HAPT2D: high accuracy of prediction of T2D with a model combining basic and advanced data depending on availability

A dynamic probabilistic model of the onset and interaction of cardio-metabolic comorbidities on an ageing adult population

Comorbidity is widespread in the ageing population, implying multiple and complex medical needs for individuals and a public health burden. Determining risk factors and predicting comorbidity development can help identify at-risk subjects and design prevention strategies. Using socio-demographic and clinical data from approximately 11,000 subjects monitored over 11 years in the English Longitudinal Study of Ageing, we develop a dynamic Bayesian network (DBN) to model the onset and interaction of three cardio-metabolic comorbidities, namely type 2 diabetes (T2D), hypertension, and heart problems. The DBN allows us to identify risk factors for developing each morbidity, simulate ageing progression over time, and stratify the population based on the risk of outcome occurrence. By applying hierarchical agglomerative clustering to the simulated, dynamic risk of experiencing morbidities, we identified patients with similar risk patterns and the variables contributing to their discrimination. The network reveals a direct joint effect of biomarkers and lifestyle on outcomes over time, such as the impact of fasting glucose, HbA1c, and BMI on T2D development. Mediated cross-relationships between comorbidities also emerge, showcasing the interconnected nature of these health issues. The model presents good calibration and discrimination ability, particularly in predicting the onset of T2D (iAUC-ROC = 0.828, iAUC-PR = 0.294) and survival (iAUC-ROC = 0.827, iAUC-PR = 0.311). Stratification analysis unveils two distinct clusters for all comorbidities, effectively discriminated by variables like HbA1c for T2D and age at baseline for heart problems. The developed DBN constitutes an effective, highly-explainable predictive risk tool for simulating and stratifying the dynamic risk of developing cardio-metabolic comorbidities. Its use could help identify the effects of risk factors and develop health policies that prevent the occurrence of comorbidities.

Prediction of type 2 diabetes mellitus onset using logistic regression-based scorecards

Background

Type 2 diabetes (T2D) accounts for ~90% of all cases of diabetes, resulting in an estimated 6.7 million deaths in 2021, according to the International Diabetes Federation. Early detection of patients with high risk of developing T2D can reduce the incidence of the disease through a change in lifestyle, diet, or medication. Since populations of lower socio-demographic status are more susceptible to T2D and might have limited resources or access to sophisticated computational resources, there is a need for accurate yet accessible prediction models.

Methods

In this study, we analyzed data from 44,709 nondiabetic UK Biobank participants aged 40-69, predicting the risk of T2D onset within a selected time frame (mean of 7.3 years with an SD of 2.3 years). We started with 798 features that we identified as potential predictors for T2D onset. We first analyzed the data using gradient boosting decision trees, survival analysis, and logistic regression methods. We devised one nonlaboratory model accessible to the general population and one more precise yet simple model that utilizes laboratory tests. We simplified both models to an accessible scorecard form, tested the models on normoglycemic and prediabetes subcohorts, and compared the results to the results of the general cohort. We established the nonlaboratory model using the following covariates: sex, age, weight, height, waist size, hip circumference, waist-to-hip ratio, and body mass index. For the laboratory model, we used age and sex together with four common blood tests: high-density lipoprotein (HDL), gamma-glutamyl transferase, glycated hemoglobin, and triglycerides. As an external validation dataset, we used the electronic medical record database of Clalit Health Services.

Results

The nonlaboratory scorecard model achieved an area under the receiver operating curve (auROC) of 0.81 (95% confidence interval [CI] 0.77-0.84) and an odds ratio (OR) between the upper and fifth prevalence deciles of 17.2 (95% CI 5-66). Using this model, we classified three risk groups, a group with 1% (0.8-1%), 5% (3-6%), and the third group with a 9% (7-12%) risk of developing T2D. We further analyzed the contribution of the laboratory-based model and devised a blood test model based on age, sex, and the four common blood tests noted above. In this scorecard model, we included age, sex, glycated hemoglobin (HbA1c%), gamma glutamyl-transferase, triglycerides, and HDL cholesterol. Using this model, we achieved an auROC of 0.87 (95% CI 0.85-0.90) and a deciles' OR of ×48 (95% CI 12-109). Using this model, we classified the cohort into four risk groups with the following risks: 0.5% (0.4-7%); 3% (2-4%); 10% (8-12%); and a high-risk group of 23% (10-37%) of developing T2D. When applying the blood tests model using the external validation cohort (Clalit), we achieved an auROC of 0.75 (95% CI 0.74-0.75). We analyzed several additional comprehensive models, which included genotyping data and other environmental factors. We found that these models did not provide cost-efficient benefits over the four blood test model. The commonly used German Diabetes Risk Score (GDRS) and Finnish Diabetes Risk Score (FINDRISC) models, trained using our data, achieved an auROC of 0.73 (0.69-0.76) and 0.66 (0.62-0.70), respectively, inferior to the results achieved by the four blood test model and by the anthropometry models.

Conclusions

The four blood test and anthropometric models outperformed the commonly used nonlaboratory models, the FINDRISC and the GDRS. We suggest that our models be used as tools for decision-makers to assess populations at elevated T2D risk and thus improve medical strategies. These models might also provide a personal catalyst for changing lifestyle, diet, or medication modifications to lower the risk of T2D onset.

Funding

The funders had no role in study design, data collection, interpretation, or the decision to submit the work for publication.

Derivation and Validation of a Prediction Model for Predicting the 5-Year Incidence of Type 2 Diabetes in Non-Obese Adults: A Population-Based Cohort Study

PURPOSE

The aim of this study was to derivate and validate a nomogram based on independent predictors to better evaluate the 5-year risk of T2D in non-obese adults.

PATIENTS AND METHODS

This is a historical cohort study from a collection of databases that included 12,940 non-obese participants without diabetes at baseline. All participants were randomised to a derivation cohort (n = 9651) and a validation cohort (n = 3289). In the derivation cohort, the least absolute shrinkage and selection operator (LASSO) regression model was used to determine the optimal risk factors for T2D. Multivariate Cox regression analysis was used to establish the nomogram of T2D prediction. The receiver operating characteristic (ROC) curve, C-index, calibration curve, and decision curve analysis were performed by 1000 bootstrap resamplings to evaluate the discrimination ability, calibration, and clinical practicability of the nomogram.

RESULTS

After LASSO regression analysis of the derivation cohort, it was found that age, fatty liver, γ-glutamyltranspeptidase, triglycerides, glycosylated hemoglobin A1c and fasting plasma glucose were risk predictors, which were integrated into the nomogram. The C-index of derivation cohort and validation cohort were 0.906 [95% confidence interval (CI), 0.878-0.934] and 0.837 (95% CI, 0.760-0.914), respectively. The AUC of 5-year T2D risk in the derivation cohort and validation cohort was 0.916 (95% CI, 0.889-0.943) and 0.829 (95% CI, 0.753-0.905), respectively. The calibration curve indicated that the predicted probability of nomogram is in good agreement with the actual probability. The decision curve analysis demonstrated that the predicted nomogram was clinically useful.

CONCLUSION

Our nomogram can be used as a reasonable, affordable, simple, and widely implemented tool to predict the 5-year risk of T2D in non-obese adults. With this model, early identification of high-risk individuals is helpful to timely intervene and reduce the risk of T2D in non-obese adults.

Early Predictors in the Onset of Type 2 Diabetes at Different Fasting Blood Glucose Levels

PURPOSE

This study investigates the possible roles and potential prediction ability of metabolic parameters in the early development of T2D by detecting their serum levels at different fasting blood glucose (FBG) levels.

METHODS

The subjects were included and divided into normal glucose tolerance (NGT), prediabetes (PD), and T2Dsubgroups. Apart from detecting the levels of routine biochemical parameters, fasting serum insulin (FINS), 25(OH)D, thioredoxin-interacting protein (TXNIP), thioredoxin (TRX), and NOD-like receptor family, pyrin domain-containing 3 (NLRP3) were detected. β-cell dysfunction (HOMA-β) and insulin resistance (HOMA-IR) were assessed by homeostasis model assessment. Both univariate and multivariate logistic regression analyses were used to estimate the risk of metabolic parameters, and their optimal cut-off values were obtained in the receiver operating characteristic (ROC) curve analysis and the Youden index.

RESULTS

Among the 207 subjects, aged from 20 to 60 years (44.62+12.92) contain 118 males and 89 females. There was a significantly lower trend of TRX, HOMA-β, and 25(OH)D following the higher FBG level among these three subgroups, while a significantly higher trend of all the other metabolic parameters. The multivariate analysis showed that subjects with higher values of TRX, HOMA-β, and 25(OH)D had a significantly lower risk for patients to be diagnosed as PD (aOR: 0.945, 0.961, and 0.543) and T2D (aOR: 0.912, 0.947, 0.434). Under the reliable 95% CI, TXNIP with a cut-off value of 119.27 showed the highest AUC value, sensitivity, and specificity (AUC: 0.981, 95% CI: 0.8524-0.9839, 91.49%, and 83.33%) to diagnose PD. FINS with a cut-off value of 28.1 also showed the highest ones (AUC=0.9872, 95% CI: 0.9753-0.9992, 100%, and 92.91%) to diagnose T2D.

CONCLUSION

Early prediction of T2D is vital for timely intervention. Based on the FBG ≥100.8 mg/dl, the results provide evidence that 25(OH)D might be the protective factor in the early development of T2D. Besides, TXNIP and FINS might be the predictor for PD and T2D, respectively.

Low-cost exercise interventions improve long-term cardiometabolic health independently of a family history of type 2 diabetes: a randomized parallel group trial

INTRODUCTION

To investigate the effect of an exercise prescription and a 1-year supervised exercise intervention, and the modifying effect of the family history of type 2 diabetes (FH), on long-term cardiometabolic health.

RESEARCH DESIGN AND METHODS

For this prospective randomized trial, we recruited non-diabetic participants with poor fitness (n=1072, 30-70 years). Participants were randomly assigned with stratification for FH either in the exercise prescription group (PG, n=144) or the supervised exercise group (EG, n=146) group and compared with a matched control group from the same population study (CON, n=782). The PG and EG received exercise prescriptions. In addition, the EG attended supervised exercise sessions two times a week for 60 min for 12 months. Cardiometabolic risk factors were measured at baseline, 1 year, 5 years, and 6 years. The CON group received no intervention and was measured at baseline and 6 years.

RESULTS

The EG reduced their body weight, waist circumference, diastolic blood pressure, and low-density lipoprotein-cholesterol (LDL-C) but not physical fitness (p=0.074) or insulin or glucose regulation (p>0.1) compared with the PG at 1 year and 5 years (p≤0.011). The observed differences were attenuated at 6 years; however, participants in the both intervention groups significantly improved their blood pressure, high-density lipoprotein-cholesterol, and insulin sensitivity compared with the population controls (p≤0.003). FH modified LDL-C and waist circumference responses to exercise at 1 year and 5 years.

CONCLUSIONS

Low-cost physical activity programs have long-term beneficial effects on cardiometabolic health regardless of the FH of diabetes. Given the feasibility and low cost of these programs, they should be advocated to promote cardiometabolic health.

TRIAL REGISTRATION NUMBER

ClinicalTrials.gov identifier NCT02131701.

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.

The PULSE Project: A Case of Use of Big Data Uses Toward a Cohomprensive Health Vision of City Well Being

Despite the silent effects sometimes hidden to the major audience, air pollution is becoming one of the most impactful threat to global health. Cities are the places where deaths due to air pollution are concentrated most.

