Dataset Information

Multiple Biomarkers Improved Prediction for the Risk of Type 2 Diabetes Mellitus in Singapore Chinese Men and Women.

ABSTRACT: BACKGROUND:Multiple biomarkers have performed well in predicting type 2 diabetes mellitus (T2DM) risk in Western populations. However, evidence is scarce among Asian populations. METHODS:Plasma triglyceride-to-high density lipoprotein (TG-to-HDL) ratio, alanine transaminase (ALT), high-sensitivity C-reactive protein (hs-CRP), ferritin, adiponectin, fetuin-A, and retinol-binding protein 4 were measured in 485 T2DM cases and 485 age-and-sex matched controls nested within the prospective Singapore Chinese Health Study cohort. Participants were free of T2DM at blood collection (1999 to 2004), and T2DM cases were identified at the subsequent follow-up interviews (2006 to 2010). A weighted biomarker score was created based on the strengths of associations between these biomarkers and T2DM risks. The predictive utility of the biomarker score was assessed by the area under receiver operating characteristics curve (AUC). RESULTS:The biomarker score that comprised of four biomarkers (TG-to-HDL ratio, ALT, ferritin, and adiponectin) was positively associated with T2DM risk (P trend <0.001). Compared to the lowest quartile of the score, the odds ratio was 12.0 (95% confidence interval [CI], 5.43 to 26.6) for those in the highest quartile. Adding the biomarker score to a base model that included smoking, history of hypertension, body mass index, and levels of random glucose and insulin improved AUC significantly from 0.81 (95% CI, 0.78 to 0.83) to 0.83 (95% CI, 0.81 to 0.86; P=0.002). When substituting the random glucose levels with glycosylated hemoglobin in the base model, adding the biomarker score improved AUC from 0.85 (95% CI, 0.83 to 0.88) to 0.86 (95% CI, 0.84 to 0.89; P=0.032). CONCLUSION:A composite score of blood biomarkers improved T2DM risk prediction among Chinese.

SUBMITTER: Wang Y

PROVIDER: S-EPMC7188981 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Gestational diabetes mellitus (GDM) is closely related to adverse pregnancy outcomes and other diseases. Early intervention in pregnant women who are at high risk of developing GDM could help prevent adverse health consequences. The study aims to develop a simple model using the stacking ensemble method to predict GDM for women in the first trimester based on easily available factors. We used the data from the Chinese Pregnant Women Cohort Study from July 2017 to November 2018. A total of 6,848 pregnant women in the first trimester were included in the analysis. Logistic regression (LR), random forest (RF), and extreme gradient boosting (XGBoost) were considered as base learners. Optimal feature subsets for each learner were chosen by using recursive feature elimination cross-validation. Then, we built a pipeline to process imbalance data, tune hyperparameters, and evaluate model performance. The learners with the best hyperparameters were employed in the first layer of the proposed stacking method. Their predictions were obtained using optimal feature subsets and served as meta-learner's inputs. Another LR was used as a meta-learner to obtain the final prediction results. Accuracy, specificity, error rate, and other metrics were calculated to evaluate the performance of the models. A paired samples t-test was performed to compare the model performance. In total, 967 (14.12%) women developed GDM. For base learners, the RF model had the highest accuracy (0.638 (95% confidence interval (CI) 0.628-0.648)) and specificity (0.683 (0.669-0.698)) and lowest error rate (0.362 (0.352-0.372)). The stacking method effectively improved the accuracy (0.666 (95% CI 0.663-0.670)) and specificity (0.725 (0.721-0.729)) and decreased the error rate (0.333 (0.330-0.337)). The differences in the performance between the stacking method and RF were statistically significant. Our proposed stacking method based on easily available factors has better performance than other learners such as RF.

Project description:BackgroundDiabetes is reported to be linked to poorer cognitive function. The purpose of this study is to examine (a) clinical correlation between cognitive function and the biochemical perturbations in T2DM, and (b) the impact of statin treatment on cognitive function in diabetic subjects.MethodsForty Singaporean Chinese males with diabetes and twenty Singaporean Chinese males without diabetes were recruited for this study. Twenty-two of the diabetic subjects were on statin therapy and all subjects were non-demented. This was a 2-period non-interventional case-control study in which subjects were assessed for cognitive function in period 1 and blood samples taken over 2 periods, approximately 1 week apart. Blood was collected to determine the level of total cholesterol, high-density lipoprotein (HDL), low-density lipoprotein (LDL), triglycerides, glucose and insulin. Cognitive performance was measured by a neuropsychological battery covering domains of attention, language, verbal and visual memory, visuomotor speed and executive function. Z-scores were derived for each cognitive domain using the mean and standard deviations (SDs), and they were used to compare between (a) diabetic and non-diabetic groups, and (b) diabetic subjects with and without statin treatment. ANCOVAs with age, education, BMI, and the duration of diabetes as covariates were employed to examine differences in mean score of cognitive domains and subtests between the two groups.ResultsOverall cognitive function was similar among diabetics and age matched non-diabetic controls. Among diabetic statin users, HDL, LDL and total cholesterol were negatively correlated with executive function, whereas peripheral insulin levels and insulin resistance were negatively associated with attention.ConclusionDiabetic statin users were likely to have poorer performance in attention and executive function. Increasing levels of the peripheral biomarkers are likely to contribute to poorer cognitive performance.

Dataset Information

Multiple Biomarkers Improved Prediction for the Risk of Type 2 Diabetes Mellitus in Singapore Chinese Men and Women.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets