recruitment with repeat HbA1c available as part of usual care. Absolute risk of developing diabetes within 5 years, defined by HbA1c ≥ 48 mmol/mol (6.5%), according to baseline HbA1c, was assessed by a flexible parametric survival model.

RESULTS

The overall absolute 5-year risk (95% CI) of developing T2D in the cohort was 4.2% (3.6, 4.8%). This rose to 7.1% (6.1, 8.2%) in the 56% (n = 2358/4224) of participants classified 'high-risk' with HbA1c ≥ 39 mmol/mol (5.7%; ADA criteria). Under IEC criteria, HbA1c ≥ 42 mmol/mol (6.0%), 22% (n = 929/4277) of the cohort was classified high-risk with 5-year risk 14.9% (12.6, 17.2%). Those with the highest HbA1c values (44-47 mmol/mol [6.2-6.4%]) had much higher 5-year risk, 26.4% (22.0, 30.5%) compared with 2.1% (1.5, 2.6%) for 39-41 mmol/mol (5.7-5.9%) and 7.0% (5.4, 8.6%) for 42-43 mmol/mol (6.0-6.1%). Changing the entry criterion to prevention programmes from 39 to 42 mmol/mol (5.7-6.0%) reduced the proportion classified high-risk by 61%, and increased the positive predictive value (PPV) from 5.8 to 12.4% with negligible impact on the negative predictive value (NPV), 99.6% to 99.1%. Increasing the threshold further, to 44 mmol/mol (6.2%), reduced those classified high-risk by 59%, and markedly increased the PPV from 12.4 to 23.2% and had little impact on the NPV (99.1% to 98.5%).

CONCLUSIONS

A large proportion of people are identified as high-risk using current thresholds. Increasing the risk threshold markedly reduces the number of people that would be classified as high-risk and entered into prevention programmes, although this must be balanced against cases missed. Raising the entry threshold would allow limited intervention opportunities to be focused on those most likely to develop T2D.

Implications of weight gain with newer anti-retrovirals: 10-year predictions of cardiovascular disease and diabetes

OBJECTIVE

To evaluate the long-term risks of type 2 diabetes mellitus (T2DM) and cardiovascular disease (CVD) secondary to weight gain and clinical obesity associated with the initiation of integrase strand transfer inhibitors and tenofovir alafenamide (TAF) in the ADVANCE trial using validated risk equation tools.

DESIGN

Retrospective data analysis.

METHODS

In ADVANCE, 1053 treatment-naive participants in South Africa (99% black, 59% female) were randomized to 96 weeks of TAF/emtricitabine + dolutegravir (TAF/FTC + DTG), tenofovir disoproxil fumarate/FTC + DTG (TDF/FTC + DTG), or TDF/FTC + efavirenz (TDF/FTC/EFV). The 5 and 10-year risks of CVD were calculated using D:A:D, QRISK and Framingham, and T2DM risk using QDiabetes, Cambridge Diabetes and Leicester Practice Risk scores. Participants were included in this analysis if they were above 30 years old at baseline.

RESULTS

A total of 217 (TAF/FTC + DTG), 218 (TDF/FTC + DTG), and 215 (TDF/FTC/EFV) participants had 96-week data available. Weight gain was +8.1, +4.2, and +2.4 kg on TAF/FTC + DTG, TDF/FTC + DTG, and TDF/FTC/EFV, respectively. Participants on TAF/FTC + DTG had greatest risk scores for CVD (using QRISK) and T2DM, driven by weight changes. Differences were statistically significant between TAF/FTC + DTG and TDF/FTC/EFV for CVD risk using the QRISK equation, equivalent to one extra case per 1000 people treated over 10 years, and between all treatment groups for T2DM risk. Six extra T2DM cases were predicted on TAF/FTC + DTG vs. TDF/FTC + DTG using QDiabetes.

CONCLUSION

Obesity, especially with TAF/FTC + DTG, drove increased risk of T2DM, with some evidence of greater CVD risk. However, predictive tools have not been validated in the HIV-positive and black African population.

Comparing non-invasive diabetes risk scores for detecting patients in clinical practice: a cross-sectional validation study

Background: Type 2 diabetes (T2DM) is a significant cause of morbidity and mortality, thus early identification is of paramount importance. A high proportion of T2DM cases are undiagnosed highlighting the importance of effective detection methods such as non-invasive diabetes risk scores (DRSs). Thus far, no DRS has been validated in an Irish population. Therefore, the aim of this study was to compare the ability of nine DRSs to detect T2DM cases in an Irish population. Methods: This was a cross-sectional study of 1,990 men and women aged 46–73 years. Data on DRS components were collected from questionnaires and clinical examinations. T2DM was determined according to a fasting plasma glucose level ≥7.0 mmol/l or a glycated haemoglobin A1c level ≥6.5% (≥48 mmol/mol). Receiver operating characteristic curve analysis assessed the ability of DRSs and their components to discriminate T2DM cases. Results: Among the examined scores, area under the curve (AUC) values ranged from 0.71–0.78, with the Cambridge Diabetes Risk Score (AUC=0.78, 95% CI: 0.75–0.82), Leicester Diabetes Risk Score (AUC=0.78, 95% CI: 0.75–0.82), Rotterdam Predictive Model 2 (AUC=0.78, 95% CI: 0.74–0.82) and the U.S. Diabetes Risk Score (AUC=0.78, 95% CI: 0.74–0.81) demonstrating the largest AUC values as continuous variables and at optimal cut-offs. Regarding individual DRS components, anthropometric measures displayed the largest AUC values. Conclusions: The best performing DRSs were broadly similar in terms of their components; all incorporated variables for age, sex, BMI, hypertension and family diabetes history. The Cambridge Diabetes Risk Score, had the largest AUC value at an optimal cut-off, can be easily accessed online for use in a clinical setting and may be the most appropriate and cost-effective method for case-finding in an Irish population.

Health Economic Evidence of Point-of-Care Testing: A Systematic Review

OBJECTIVE

Point-of-care testing (POCT) has become an essential diagnostic technology for optimal patient care. Its implementation, however, still falls behind. This paper reviews the available evidence on the health economic impact of introducing POCT to assess if poor POCT uptake may be related to lacking evidence.

STUDY DESIGN

The Scopus and PubMed databases were searched to identify publications describing a health economic evaluation of a point-of-care (POC) test. Data were extracted from the included publications, including general and methodological characteristics as well as the study results summarized in either cost, effects or an incremental cost-effectiveness ratio. Results were sorted into six groups according to the POC test's purpose (diagnosis, screening or monitoring) and care setting (primary care or secondary care). The reporting quality of the publications was determined using the CHEERS checklist.

RESULTS

The initial search resulted in 396 publications, of which 44 met the inclusion criteria. Most of the evaluations were performed in a primary care setting (n = 31; 70.5%) compared with a secondary care setting (n = 13; 29.5%). About two thirds of the evaluations were on POC tests implemented with a diagnostic purpose (n = 28; 63.6%). More than 75% of evaluations concluded that POCT is recommended for implementation, although in some cases only under specific circumstances and conditions. Compliance with the CHEERS checklist items ranged from 20.8% to 100%, with an average reporting quality of 72.0%.

CONCLUSION

There were very few evaluations in this review that advised against the implementation of POCT. However, the uptake of POCT in many countries remains low. Even though the evaluations included in this review did not always include the full long-term benefits of POCT, it is clear that health economic evidence across a few dimensions of value already indicate the benefits of POCT. This suggests that the lack of evidence on POCT is not the primary barrier to its implementation and that the low uptake of these tests in clinical practice is due to (a combination of) other barriers. In this context, aspects around organization of care, support of clinicians and quality management may be crucial in the widespread implementation of POCT.

Improving Current Glycated Hemoglobin Prediction in Adults: Use of Machine Learning Algorithms With Electronic Health Records

Background

Predicting the risk of glycated hemoglobin (HbA_1c) elevation can help identify patients with the potential for developing serious chronic health problems, such as diabetes. Early preventive interventions based upon advanced predictive models using electronic health records data for identifying such patients can ultimately help provide better health outcomes.

Objective

Our study investigated the performance of predictive models to forecast HbA_1c elevation levels by employing several machine learning models. We also examined the use of patient electronic health record longitudinal data in the performance of the predictive models. Explainable methods were employed to interpret the decisions made by the black box models.

Methods

This study employed multiple logistic regression, random forest, support vector machine, and logistic regression models, as well as a deep learning model (multilayer perceptron) to classify patients with normal (<5.7%) and elevated (≥5.7%) levels of HbA_1c. We also integrated current visit data with historical (longitudinal) data from previous visits. Explainable machine learning methods were used to interrogate the models and provide an understanding of the reasons behind the decisions made by the models. All models were trained and tested using a large data set from Saudi Arabia with 18,844 unique patient records.

Results

The machine learning models achieved promising results for predicting current HbA_1c elevation risk. When coupled with longitudinal data, the machine learning models outperformed the multiple logistic regression model used in the comparative study. The multilayer perceptron model achieved an accuracy of 83.22% for the area under receiver operating characteristic curve when used with historical data. All models showed a close level of agreement on the contribution of random blood sugar and age variables with and without longitudinal data.

Conclusions

This study shows that machine learning models can provide promising results for the task of predicting current HbA_1c levels (≥5.7% or less). Using patients’ longitudinal data improved the performance and affected the relative importance for the predictors used. The models showed results that are consistent with comparable studies.

A Prediction Model Based on Noninvasive Indicators to Predict the 8-Year Incidence of Type 2 Diabetes in Patients with Nonalcoholic Fatty Liver Disease: A Population-Based Retrospective Cohort Study

Background

The prevention of type 2 diabetes (T2D) and its associated complications has become a major priority of global public health. In addition, there is growing evidence that nonalcoholic fatty liver disease (NAFLD) is associated with an increased risk of diabetes. Therefore, the purpose of this study was to develop and validate a nomogram based on independent predictors to better assess the 8-year risk of T2D in Japanese patients with NAFLD.

Methods

This is a historical cohort study from a collection of databases that included 2741 Japanese participants with NAFLD without T2D at baseline. All participants were randomized to a training cohort (n = 2058) and a validation cohort (n = 683). The data of the training cohort were analyzed using the least absolute shrinkage and selection operator method to screen the suitable and effective risk factors for Japanese patients with NAFLD. A cox regression analysis was applied to build a nomogram incorporating the selected features. The C-index, receiver operating characteristic curve (ROC), calibration plot, decision curve analysis, and Kaplan-Meier analysis were used to validate the discrimination, calibration, and clinical usefulness of the model. The results were reevaluated by internal validation in the validation cohort.

Results

We developed a simple nomogram that predicts the risk of T2D for Japanese patients with NAFLD by using the parameters of smoking status, waist circumference, hemoglobin A1c, and fasting blood glucose. For the prediction model, the C-index of training cohort and validation cohort was 0.839 (95% confidence interval (CI), 0.804-0.874) and 0.822 (95% CI, 0.777-0.868), respectively. The pooled area under the ROC of 8-year T2D risk in the training cohort and validation cohort was 0.811 and 0.805, respectively. The calibration curve indicated a good agreement between the probability predicted by the nomogram and the actual probability. The decision curve analysis demonstrated that the nomogram was clinically useful.

Conclusions

We developed and validated a nomogram for the 8-year risk of incident T2D among Japanese patients with NAFLD. Our nomogram can effectively predict the 8-year incidence of T2D in Japanese patients with NAFLD and helps to identify people at high risk of T2D early, thus contributing to effective prevention programs for T2D.

Examining social determinants of undiagnosed diabetes in Namibia and South Africa using a behavioral model of health services use

AIMS

To examine factors associated with undiagnosed diabetes in Namibia and South Africa.

METHODS

This study used the most recent Demographic and Health Surveys (DHS) from Namibia (2013) and South Africa (2016). This study focused on adults at 35-64 years old. Using Andersen's Behavioral Model, potential contributing factors were categorized into predisposing factors (sex and education), enabling factors (wealth, health insurance, and residence), and a need factor (age, BMI, and high blood pressure). Separate multivariable logistic regression models were used to examine factors associated with undiagnosed diabetes in Namibia (N = 242) and South Africa (N = 525).

RESULTS

In Namibia, higher odds of having undiagnosed diabetes were associated with rural residence (adjusted odds ratio (aOR) = 2.21) and age younger than 45 years old (aOR = 3.20). In South Africa, odds of having undiagnosed diabetes were higher among the poorest-to-poorer group than it was in the richer-to-richest group (aOR = 2.33). In both countries, having high blood pressure was associated with lower odds of having undiagnosed diabetes (aOR = 0.31 in Namibia; aOR = 0.21 in South Africa).

DISCUSSION

Different enabling and need factors were associated with undiagnosed diabetes in these two countries, which implies potentially-different mechanisms driving the high prevalence of undiagnosed diabetes, as well as the needs for different solutions.

Using a Diabetes Risk Score to Identify Patients Without Diabetes at Risk for New Hyperglycemia in the Hospital

OBJECTIVE

To assess the value of a validated diabetes risk test, the Cambridge Risk Score (CRS), to identify patients admitted to hospital without diabetes at risk for new hyperglycemia (NH).

METHODS

This retrospective cross-sectional study included adults admitted to a hospital over a 4-year period. Patients with no diabetes diagnosis and not on antidiabetics were included. The CRS was calculated for each patient, and those with available glycated hemoglobin (HbA1C) results were investigated in a second analysis. Multivariate regression analyses were performed to assess the association among CRS, HbA1C, and the risk for NH.

RESULTS

A total of 19,830 subjects comprised the sample, of which 38% were found to have developed NH, defined as a blood glucose level ≥140 mg/dL. After accounting for covariates, the CRS was significantly associated with NH (odds ratio [OR], 1.19 [1.16, 1.22]; P < .001). Only 17% of patients had their HbA1C values checked within 6 months of admission. Compared with patients without diabetes, patients with prediabetes based on their HbA1C level (OR, 1.59 [1.37, 1.86]; P < .001) and patients with undiagnosed diabetes (OR, 5.95 [3.50, 10.65]; P < .001) were also significantly more likely to have NH.

CONCLUSION

Results of this study show that the CRS and HbA1C levels were significantly associated with the risk of developing NH in inpatient adults without diabetes. Given that an HbA1C level was missing in most medical records of hospitalized patients without diabetes, the CRS could be a useful tool for early identification and management of NH, possibly leading to better outcomes.

Optimal treatment recommendations for diabetes patients using the Markov decision process along with the South Korean electronic health records

The extensive utilization of electronic health records (EHRs) and the growth of enormous open biomedical datasets has readied the area for applications of computational and machine learning techniques to reveal fundamental patterns. This study’s goal is to develop a medical treatment recommendation system using Korean EHRs along with the Markov decision process (MDP). The sharing of EHRs by the National Health Insurance Sharing Service (NHISS) of Korea has made it possible to analyze Koreans’ medical data which include treatments, prescriptions, and medical check-up. After considering the merits and effectiveness of such data, we analyzed patients’ medical information and recommended optimal pharmaceutical prescriptions for diabetes, which is known to be the most burdensome disease for Koreans. We also proposed an MDP-based treatment recommendation system for diabetic patients to help doctors when prescribing diabetes medications. To build the model, we used the 11-year Korean NHISS database. To overcome the challenge of designing an MDP model, we carefully designed the states, actions, reward functions, and transition probability matrices, which were chosen to balance the tradeoffs between reality and the curse of dimensionality issues.

Genetic Risk Score Increased Discriminant Efficiency of Predictive Models for Type 2 Diabetes Mellitus Using Machine Learning: Cohort Study

Background: Previous studies have constructed prediction models for type 2 diabetes mellitus (T2DM), but machine learning was rarely used and few focused on genetic prediction. This study aimed to establish an effective T2DM prediction tool and to further explore the potential of genetic risk scores (GRS) via various classifiers among rural adults.

Methods: In this prospective study, the GRS for a total of 5,712 participants from the Henan Rural Cohort Study was calculated. Cox proportional hazards (CPH) regression was used to analyze the associations between GRS and T2DM. CPH, artificial neural network (ANN), random forest (RF), and gradient boosting machine (GBM) were used to establish prediction models, respectively. The area under the receiver operating characteristic curve (AUC) and net reclassification index (NRI) were used to assess the discrimination ability of the models. The decision curve was plotted to determine the clinical-utility for prediction models.

Results: Compared with the individuals in the lowest quintile of the GRS, the HR (95% CI) was 2.06 (1.40 to 3.03) for those with the highest quintile of GRS (P_trend < 0.05). Based on conventional predictors, the AUCs of the prediction model were 0.815, 0.816, 0.843, and 0.851 via CPH, ANN, RF, and GBM, respectively. Changes with the integration of GRS for CPH, ANN, RF, and GBM were 0.001, 0.002, 0.018, and 0.033, respectively. The reclassifications were significantly improved for all classifiers when adding GRS (NRI: 41.2% for CPH; 41.0% for ANN; 46.4% for ANN; 45.1% for GBM). Decision curve analysis indicated the clinical benefits of model combined GRS.

Conclusion: The prediction model combined with GRS may provide incremental predictions of performance beyond conventional factors for T2DM, which demonstrated the potential clinical use of genetic markers to screen vulnerable populations.

Clinical Trial Registration: The Henan Rural Cohort Study is registered in the Chinese Clinical Trial Register (Registration number: ChiCTR-OOC-15006699). http://www.chictr.org.cn/showproj.aspx?proj=11375.

Risk Prediction of the Diabetes Missing Million: Identifying Individuals at High Risk of Diabetes and Related Complications

Early diagnosis and effective management of type 2 diabetes (T2D) are crucial in reducing the risk of developing life-changing complications such as heart failure, stroke, kidney disease, blindness and amputation, which are also associated with significant costs for healthcare providers. However, as T2D symptoms often develop slowly it is not uncommon for people to live with T2D for years without being aware of their condition-commonly known as the undiagnosed missing million. By the time a diagnosis is received, many individuals will have already developed serious complications. While the existence of undiagnosed diabetes has long been recognised, wide-reaching awareness among the general public, clinicians and policymakers is lacking, and there is uncertainty in how best to identify high-risk individuals. In this article we have used consensus expert opinion alongside the available evidence, to provide support for the diabetes healthcare community regarding risk prediction of the missing million. Its purpose is to provide awareness of the risk factors for identifying individuals at high, moderate and low risk of T2D and T2D-related complications. The awareness of risk predictors, particularly in primary care, is important, so that appropriate steps can be taken to reduce the clinical and economic burden of T2D and its complications.

A prediction nomogram for the 3-year risk of incident diabetes among Chinese adults

Identifying individuals at high risk for incident diabetes could help achieve targeted delivery of interventional programs. We aimed to develop a personalized diabetes prediction nomogram for the 3-year risk of diabetes among Chinese adults. This retrospective cohort study was among 32,312 participants without diabetes at baseline. All participants were randomly stratified into training cohort (n = 16,219) and validation cohort (n = 16,093). The least absolute shrinkage and selection operator model was used to construct a nomogram and draw a formula for diabetes probability. 500 bootstraps performed the receiver operating characteristic (ROC) curve and decision curve analysis resamples to assess the nomogram's determination and clinical use, respectively. 155 and 141 participants developed diabetes in the training and validation cohort, respectively. The area under curve (AUC) of the nomogram was 0.9125 (95% CI, 0.8887-0.9364) and 0.9030 (95% CI, 0.8747-0.9313) for the training and validation cohort, respectively. We used 12,545 Japanese participants for external validation, its AUC was 0.8488 (95% CI, 0.8126-0.8850). The internal and external validation showed our nomogram had excellent prediction performance. In conclusion, we developed and validated a personalized prediction nomogram for 3-year risk of incident diabetes among Chinese adults, identifying individuals at high risk of developing diabetes.

Cardiometabolic risk prediction algorithms for young people with psychosis: a systematic review and exploratory analysis

OBJECTIVE

Cardiometabolic risk prediction algorithms are common in clinical practice. Young people with psychosis are at high risk for developing cardiometabolic disorders. We aimed to examine whether existing cardiometabolic risk prediction algorithms are suitable for young people with psychosis.

METHODS

We conducted a systematic review and narrative synthesis of studies reporting the development and validation of cardiometabolic risk prediction algorithms for general or psychiatric populations. Furthermore, we used data from 505 participants with or at risk of psychosis at age 18 years in the ALSPAC birth cohort, to explore the performance of three algorithms (QDiabetes, QRISK3 and PRIMROSE) highlighted as potentially suitable. We repeated analyses after artificially increasing participant age to the mean age of the original algorithm studies to examine the impact of age on predictive performance.

RESULTS

We screened 7820 results, including 110 studies. All algorithms were developed in relatively older participants, and most were at high risk of bias. Three studies (QDiabetes, QRISK3 and PRIMROSE) featured psychiatric predictors. Age was more strongly weighted than other risk factors in each algorithm. In our exploratory analysis, calibration plots for all three algorithms implied a consistent systematic underprediction of cardiometabolic risk in the younger sample. After increasing participant age, calibration plots were markedly improved.

CONCLUSION

Existing cardiometabolic risk prediction algorithms cannot be recommended for young people with or at risk of psychosis. Existing algorithms may underpredict risk in young people, even in the face of other high-risk features. Recalibration of existing algorithms or a new tailored algorithm for the population is required.

Development of a risk score to predict abnormal glycemic status among Thai dental patients

Purpose

To construct a risk score using both clinical and intra-oral variables and to determine a risk score to screen individuals according to their risk of hyperglycemia.

Design/methodology/approach

A cross-sectional study was carried out among 690 Thai dental patients who visited the Special Clinic, Faculty of Dentistry, Mahidol University and a mobile dental unit of His Majesty the King of Thailandss Dental Service Unit. Participants aged ≥25 years without a previous history of type 2 diabetes mellitus were included in the study. Participants diagnosed with severe anemia and polycythemia were excluded. Questionnaires were used to collect demographic data. Point-of-care HbA1c, body mass index (BMI), blood pressure and periodontal status were analyzed.

Findings

A total of 690 participants were included in the study. A risk scoring system including five variables was developed. It exhibited fair discrimination (area under the curve = 0.72, 95%CI 0.68–0.71). The risk score value of 9 was used as the cut-off point for increased risk of abnormal HbA1c. Subjects that had a total risk score of 9 or more had a high probability of having abnormal HbA1c and were identified for referral to physicians for further investigation and diagnosis.

Originality/value

A risk score to predict hyperglycemia using a dental parameter was developed for convenient evaluation in dental clinics.

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

BACKGROUND

Previous conventional models for the prediction of diabetes could be updated by incorporating the increasing amount of health data available and new risk prediction methodology.

OBJECTIVE

We aimed to develop a substantially improved diabetes risk prediction model using sophisticated machine-learning algorithms based on a large retrospective population cohort of over 230,000 people who were enrolled in the study during 2006-2017.

METHODS

We collected demographic, medical, behavioral, and incidence data for type 2 diabetes mellitus (T2DM) in over 236,684 diabetes-free participants recruited from the 45 and Up Study. We predicted and compared the risk of diabetes onset in these participants at 3, 5, 7, and 10 years based on three machine-learning approaches and the conventional regression model.

RESULTS

Overall, 6.05% (14,313/236,684) of the participants developed T2DM during an average 8.8-year follow-up period. The 10-year diabetes incidence in men was 8.30% (8.08%-8.49%), which was significantly higher (odds ratio 1.37, 95% CI 1.32-1.41) than that in women at 6.20% (6.00%-6.40%). The incidence of T2DM was doubled in individuals with obesity (men: 17.78% [17.05%-18.43%]; women: 14.59% [13.99%-15.17%]) compared with that of nonobese individuals. The gradient boosting machine model showed the best performance among the four models (area under the curve of 79% in 3-year prediction and 75% in 10-year prediction). All machine-learning models predicted BMI as the most significant factor contributing to diabetes onset, which explained 12%-50% of the variance in the prediction of diabetes. The model predicted that if BMI in obese and overweight participants could be hypothetically reduced to a healthy range, the 10-year probability of diabetes onset would be significantly reduced from 8.3% to 2.8% (P<.001).

CONCLUSIONS

A one-time self-reported survey can accurately predict the risk of diabetes using a machine-learning approach. Achieving a healthy BMI can significantly reduce the risk of developing T2DM.

Predicting Current Glycated Hemoglobin Levels in Adults From Electronic Health Records: Validation of Multiple Logistic Regression Algorithm

BACKGROUND

Electronic health record (EHR) systems generate large datasets that can significantly enrich the development of medical predictive models. Several attempts have been made to investigate the effect of glycated hemoglobin (HbA1c) elevation on the prediction of diabetes onset. However, there is still a need for validation of these models using EHR data collected from different populations.

OBJECTIVE

The aim of this study is to perform a replication study to validate, evaluate, and identify the strengths and weaknesses of replicating a predictive model that employed multiple logistic regression with EHR data to forecast the levels of HbA1c. The original study used data from a population in the United States and this differentiated replication used a population in Saudi Arabia.

METHODS

A total of 3 models were developed and compared with the model created in the original study. The models were trained and tested using a larger dataset from Saudi Arabia with 36,378 records. The 10-fold cross-validation approach was used for measuring the performance of the models.

RESULTS

Applying the method employed in the original study achieved an accuracy of 74% to 75% when using the dataset collected from Saudi Arabia, compared with 77% obtained from using the population from the United States. The results also show a different ranking of importance for the predictors between the original study and the replication. The order of importance for the predictors with our population, from the most to the least importance, is age, random blood sugar, estimated glomerular filtration rate, total cholesterol, non-high-density lipoprotein, and body mass index.

CONCLUSIONS

This replication study shows that direct use of the models (calculators) created using multiple logistic regression to predict the level of HbA1c may not be appropriate for all populations. This study reveals that the weighting of the predictors needs to be calibrated to the population used. However, the study does confirm that replicating the original study using a different population can help with predicting the levels of HbA1c by using the predictors that are routinely collected and stored in hospital EHR systems.

Behaviour change, weight loss and remission of Type 2 diabetes: a community-based prospective cohort study

AIM

To quantify the association between behaviour change and weight loss after diagnosis of Type 2 diabetes, and the likelihood of remission of diabetes at 5-year follow-up.

METHOD

We conducted a prospective cohort study in 867 people with newly diagnosed diabetes aged 40-69 years from the ADDITION-Cambridge trial. Participants were identified via stepwise screening between 2002 and 2006, and underwent assessment of weight change, physical activity (EPAQ2 questionnaire), diet (plasma vitamin C and self-report), and alcohol consumption (self-report) at baseline and 1 year after diagnosis. Remission was examined at 5 years after diabetes diagnosis via HbA1c level. We constructed log binomial regression models to quantify the association between change in behaviour and weight over both the first year after diagnosis and the subsequent 1-5 years, as well as remission at 5-year follow-up.

RESULTS

Diabetes remission was achieved in 257 participants (30%) at 5-year follow-up. Compared with people who maintained the same weight, those who achieved ≥ 10% weight loss in the first year after diagnosis had a significantly higher likelihood of remission [risk ratio 1.77 (95% CI 1.32 to 2.38; p<0.01)]. In the subsequent 1-5 years, achieving ≥10% weight loss was also associated with remission [risk ratio 2.43 (95% CI 1.78 to 3.31); p<0.01].

CONCLUSION

In a population-based sample of adults with screen-detected Type 2 diabetes, weight loss of ≥10% early in the disease trajectory was associated with a doubling of the likelihood of remission at 5 years. This was achieved without intensive lifestyle interventions or extreme calorie restrictions. Greater attention should be paid to enabling people to achieve weight loss following diagnosis of Type 2 diabetes.

A composite of BMI and waist circumference may be a better obesity metric in Indians with high risk for type 2 diabetes: An analysis of NMB-2017, a nationwide cross-sectional study

AIMS

Obesity measurement is a vital component of most type 2 diabetes screening tests; while studies had shown that waist circumference (WC) is a better predictor in South Asians, there is evidence that BMI is also effective. Our objective was to evaluate the efficacy of BMI_WC, a composite measure, against BMI and WC.

METHODS

Using data from a nationwide randomized cluster sample survey (NMB-2017), we analyzed 7496 adults at high risk for type 2 diabetes. WC, BMI, and BMI_WC were evaluated using Odds Ratio (OR), and Classification scores (Sensitivity, Specificity, and Accuracy). These were validated using Indian Diabetes Risk Score (IDRS) by replacing WC with BMI and BMI_WC, and calculating Sensitivity, Specificity, and Accuracy.

RESULTS

BMI_WC had higher OR (2·300) compared to WC (1·87) and BMI (2·26). WC, BMI, and BMI_WC were all highly Sensitive (0·75, 0·81, 0·70 resp.). But BMI_WC had significantly higher Specificity (0.36) when compared to WC and BMI (0.27 each). IDRS_WC, IDRS_BMI, and IDRS_BMIWC were all highly Sensitive (0·87, 0·88, 0·82 resp.). But IDRS_BMIWC had significantly higher Specificity (0·39) compared to IDRS_WC and IDRS_BMI (0·30, 0·31 resp.).

CONCLUSIONS

Both WC and BMI are good predictors of risk for T2DM, but BMI_WC is a better predictor, with higher Specificity; this may indicate that Indians with high values of both central (high WC) and general (BMI > 23) obesity carry higher risk for type 2 diabetes than either one in isolation. Using BMI_WC in IDRS improves its performance on Accuracy and Specificity.

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.

Prediction of 5-year risk of diabetes mellitus in relatively low risk middle-aged and elderly adults

AIMS

To determine the potential risk factors and construct the predictive model of diabetic risk among a relatively low risk middle-aged and elderly Chinese population.

METHODS

Information of participants was collected in the Dongfeng-Tongji cohort study, a perspective cohort study of Chinese occupational population. The main outcome was incident type 2 diabetes (T2DM). Based on the conventional risk factors of diabetes, we defined low risk participants without underlying diseases such as coronary heart disease, stroke, cancer, dyslipidemia, hypertension, metabolic syndrome, obesity and family history of diabetes. Totally, 4833 participants from the Dongfeng-Tongji cohort study were enrolled, and of them, 171 had an incident diagnosis of T2DM during 4.6 years of follow-up period. A Cox proportional hazards model was used to estimate effects of risk factors. The restricted cubic spline regression and the Youden index were used to explore the optimal cutoffs of risk factors, and the C index was used to assess the discrimination power of prediction models.

RESULTS

There were significant linear relationships between BMI/TG level/fasting glucose level and incident diabetic risk among low risk participants. In the restricted cubic spline regression, when fasting glucose level was above 5.4 mmol/L, TG above 1.06 mmol/L and BMI above 22 kg/m², the HRs (95% CIs) of diabetes were above 1.0. The detailed HRs (95% CI) were 1.29 (1.01, 1.64), 2.57 (1.00, 6.58), and 1.49 (1.00, 2.22), respectively. The optimal cutoff determined by the Yonden index was 1.1 mmol/L for TG, 24 kg/m² for BMI and 5.89 mmol/L for fasting plasma glucose, respectively. The C index was 0.75 (95% CI: 0.7-0.81) when age, sex, smoke status, physical activity, BMI (< 24 kg/m² and ≥ 24 kg/m²), TG (< 1.1 mmol/L and ≥ 1.1 mmol/L), and FPG (< 5.89 mmol/L and ≥ 5.89 mmol/L) were introduced into the diabetes predictive model.

CONCLUSIONS

Fasting plasma glucose level, BMI, and triglyceride level were still dominated factors to predict 5-year diabetic risk among the relatively low risk participants. The cutoff values for fasting plasma glucose, TG, and BMI set as 5.89 mmol/L, 1.1 mmol/L, and 24 kg/m², respectively, had the best predictive discrimination of diabetes.

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.

Predictive models for diabetes mellitus using machine learning techniques

BACKGROUND

Diabetes Mellitus is an increasingly prevalent chronic disease characterized by the body's inability to metabolize glucose. The objective of this study was to build an effective predictive model with high sensitivity and selectivity to better identify Canadian patients at risk of having Diabetes Mellitus based on patient demographic data and the laboratory results during their visits to medical facilities.

METHODS

Using the most recent records of 13,309 Canadian patients aged between 18 and 90 years, along with their laboratory information (age, sex, fasting blood glucose, body mass index, high-density lipoprotein, triglycerides, blood pressure, and low-density lipoprotein), we built predictive models using Logistic Regression and Gradient Boosting Machine (GBM) techniques. The area under the receiver operating characteristic curve (AROC) was used to evaluate the discriminatory capability of these models. We used the adjusted threshold method and the class weight method to improve sensitivity - the proportion of Diabetes Mellitus patients correctly predicted by the model. We also compared these models to other learning machine techniques such as Decision Tree and Random Forest.

RESULTS

The AROC for the proposed GBM model is 84.7% with a sensitivity of 71.6% and the AROC for the proposed Logistic Regression model is 84.0% with a sensitivity of 73.4%. The GBM and Logistic Regression models perform better than the Random Forest and Decision Tree models.

CONCLUSIONS

The ability of our model to predict patients with Diabetes using some commonly used lab results is high with satisfactory sensitivity. These models can be built into an online computer program to help physicians in predicting patients with future occurrence of diabetes and providing necessary preventive interventions. The model is developed and validated on the Canadian population which is more specific and powerful to apply on Canadian patients than existing models developed from US or other populations. Fasting blood glucose, body mass index, high-density lipoprotein, and triglycerides were the most important predictors in these models.

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.

Changes in behaviors after diagnosis of type 2 diabetes and 10-year incidence of cardiovascular disease and mortality

Background

Large changes in health behaviors achieved through intensive lifestyle intervention programs improve cardiovascular disease (CVD) risk factors among adults with type 2 diabetes. However, such interventions are not widely available, and there is limited evidence as to whether changes in behaviors affect risk of CVD events.

Methods

Among 852 adults with screen-detected type 2 diabetes in the ADDITION-Cambridge study, we assessed changes in diet, physical activity, and alcohol use in the year following diabetes diagnosis. Participants were recruited from 49 general practices in Eastern England from 2002 to 2006, and were followed through 2014 for incidence of CVD events (n = 116) and all-cause mortality (n = 127). We used Cox proportional hazards regression to estimate hazard ratios (HR) for the associations of changes in behaviors with CVD and all-cause mortality. We estimated associations with CVD risk factors using linear regression. We considered changes in individual behaviors and overall number of healthy changes. Models adjusted for demographic factors, bodyweight, smoking, baseline value of the health behavior, and cardio-protective medication use.

Results

Decreasing alcohol intake by ≥ 2 units/week was associated with lower hazard of CVD vs maintenance [HR: 0.56, 95% CI 0.36, 0.87]. Decreasing daily calorie intake by ≥ 300 kcal was associated with lower hazard of all-cause mortality vs maintenance [HR: 0.56, 95% CI 0.34, 0.92]. Achieving ≥ 2 healthy behavior changes was associated with lower hazard of CVD vs no healthy changes [HR: 0.39, 95% CI 0.18, 0.82].

Conclusions

In the year following diabetes diagnosis, small reductions in alcohol use were associated with lower hazard of CVD and small reductions in calorie intake were associated with lower hazard of all-cause mortality in a population-based sample. Where insufficient resources exist for specialist-led interventions, achievement of moderate behavior change targets is possible outside of treatment programs and may reduce long-term risk of CVD complications.

Trial registration This trial is registered as ISRCTN86769081. Retrospectively registered 15 December 2006

Electronic supplementary material

The online version of this article (10.1186/s12933-019-0902-5) contains supplementary material, which is available to authorized users.

Moderate weight change following diabetes diagnosis and 10 year incidence of cardiovascular disease and mortality

AIMS/HYPOTHESIS

Adults with type 2 diabetes are at high risk of developing cardiovascular disease (CVD). Evidence of the impact of weight loss on incidence of CVD events among adults with diabetes is sparse and conflicting. We assessed weight change in the year following diabetes diagnosis and estimated associations with 10 year incidence of CVD events and all-cause mortality.