In order to correctly address intervention and prevention thus is essential to assest the risk and the impacts of air pollution spatially and temporally inside the urban spaces. PULSE aims to design and build a large-scale data management system enabling real time analytics of health, behaviour and environmental data on air quality. The objective is to reduce the environmental and behavioral risk of chronic disease incidence to allow timely and evidence-driven management of epidemiological episodes linked in particular to two pathologies; asthma and type 2 diabetes in adult populations. developing a policy-making across the domains of health, environment, transport, planning in the PULSE test bed cities.

Baseline Modelling and Composite Representation of Unobtrusively (IoT) Sensed Behaviour Changes Related to Urban Physical Well-Being

We present the grounding approach, deployment and preliminary validation of the elementary devised model of physical well-being in urban environments, summarizing the heterogeneous personal Big Data (on physical activity/exercise, walking, cardio-respiratory fitness, quality of sleep and related lifestyle and health habits and status, continuously collected for over a year mainly through wearable IoT devices and survey instruments in 7 global testbed cities) into 5 composite domain indicators/indexes convenient for interpretation and use in predictive public health and preventive interventions. The approach is based on systematized comprehensive domain knowledge implemented through range/threshold-based rules from institutional and study recommendations, combined with statistical methods, and will serve as a representative and performance benchmark for evolution and evaluation of more complex and advanced well-being models for the aimed predictive analytics (incorporating machine learning methods) in subsequent development underway.

A Dynamic Bayesian Network model for the simulation of Amyotrophic Lateral Sclerosis progression

BACKGROUND

Amyotrophic lateral sclerosis (ALS) is an adult-onset neurodegenerative disease progressively affecting upper and lower motor neurons in the brain and spinal cord. Mean life expectancy is three to five years, with paralysis of muscles, respiratory failure and loss of vital functions being the common causes of death. Clinical manifestations of ALS are heterogeneous due to the mix of anatomic regions involvement and the variability in disease course; consequently, diagnosis and prognosis at the level of individual patient is really challenging. Prediction of ALS progression and stratification of patients into meaningful subgroups have been long-standing interests to clinical practice, research and drug development.

METHODS

We developed a Dynamic Bayesian Network (DBN) model on more than 4500 ALS patients included in the Pooled Resource Open-Access ALS Clinical Trials Database (PRO-ACT), in order to detect probabilistic relationships among clinical variables and identify risk factors related to survival and loss of vital functions. Furthermore, the DBN was used to simulate the temporal evolution of an ALS cohort predicting survival and the time to impairment of vital functions (communication, swallowing, gait and respiration). A first attempt to stratify patients by risk factors and simulate the progression of ALS subgroups was also implemented.

RESULTS

The DBN model provided the prediction of ALS most probable trajectories over time in terms of important clinical outcomes, including survival and loss of autonomy in functional domains. Furthermore, it allowed the identification of biomarkers related to patients' clinical status as well as vital functions, and unrevealed their probabilistic relationships. For instance, DBN found that bicarbonate and calcium levels influence survival time; moreover, the model evidenced dependencies over time among phosphorus level, movement impairment and creatinine. Finally, our model provided a tool to stratify patients into subgroups of different prognosis studying the effect of specific variables, or combinations of them, on either survival time or time to loss of autonomy in specific functional domains.

CONCLUSIONS

The analysis of the risk factors and the simulation allowed by our DBN model might enable better support for ALS prognosis as well as a deeper insight into disease manifestations, in a context of a personalized medicine approach.

1-Hour Post-OGTT Glucose Improves the Early Prediction of Type 2 Diabetes by Clinical and Metabolic Markers

CONTEXT

Early prediction of dysglycemia is crucial to prevent progression to type 2 diabetes. The 1-hour postload plasma glucose (PG) is reported to be a better predictor of dysglycemia than fasting plasma glucose (FPG), 2-hour PG, or glycated hemoglobin (HbA1c).

