Diabetes Risk Research Articles

Higher remnant cholesterol increases the risk of coronary heart disease and diabetes in postmenopausal women

BackgroundPostmenopausal women represent the demographic increasingly susceptible to cardiovascular and metabolic diseases. Elevated levels of remnant cholesterol (RC) have been implicated in atherosclerosis and insulin resistance.MethodsThis study aimed to investigate the relationship between RC and the prevalence of coronary heart disease (CHD), diabetes, and CHD combined with diabetes in a nationally representative sample of US postmenopausal women using data from the National Health and Nutrition Examination Survey (NHANES) 2007-2018. Multivariate logistic regression models were employed to evaluate the association between RC and the outcomes of interest. Nonlinear associations were assessed using restricted cubic splines (RCS), and subgroup analyses, along with interaction tests, were performed.ResultsA total of 1611 participants were included in the final analysis. Higher RC levels were significantly associated with increased risks of CHD [OR=1.67, 95%CI (1.02, 2.74)], diabetes [OR=1.77, 95%CI (1.22, 2.58)], and CHD combined with diabetes [OR=2.28, 95%CI (1.17, 4.42)] (all P<0.05). Compared to the lowest RC quartile (Q1), the highest quartile (Q4) demonstrated elevated incidences of CHD [OR=1.76, 95%CI (1.04, 2.98)], diabetes [OR=1.81, 95%CI (1.30, 2.53)], and CHD combined with diabetes [OR=3.08, 95%CI (1.29, 7.37)] (all P<0.05). RCS curves indicated a nearly linear relationship between RC and the risks of CHD, diabetes, and CHD combined with diabetes.ConclusionOur study reveals a significant positive correlation between RC levels and the prevalence of CHD, diabetes, and CHD combined with diabetes among postmenopausal women. Understanding these associations could potentially inform targeted prevention and management strategies tailored to this vulnerable population.

Machine learning-based assessment of diabetes risk

Machine learning-based assessment of diabetes risk

The Role of Sudden Weight Loss as an Early Indicator of Diabetes Onset in Prediabetic and Newly Diagnosed Diabetic Patients

Background and Objective: Sudden weight loss is a potential early indicator of metabolic disorders commonly associated with diabetes, although its role in the early detection of the disease has not been extensively studied. Therefore, further exploration is needed to evaluate whether unexplained weight loss can serve as a more significant risk factor or marker for early diabetes detection, as well as to understand the metabolic changes occurring in the body of individuals with diabetes. This study investigates the relationship between unexplained sudden weight loss and early diagnosis of diabetes in prediabetic patients and newly diagnosed diabetic patients. Methods: This research employed a cross-sectional observational design, analyzing the association between sudden weight loss and a diabetes diagnosis using statistical tools such as SPSS. Results: The findings revealed a statistically significant relationship, as indicated by a p-value of 0.001 and an odds ratio of 8.39, suggesting that individuals experiencing unexplained weight loss are eight times more likely to be diagnosed with diabetes. Discussion: These results suggest that sudden weight loss may serve as an important diagnostic clue in identifying individuals at risk for diabetes at an early stage, particularly in high-risk populations. Conclusion: The findings support the need for healthcare providers to consider unexplained weight loss as a potential warning sign for the onset of diabetes, prompting earlier screening and intervention.

A Dual Burden Dilemma: Navigating the Global Impact of Communicable and Non-Communicable Diseases and the Way Forward

The global burden of disease has shifted significantly, with communicable diseases (CDs) like HIV/AIDS, tuberculosis, and malaria increasingly intersecting with the rising prevalence of non-communicable diseases (NCDs) such as cardiovascular diseases, cancers, and diabetes. This narrative review explores the dual burden posed by CDs and NCDs, emphasizing their interconnections, societal impacts, and regional disparities. While CDs continue to challenge healthcare systems in low- and middle-income countries, NCDs dominate global mortality, driven by aging populations, urbanization, and lifestyle changes. The review highlights how infectious agents contribute to chronic diseases, such as hepatitis B leading to liver cancer or COVID-19 exacerbating diabetes and cardiovascular risks. It underscores the necessity for integrated healthcare approaches that address both disease categories to reduce health inequities. Regional and demographic disparities, such as higher disease burdens in sub-Saharan Africa and Southeast Asia, are also discussed, along with their socio-economic drivers. Global efforts, including vaccination programs, lifestyle interventions, and sustainable health policies, are evaluated for their effectiveness and challenges. The review concludes with a call for innovative, equity-focused strategies to mitigate the dual burden and strengthen global health resilience.

Diabetes Prediction Based on Machine Learning

Diabetes mellitus is a growing global health issue with an increasing incidence rate. Traditional methods for predicting diabetes, which rely heavily on clinical data and physical examinations, present challenges such as high costs, time-consuming processes, and difficulties in providing timely and personalized risk assessments. However, with the rise of machine learning (ML), new opportunities have emerged in diabetes prediction, utilizing large-scale data and advanced pattern recognition techniques. This study examines the application of ML in diabetes risk assessment by leveraging electronic health records (EHR) and big data, leading to significant improvements in accuracy and efficiency. The results demonstrate that ML methods can more effectively identify high-risk individuals, facilitating early intervention and contributing to the advancement of diabetes prediction.

Non-linear dose-response relationship between the visceral adiposity index and diabetes in adults with normoglycemia: a cohort study.

Previous studies have identified a positive link between the visceral adiposity index (VAI) and diabetes in specific populations. Our investigation focused on examining this association in normoglycemic adults in Japan. A cohort study of NAGALA (NAfld in the Gifu Area Longitudinal Analysis) was undertaken from 2004 to 2015 in Japan. The link between VAI and diabetes was evaluated using multivariate Cox proportional hazards regression and restricted cubic spline (RCS) regression models. Receiver operating characteristic (ROC) curve analysis was performed to assess the predictive value of the VAI for incident diabetes. Our study included 15,452 participants, with 8,418 men (54.48%) and 7,034 women (45.52%). The average age was 43.71 ± 8.90, and 373 participants (2.41%) developed diabetes. VAI was positively related to diabetes (HR=1.13, 95% CI 1.08-1.18). The inflection point of the non-linear relationship was observed at a VAI value of 4.67. For the VAI values up to 4.67, one unit increase in the VAI related to a 24% increase in new-onset diabetes (HR=1.24, 95% CI 1.12-1.37, p<0.0001). Subgroup analysis detected a more robust relationship in women (HR=1.40, 95% CI 1.14-1.70, p=0.0010). ROC analysis indicated that VAI, with an AUC of 0.7479 (95% CI: 0.7237-0.7720), had good predictive power. Our cohort study validated the positive and non-linear relationship between the VAI and diabetes in normoglycemic adults in Japan. The relevance was more marked in women than in men. For those with a VAI below 4.67, a further reduction in the VAI could potentially lead to a significant decrease in diabetes risk.

The Association Between the C-Reactive ProteinGene Variants rs1130864 and rs2794521 and Obstructive Sleep Apnea in the Iranian Kurdish Population.

Introduction: Obstructive sleep apnea (OSA) syndrome is a widespread multifactorial disorder that raises the risk of cardiovascular disease, diabetes, and Alzheimer's disease. This study aimed to investigate the association between the risk of OSA and two C-reactive protein (CRP) gene variants, rs1130864 and rs2794521. Materials and methods: In this study, 100 patients and 100 controls participated. Among 500 patients with OSA attending the sleep disorder center, 100 were randomly selected from those with apnea/hypopnea symptoms and daytime sleepiness. Polymerase chain reaction and restriction fragment length polymorphism of the CRP gene polymorphisms were used in this investigation. Results: The frequency of the mutant C allele was higher in the patient group than in the control group for the rs2794521 CRP gene variant (p ≤ 0.001), and the C allele elevated the risk of OSA by 2.584 times (odds ratios = 2.584, 95% confidence interval). The frequency of the mutant T allele was higher in the patient group than in the control group for the rs1130864 CRP gene variant, while the frequency of the C allele was higher in the control group, and this difference was statistically significant (p ≤ 0.001). Conclusions: Our findings indicated that rs1130864 and rs2794521 of the CRP gene are associated with increased risk for OSA. Extensive research is required to determine the role of distinct CRP gene variants in OSA.

The protective role of gamma zone peripapillary atrophy in diabetic retinopathy: insights from deep learning and SS-OCT angiography.

To explore the relationship between peripapillary atrophy (PPA) and diabetic retinopathy (DR), and to uncover potential mechanisms using swept-source optical coherence tomography (SS-OCT) angiography. This cross-sectional study included 845 patients with type 2 diabetes (T2DM), who underwent detailed systemic and ophthalmic evaluations. A state-of-the-art deep learning method was employed to precisely identify the parapapillary beta and gamma zones. Based on PPA characteristics, eyes were categorized into four groups: without beta or gamma zone (Group A), isolated beta zone (Group B), isolated gamma zone (Group C), and with both beta and gamma zone (Group D). Digital fundus photography was utilized to diagnose and stage DR severity, while SS-OCT angiography quantified retinal and choroidal vasculature. Participants had a mean age of 66 ± 8.8years, with 437 (51.7%) male. Beta and gamma PPA zones were observed in 574 (67.9%) and 256 (30.3%) eyes, respectively. Beta zone PPA was associated with older age, whereas gamma zone PPA was correlated with longer axial length (AL), lower vessel density, and reduced choroidal thickness. Adjusted analyses revealed that eyes with isolated (Group C) or concurrent (Group D) gamma zone PPA conferred significantly lower DR grade, independent of known risk factors including systemic diabetes risk factors and AL. This study finds that gamma zone PPA is linked to a reduced risk of developing DR. These results imply that the gamma zone may reflect progressive myopia-associated thinning and microvascular depletion in posterior ocular tissues, potentially contributing to structural resilience against DR. This novel insight offers a promising avenue for understanding the interplay between PPA and DR.

Plasma proteomic signatures of adiposity are associated with cardiovascular risk factors and type 2 diabetes risk in a multi-ethnic Asian population.

The biomarkers connecting obesity and cardiometabolic diseases are not fully understood. We aimed to (i) evaluate the associations between body mass index (BMI), waist circumference (WC), and ∼5,000 plasma proteins (SomaScan v4), (ii) identify protein signatures of BMI and WC, and (iii) evaluate the associations between the protein signatures and cardiometabolic health including metabolically unhealthy obesity and type 2 diabetes incidence in the Singapore Multi-Ethnic Cohort (MEC1). Among 410 BMI-associated and 385 WC-associated proteins, we identified protein signatures of BMI and WC and validated them in an independent dataset across two timepoints and externally in the Atherosclerosis Risk in Communities (ARIC) study. The BMI- and WC-protein signatures were highly correlated with total and visceral body fat, respectively. Furthermore, the protein signatures were significantly associated with cardiometabolic risk factors and metabolically unhealthy obesity. In prospective analyses, the protein signatures were strongly associated with type 2 diabetes risk in MEC1 (odds ratio per SD increment in WC-protein signature = 2.84, 95% CI 2.47 to 3.25) and ARIC (hazard ratio = 1.98, 95% CI 1.88 to 2.08). Our protein signatures have potential uses for the monitoring of metabolically unhealthy obesity.

Universal Health Checkups and Risk of Incident Diabetes and Hypertension

Type 2 diabetes and hypertension are obesity-related, noncommunicable diseases becoming increasingly common worldwide. In 2008, Japan launched a nationwide universal health checkup program, Specific Health Checkup (SHC), for the primary prevention of obesity-related diseases, but its effectiveness has been understudied. To investigate the association of the SHC program with incident diabetes and hypertension, using a target trial emulation framework. This retrospective cohort study used data from a longitudinal health care database involving both checkup history and medical encounter records in Japan. Individuals aged 40 to 74 years, without diabetes or hypertension, and without a prior checkup history, were eligible. Individuals were repeatedly assessed for eligibility from April 1, 2008, to March 31, 2020, to assemble sequential cohorts of 78 620 SHC participants and 214 554 nonparticipants. Statistical analysis was conducted from June 8 to December 30, 2023. The composite risk of incident type 2 diabetes or hypertension over a period of up to 10 years, defined as the combination of a newly documented diagnosis and use of relevant medications. A propensity score-weighted survival analysis was conducted to adjust for baseline variables. A series of sensitivity analyses and a negative outcome control analysis were conducted using depression as a benchmark. Sequential cohorts consisted of 78 620 SHC participants (median age, 46 years [IQR, 41-53 years]; 62.7% women) and 214 554 nonparticipants (median age, 49 years [IQR, 44-55 years]; 82.0% women) from 153 084 unique persons, each of whom entered the study cohort a mean (SD) of 1.9 (1.5) times. Within a median follow-up of 4.2 years (IQR, 2.7-6.3 years), the primary end point occurred among 11.2% of all individuals (10.6% of the SHC participants and 11.4% of the nonparticipants), with a lower hazard ratio (HR) among the SHC recipients (HR, 0.90; 95% CI, 0.89-0.92); the difference in cumulative incidence at 10 years was -1.6% (95% CI, -1.8% to -1.3%). The sensitivity analyses showed similar results. The negative control analysis suggested the potential for residual confounding (HR, 1.05; 95% CI, 1.02-1.07); the bias-calibrated HR was 0.86 (95% CI, 0.84-0.89) for the primary outcome. In this cohort study, within a median of 4.2 years of follow-up, SHC recipients had a 9.8% lower risk of incident diabetes and hypertension (13.8% in the bias-calibrated analysis). The cost-effectiveness of the SHC and its transportability to other regions are unclear, requiring future investigations.

The effect of vitamin D3 supplementation on the incidence of type 2 diabetes in healthy older adults not at high risk for diabetes (FIND): a randomised controlled trial.

Vitamin D insufficiency is associated with an elevated risk of type 2 diabetes, but evidence from randomised trials on the benefits of vitamin D supplementation is limited, especially for average-risk populations. The Finnish Vitamin D Trial (FIND) investigated the effects of vitamin D3 supplementation at two different doses on the incidence of type 2 diabetes in a generally healthy older adult population. FIND was a 5 year randomised placebo-controlled, parallel-arm trial among 2271 male and female participants aged ≥60 years and ≥65 years, respectively, from a general Finnish population who were free of CVD or cancer and did not use diabetes medications. The study had three arms: placebo, 1600 IU/day of vitamin D3 or 3200 IU/day of vitamin D3. A non-study group statistician carried out sex-stratified simple randomisation in a 1:1:1 ratio, based on computerised random number generation. The participants, investigators and study staff were masked to group assignment. National health registries were used to collect event data. A representative subcohort of 505 participants had more detailed in-person investigations at months 0, 6, 12 and 24. During the mean follow-up of 4.2 years, there were 38 (5.0%), 31 (4.2%) and 36 (4.7%) type 2 diabetes events in the placebo (n=760), 1600 IU/day vitamin D3 (n=744; vs placebo: HR 0.81; 95% CI 0.50, 1.30) and 3200 IU/day vitamin D3 (n=767; vs placebo: HR 0.92, 95% CI 0.58, 1.45) arms, respectively (p-trend=0.73). When the two vitamin D3 arms were combined and compared with the placebo arm, the HR was 0.86 (95% CI 0.58, 1.29). In the analyses stratified by BMI (<25 kg/m2 [n=813, number of type 2 diabetes events=12], 25-30 kg/m2 [n=1032, number of events=38], ≥30 kg/m2 [n=422, number of events=54]), the HRs in the combined vitamin D3 arms vs the placebo were 0.43 (95% CI 0.14, 1.34), 0.97 (0.50, 1.91) and 1.00 (0.57, 1.75), respectively (p-interaction <0.001). In the subcohort, the mean (SD) baseline serum 25-hydroxyvitamin D3 (25(OH)D3) concentration was 74.5 (18.1) nmol/l. After 12 months, the concentrations were 72.6 (17.7), 99.3 (20.8) and 120.9 (22.1) nmol/l in the placebo, 1600 IU/day vitamin D3 and 3200 IU/day vitamin D3 arms, respectively. In the subcohort, no differences were observed in changes in plasma glucose or insulin concentrations, BMI or waist circumference during the 24 month follow-up (p values ≥0.19). Among generally healthy older adults who are not at high risk for diabetes and who have serum 25(OH)D3 levels that are sufficient for bone health, vitamin D3 supplementation did not significantly reduce the risk of developing diabetes. ClinicalTrials.gov NCT01463813.

Evidence on the effectiveness and equity of population-based policies to reduce the burden of type 2 diabetes: a narrative review

AbstractThere is increasing evidence for the effectiveness of population-based policies to reduce the burden of type 2 diabetes. Yet, there are concerns about the equity effects of some policies, whereby socioeconomically disadvantaged populations are not reached or are adversely affected. There is a lack of knowledge on the effectiveness and equity of policies that are both population based (i.e. targeting both at-risk and low-risk populations) and low agency (i.e. not requiring personal resources to benefit from the policy). In this narrative review, we selected 16 policies that were both population based and low agency and reviewed the evidence on their effectiveness and equity. Substantial evidence suggests that fruit and vegetable subsidies, unhealthy food taxes, mass media campaigns, and school nutrition and physical activity education are effective in promoting healthier lifestyle behaviours. Less evidence was available for mandatory food reformulation, reduced portion sizes, marketing restrictions and restriction of availability and promotion of unhealthy products, although the available evidence suggested that these policies were effective in reducing unhealthy food choices. Effects could rarely be quantified across different studies due to substantial heterogeneity. There is an overall lack of evidence on equity effects of population-based policies, although available studies mostly concluded that the policies had favourable equity effects, with the exception of food-labelling policies. Each of the policies is likely to have a relatively modest effect on population-level diabetes risks, which emphasises the importance of combining different policy measures. Future research should consider the type of evidence needed to demonstrate the real-world effectiveness and equity of population-based diabetes prevention policies. Graphical Abstract

Fuzzy logic and machine learning for diabetes risk prediction using modifiable factors

Diabetes mellitus, a global health concern, includes type 1 diabetes, with an uncontrollable risk, and type 2 diabetes, where risk can be managed through lifestyle modifications. This study examines the impact of modifiable risk factors—diet, physical activity, and body mass index (BMI)—on type 2 diabetes development. Using fuzzy logic, binary variables from a healthcare diabetes dataset were transformed into a fuzzy format, generating three output classes: "no diabetes risk," "possible diabetes risk," and "diabetes risk present." The intermediate class, "possible diabetes risk," serves as an alert for adopting healthier lifestyles to mitigate risk. Machine learning was applied to both the original and fuzzy-transformed datasets. While the original dataset provided binary outputs with moderate accuracy and higher computation times, the fuzzy-transformed dataset yielded more nuanced predictions, reduced computation time, and improved classifier performance. This approach enhances diabetes risk assessment and supports proactive interventions.

Periodontal Disease and Metabolic Syndrome in Women at Prior High Risk for Gestational Diabetes.

This study aimed to assess the association between periodontal disease and metabolic syndrome (MetS) among women at prior high risk for gestational diabetes with the hypothesis that women with MetS show more signs of periodontal disease than women without MetS. A total of 112 women from an original study cohort of 348 women at high risk of gestational diabetes were examined 4-6 years postpartum. Diagnosis of MetS was based on the National Cholesterol Education Program Adult Treatment Panel III diagnostic criteria. Insulin resistance was approximated by the homeostatic model assessment for insulin resistance. Full-mouth examinations and panoramic radiographs provided the total dental index, number of teeth, and decayed, missing, and filled teeth index. Clinical examination assessed bleeding on probing, probing depth, visible plaque index, signs of infection, and clinical attachment levels. The periodontal inflammatory burden index (PIBI) was also calculated. Information on oral health habits, symptoms, and individual opinions on oral health was collected through questionnaires. Five years after delivery, 21% of the women had MetS, and they had more gingivitis compared to those without MetS (bleeding on probing: 52% and 44%, p = 0.011). Women with MetS tended to have more periodontitis than those without (39% and 25%, p = 0.13). A high PIBI correlated with insulin resistance (partial correlation of PIBI and homeostatic model assessment for insulin resistance: 0.25 p < 0.05). Periodontal disease was associated with insulin resistance and MetS in women at prior high risk of developing gestational diabetes.

Biochemical study of the risk of diabetes, prediabetic and insulin resistance in car painters and its association with mercury exposure: a retrospective case-control study.

There is controversy about the effect of mercury (Hg) exposure on developing diabetes and insulin resistance. This study aimed to assess the risk of diabetes and insulin resistance in car painters using biochemical markers and serum Hg levels. A retrospective case-control study involving 210 male participants aged between 25 and 50years. The participants were divided into two groups: Car painters for at least one year and healthy people who had not worked as car painters and had no health concerns or chronic diseases. The serum levels of Hg, MDA (malondialdehyde), interleukin (IL)-1β, visfatin, fasting insulin, and fasting blood glucose (FBG) were evaluated. Serum Hg levels were significantly higher in car painters compared to the control group (19.00±7.20 vs. 8.339±3.916μg/L, P-value<0.001). Serum levels of visfatin, MDA, insulin, FBG, and IL-1β were significantly higher in the car painter compared to the control (P-value<0.001). There was a significantly higher proportion of people with diabetes in car painters compared to control (8.6% vs. 0%) and higher prediabetic (30.5% vs. 13.3%, P-value<0.001). In car painter workers, levels of Hg were significantly higher in DM compared to prediabetic and normoglycemic car painter workers (27.01±1.59, 23.98±4.31, and 15.39±6.41μg/mL, respectively, P-value<0.001); additionally, levels of Hg were significantly higher car painter with insulin resistance compared to non-insulin resistance workers (21.18±7.29 vs. 16.79±16.7μg/mL, P-value<0.001). Increased serum Hg in car painters increases the risk of insulin resistance and diabetes/prediabetes status.

Variation in Lipoprotein(a) Response to Potent Lipid Lowering: The Role of Apolipoprotein (a) Isoform size

BackgroundLipoprotein(a) [Lp(a)] is a driver of residual cardiovascular risk. Proprotein Convertase Subtilisin/Kexin Type 9 inhibitors (PCSK9i) decrease Lp(a) with significant heterogeneity in response. We investigated contributors to the heterogeneous response. MethodsCHOlesterol Reduction and Residual Risk in Diabetes (CHORD) was a prospective study examining lipid lowering in participants with an LDL-C >100 mg/dl with and without diabetes (DM) on lipid lowering therapy (LLT) for 30-days with evolocumab 140 mg every 14 days combined with either atorvastatin 80 mg or ezetimibe 10 mg daily. Lp(a) level was measured by immunoturbidometry, and the apolipoprotein a [apo(a)] isoform size was measured by denaturing agarose gel electrophoresis and western blotting. We examined the change in Lp(a) levels from baseline to 30 days. ResultsAmong 150 participants (mean age 50 years, 58% female, 50% non-White, 17% Hispanic, 50% diabetes), median (IQR) Lp(a) was 27.5 (8-75) mg/dL at baseline and 23 (3-68) mg/dL at 30 days, leading to a 10% (0-36) median reduction (P<0.001). Among 73 (49%) participants with Lp(a) ≥30 mg/dL at baseline, there was a 15% (3-25) median reduction in Lp(a) (P<0.001). While baseline Lp(a) level was not correlated with change in Lp(a) (r=0.04, P=0.59), apo(a) size directly correlated with Lp(a) reduction (P<0.001). After adjustment for age, sex, race/ethnicity, DM, and type of LLT, apo(a) size remained positively associated with a reduction in Lp(a) (Beta 0.95, 95%CI, 0.93-0.97, p<0.001). ConclusionOur data demonstrate variation in Lp(a) reduction with potent LLT. Change in Lp(a) was strongly associated with apo(a) isoform size.

Pentachlorophenol increases diabetes risk by damaging β-cell secretion and disrupting gut microbial-related amino acids and fatty acids biosynthesis

Pentachlorophenol (PCP), a ubiquitous environmental pollutant, has been reported as a possible contributor to diabetes. However, evidence for general population is scarce while related mechanisms are largely unknown. Using a representative population-based case-control study in Beijing (n=1796), we found a positive association between PCP exposure and diabetes risk with the odds ratio reaching 1.68 (95% confidence interval: 1.30 to 2.18). A further rat experiment revealed that low-dose PCP mimicking real-world human exposure can significantly impair glycemic homeostasis by inducing pancreatic β-cell dysfunction, with non-linear dose-response relationships. Subsequent multi-omics analysis suggested that low-dose PCP led to notable gut microbiota dysbiosis (especially the species from genus Prevotella, such as intermedia, dentalis, ruminicola, denticola, melaninogenica, and oris), decreased serum amino acids (L-phenylalanine, L-tyrosine, and L-tryptophan) and increased serum fatty acids (oleic and palmitic acid) in rats, while strong correlations were observed among alterations of gut microbes, serum metabolites and glycemic-related biomarkers (e.g., fasting blood glucose and insulin). Collectively, these results imply PCP may increase diabetes risk by disrupting gut microbial-related amino acids and fatty acids biosynthesis. This will help guide future in-depth studies on the roles of PCP in the development of human diabetes.

Ensemble stacking classifier model for prediction of diabetes

Diabetes, being a chronic condition, possesses the capacity to instigate a global healthcare catastrophe. This condition can be managed and potentially cured with prompt diagnosis and treatment. Integrating machine learning technology with medical science enables precise prognosis of an individual’s susceptibility to diabetes. The proposed work presents the ensemble stacking classifier model. This efficient and effective diabetes prediction model predicts a patient’s diabetes risk by combining the output of multiple machine-learning techniques into a single model. The performance parameters of four distinct machine learning classification algorithms K-nearest neighbors (KNN), random forest (RF), support vector machine (SVM), and decision tree (DT) are compared in this study with those of the proposed stacked classifier model. The suggested model is developed using ensemble methods, where the previously discussed algorithms are integrated to create the base classifier layer of the stack classifier. The meta-classifier is implemented in the form of the logistic regression (LR) algorithm. Upon evaluating the performance of both the developed model and its algorithms, it is proved that the proposed model attains a testing accuracy of 88.5%, surpassing the accuracy of all baseline classification algorithms. As a result, this work determines that the ensemble stacking classifier model exhibits higher prediction accuracy than the base classifier algorithms. This finding underscores the model’s potential as a viable instrument for predicting diabetes in individuals.

Positive association of oscillometrically estimated baseline arterial stiffness with incident diabetes and prediabetes: A large population-based cohort study.

This large population-based study aimed to investigate whether arterial stiffness, assessed oscillometrically, was associated with incident diabetes/prediabetes. The study sample comprised 4240 participants from the Vitamin D Assessment (ViDA) Study (mean±SD age = 66 ± 8). Arterial stiffness was assessed from 5 April 2011-6 November 2012 by way of aortic PWV (aPWV) and estimated carotid-femoral PWV (ecfPWV). Incident diabetes/prediabetes was determined by linkage to dispensed prescription and national hospital discharge registers. Cox proportional hazards regression was used to assess the risk of diabetes/prediabetes in relation to chosen arterial stiffness measures both overall and over quartiles. During a mean±SD follow-up of 10.5 ± 0.4 years, 470 participants developed diabetes/prediabetes. Following adjustment for potential confounders, aPWV (hazard ratio (HR) per SD increase, 1.40, 95 % CI, 1.19-1.64) was associated with the incidence of diabetes. The risk of incident diabetes was, compared to the first quartile, higher in the fourth quartile of aPWV (HR, 1.98, 95 %CI, 1.26-3.11)(Ptrend=0.01). Arterial stiffness, as measured by aPWV may be a useful predictor of incident diabetes that can be utilized in clinical practice.

Unearthing Insights into Metabolic Syndrome by Linking Drugs, Targets, and Gene Expressions Using Similarity Measures and Graph Theory.

Metabolic syndrome (MetS) is a group of metabolic disorders that includes obesity in combination with at least any two of the following conditions, i.e., insulin resistance, high blood pressure, low HDL cholesterol, and high triglycerides level. Treatment of this syndrome is challenging because of the multiple interlinked factors that lead to increased risks of type-2 diabetes and cardiovascular diseases. This study aims to conduct extensive in silico analysis to (i) find central genes that play a pivotal role in MetS and (ii) propose suitable drugs for therapy. Our objective is to first create a drug-disease network and then identify novel genes in the drug-disease network with strong associations to drug targets, which can help in increasing the therapeutical effects of different drugs. In the future, these novel genes can be used to calculate drug synergy and propose new drugs for the effective treatment of MetS. For this purpose, we (i) investigated associated drugs and pathways for MetS, (ii) employed eight different similarity measures to construct eight gene regulatory networks, (iii) chose an optimal network, where a maximum number of drug targets were central, (iv) determined central genes exhibiting strong associations with these drug targets and associated disease-causing pathways, and lastly (v) employed these candidate genes to propose suitable drugs. Our results indicated (i) a novel drug-disease network complex, with (ii) novel genes associated with MetS. Our developed drug-disease network complex closely represents MetS with associated novel findings and markers for an improved understanding of the disease and suggested therapy.