METHODS

In a cohort analysis among 725 adults with screen-detected diabetes enrolled in the Anglo-Danish-Dutch Study of Intensive Treatment in People with Screen-Detected Diabetes in Primary Care (ADDITION)-Cambridge trial, we estimated HRs for weight change in the year following diabetes diagnosis and 10 year incidence of CVD (n = 99) and all-cause mortality (n = 95) using Cox proportional hazards regression. We used linear regression to estimate associations between weight loss and CVD risk factors. Models were adjusted for age, sex, baseline BMI, smoking, occupational socioeconomic status, cardio-protective medication use and treatment group.

RESULTS

Loss of ≥5% body weight in the year following diabetes diagnosis was associated with improvements in HbA_1c and blood lipids and a lower hazard of CVD at 10 years compared with maintaining weight (HR 0.52 [95% CI 0.32, 0.86]). The associations between weight gain vs weight maintenance and CVD (HR 0.41 [95% CI 0.15, 1.11]) and mortality (HR 1.63 [95% CI 0.83, 3.19]) were less clear.

CONCLUSIONS/INTERPRETATION

Among adults with screen-detected diabetes, loss of ≥5% body weight during the year after diagnosis was associated with a lower hazard of CVD events compared with maintaining weight. These results support the hypothesis that moderate weight loss may yield substantial long-term CVD reduction, and may be an achievable target outside of specialist-led behavioural treatment programmes.

Association Between Primary Care Practitioner Empathy and Risk of Cardiovascular Events and All-Cause Mortality Among Patients With Type 2 Diabetes: A Population-Based Prospective Cohort Study

PURPOSE

To examine the association between primary care practitioner (physician and nurse) empathy and incidence of cardiovascular disease (CVD) events and all-cause mortality among patients with type 2 diabetes.

METHODS

This was a population-based prospective cohort study of 49 general practices in East Anglia (United Kingdom). The study population included 867 individuals with screen-detected type 2 diabetes who were followed up for an average of 10 years until December 31, 2014 in the Anglo-Danish-Dutch Study of Intensive Treatment in People With Screen Detected Diabetes in Primary Care (ADDITION)-Cambridge trial. Twelve months after diagnosis, patients assessed practitioner empathy and their experiences of diabetes care during the preceding year using the consultation and relational empathy (CARE) measure questionnaire. CARE scores were grouped into tertiles. The main outcome measures were first recorded CVD event (a composite of myocardial infarction, revascularization, nontraumatic amputation, stroke, and fatal CVD event) and all-cause mortality, obtained from electronic searches of the general practitioner record, national registries, and hospital records. Hazard ratios (HRs) were estimated using Cox models adjusted for relevant confounders. The ADDITION-Cambridge trial is registered as ISRCTN86769081.

RESULTS

Of the 628 participants with a completed CARE score, 120 (19%) experienced a CVD event, and 132 (21%) died during follow up. In the multivariable model, compared with the lowest tertile, higher empathy scores were associated with a lower risk of CVD events (although this did not achieve statistical significance) and a lower risk of all-cause mortality (HRs for the middle and highest tertiles, respectively: 0.49; 95% CI, 0.27-0.88, P = .01 and 0.60; 95% CI, 0.35-1.04, P = .05).

CONCLUSIONS

Positive patient experiences of practitioner empathy in the year after diagnosis of type 2 diabetes may be associated with beneficial long-term clinical outcomes. Further work is needed to understand which aspects of patient perceptions of empathy might influence health outcomes and how to incorporate this understanding into the education and training of practitioners.

Development and validation of a predictive model for incident type 2 diabetes in middle-aged Mexican adults: the metabolic syndrome cohort

BACKGROUND

Type 2 diabetes mellitus (T2D) is a leading cause of morbidity and mortality in Mexico. Here, we aimed to report incidence rates (IR) of type 2 diabetes in middle-aged apparently-healthy Mexican adults, identify risk factors associated to ID and develop a predictive model for ID in a high-risk population.

METHODS

Prospective 3-year observational cohort, comprised of apparently-healthy adults from urban settings of central Mexico in whom demographic, anthropometric and biochemical data was collected. We evaluated risk factors for ID using Cox proportional hazard regression and developed predictive models for ID.

RESULTS

We included 7636 participants of whom 6144 completed follow-up. We observed 331 ID cases (IR: 21.9 per 1000 person-years, 95%CI 21.37-22.47). Risk factors for ID included family history of diabetes, age, abdominal obesity, waist-height ratio, impaired fasting glucose (IFG), HOMA2-IR and metabolic syndrome. Early-onset ID was also high (IR 14.77 per 1000 person-years, 95%CI 14.21-15.35), and risk factors included HOMA-IR and IFG. Our ID predictive model included age, hypertriglyceridemia, IFG, hypertension and abdominal obesity as predictors (Dxy = 0.487, c-statistic = 0.741) and had higher predictive accuracy compared to FINDRISC and Cambridge risk scores.

CONCLUSIONS

ID in apparently healthy middle-aged Mexican adults is currently at an alarming rate. The constructed models can be implemented to predict diabetes risk and represent the largest prospective effort for the study metabolic diseases in Latin-American population.