OBJECTIVE

To evaluate the predictive performance of clinical markers, metabolites, HbA1c, and PG and serum insulin (INS) levels during a 75-g oral glucose tolerance test (OGTT).

DESIGN AND SETTING

We measured PG and INS levels at 0, 30, 60, and 120 minutes during an OGTT in 543 participants in the Botnia Prospective Study, 146 of whom progressed to type 2 diabetes within a 10-year follow-up period. Using combinations of variables, we evaluated 1527 predictive models for progression to type 2 diabetes.

RESULTS

The 1-hour PG outperformed every individual marker except 30-minute PG or mannose, whose predictive performances were lower but not significantly worse. HbA1c was inferior to 1-hour PG according to DeLong test P value but not false discovery rate. Combining the metabolic markers with PG measurements and HbA1c significantly improved the predictive models, and mannose was found to be a robust metabolic marker.

CONCLUSIONS

The 1-hour PG, alone or in combination with metabolic markers, is a robust predictor for determining the future risk of type 2 diabetes, outperforms the 2-hour PG, and is cheaper to measure than metabolites. Metabolites add to the predictive value of PG and HbA1c measurements. Shortening the standard 75-g OGTT to 1 hour improves its predictive value and clinical usability.

The associations of daylight and melatonin receptor 1B gene rs10830963 variant with glycemic traits: the prospective PPP-Botnia study

BACKGROUND

Seasonal variation in glucose metabolism might be driven by changes in daylight. Melatonin entrains circadian regulation and is directly associated with daylight. The relationship between melatonin receptor 1B gene variants with glycemic traits and type 2 diabetes is well established. We studied if daylight length was associated with glycemic traits and if it modified the relationship between melatonin receptor 1B gene rs10830963 variant and glycemic traits.

MATERIALS

A population-based sample of 3422 18-78-year-old individuals without diabetes underwent an oral glucose tolerance test twice, an average 6.8 years (SD = 0.9) apart and were genotyped for rs10830963. Daylight data was obtained from the Finnish Meteorological Institute.

RESULTS

Cross-sectionally, more daylight was associated with lower fasting glucose, but worse insulin sensitivity and secretion at follow-up. Longitudinally, individuals studied on lighter days at follow-up than at baseline showed higher glucose values during the oral glucose tolerance test and lower Corrected Insulin Response at follow-up. GG genotype carriers in the rs10830963 became more insulin resistant during follow-up if daylight length was shorter at follow-up than at baseline.

CONCLUSIONS

Our study shows that individual glycemic profiles may vary according to daylight, MTNR1B genotype and their interaction. Future studies may consider taking daylight length into account. Key messages In Western Finland, the amount daylight follows an extensive annual variation ranging from 4 h 44 min to 20 h 17 min, making it ideal to study the associations between daylight and glycemic traits. Moreover, this allows researchers to explore if the relationship between the melatonin receptor 1B gene rs10830963 variant and glycemic traits is modified by the amount of daylight both cross-sectionally and longitudinally. This study shows that individuals, who participated in the study on lighter days at the follow-up than at the baseline, displayed to a greater extent worse glycemic profiles across the follow-up. Novel findings from the current study show that in the longitudinal analyses, each addition of the minor G allele of the melatonin receptor 1B gene rs10830963 was associated with worsening of fasting glucose values and insulin secretion across the 6.8-year follow-up. Importantly, this study shows that in those with the rs10830963 GG genotype, insulin sensitivity deteriorated the most significantly across the 6.8-year follow-up if the daylight length on the oral glucose tolerance testing date at the follow-up was shorter than at the baseline. Taken together, the current findings suggest that the amount of daylight may affect glycemic traits, especially fasting glucose and insulin secretion even though the effect size is small. The association can very according to the rs10830963 risk variant. Further research is needed to elucidate the mechanisms behind these associations.