Dataset Information

Genotype prediction of adult type 2 diabetes from adolescence in a multiracial population.

ABSTRACT: Understanding the risk for type 2 diabetes (T2D) early in the life course is important for prevention. Whether genetic information improves prediction models for diabetes from adolescence into adulthood is unknown.With the use of data from 1030 participants in the Bogalusa Heart Study aged 12 to 18 followed into middle adulthood, we built Cox models for incident T2D with risk factors assessed in adolescence (demographics, family history, physical examination, and routine biomarkers). Models with and without a 38 single-nucleotide polymorphism diabetes genotype score were compared by C statistics and continuous net reclassification improvement indices.Participant mean (± SD) age at baseline was 14.4 ± 1.6 years, and 32% were black. Ninety (8.7%) participants developed T2D over a mean 26.9 ± 5.0 years of follow-up. Genotype score significantly predicted T2D in all models. Hazard ratios ranged from 1.09 per risk allele (95% confidence interval 1.03-1.15) in the basic demographic model to 1.06 (95% confidence interval 1.00-1.13) in the full model. The addition of genotype score did not improve the discrimination of the full clinical model (C statistic 0.756 without and 0.760 with genotype score). In the full model, genotype score had weak improvement in reclassification (net reclassification improvement index 0.261).Although a genotype score assessed among white and black adolescents is significantly associated with T2D in adulthood, it does not improve prediction over clinical risk factors. Genetic screening for T2D in its current state is not a useful addition to adolescents' clinical care.

SUBMITTER: Vassy JL

PROVIDER: S-EPMC3483893 | biostudies-literature | 2012 Nov

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Genotype prediction of adult type 2 diabetes from adolescence in a multiracial population.

Vassy Jason L JL Dasmahapatra Pronabesh P Meigs James B JB Schork Nicholas J NJ Magnussen Costan G CG Chen Wei W Raitakari Olli T OT Pencina Michael J MJ Jamal Seema M SM Berenson Gerald S GS Goodman Elizabeth E

Pediatrics 20121015 5

<h4>Background</h4>Understanding the risk for type 2 diabetes (T2D) early in the life course is important for prevention. Whether genetic information improves prediction models for diabetes from adolescence into adulthood is unknown.<h4>Methods</h4>With the use of data from 1030 participants in the Bogalusa Heart Study aged 12 to 18 followed into middle adulthood, we built Cox models for incident T2D with risk factors assessed in adolescence (demographics, family history, physical examination, a ...[more]

PMID: 23071215

Similar Datasets

Project description:BackgroundGenotype-phenotype predictions are of great importance in genetics. These predictions can help to find genetic mutations causing variations in human beings. There are many approaches for finding the association which can be broadly categorized into two classes, statistical techniques, and machine learning. Statistical techniques are good for finding the actual SNPs causing variation where Machine Learning techniques are good where we just want to classify the people into different categories. In this article, we examined the Eye-color and Type-2 diabetes phenotype. The proposed technique is a hybrid approach consisting of some parts from statistical techniques and remaining from Machine learning.ResultsThe main dataset for Eye-color phenotype consists of 806 people. 404 people have Blue-Green eyes where 402 people have Brown eyes. After preprocessing we generated 8 different datasets, containing different numbers of SNPs, using the mutation difference and thresholding at individual SNP. We calculated three types of mutation at each SNP no mutation, partial mutation, and full mutation. After that data is transformed for machine learning algorithms. We used about 9 classifiers, RandomForest, Extreme Gradient boosting, ANN, LSTM, GRU, BILSTM, 1DCNN, ensembles of ANN, and ensembles of LSTM which gave the best accuracy of 0.91, 0.9286, 0.945, 0.94, 0.94, 0.92, 0.95, and 0.96% respectively. Stacked ensembles of LSTM outperformed other algorithms for 1560 SNPs with an overall accuracy of 0.96, AUC = 0.98 for brown eyes, and AUC = 0.97 for Blue-Green eyes. The main dataset for Type-2 diabetes consists of 107 people where 30 people are classified as cases and 74 people as controls. We used different linear threshold to find the optimal number of SNPs for classification. The final model gave an accuracy of 0.97%.ConclusionGenotype-phenotype predictions are very useful especially in forensic. These predictions can help to identify SNP variant association with traits and diseases. Given more datasets, machine learning model predictions can be increased. Moreover, the non-linearity in the Machine learning model and the combination of SNPs Mutations while training the model increases the prediction. We considered binary classification problems but the proposed approach can be extended to multi-class classification.

Project description:Aims/hypothesisThere is limited information on how polygenic scores (PSs), based on variants from genome-wide association studies (GWASs) of type 2 diabetes, add to clinical variables in predicting type 2 diabetes incidence, particularly in non-European-ancestry populations.MethodsFor participants in a longitudinal study in an Indigenous population from the Southwestern USA with high type 2 diabetes prevalence, we analysed ten constructions of PS using publicly available GWAS summary statistics. Type 2 diabetes incidence was examined in three cohorts of individuals without diabetes at baseline. The adult cohort, 2333 participants followed from age ≥20 years, had 640 type 2 diabetes cases. The youth cohort included 2229 participants followed from age 5-19 years (228 cases). The birth cohort included 2894 participants followed from birth (438 cases). We assessed contributions of PSs and clinical variables in predicting type 2 diabetes incidence.ResultsOf the ten PS constructions, a PS using 293 genome-wide significant variants from a large type 2 diabetes GWAS meta-analysis in European-ancestry populations performed best. In the adult cohort, the AUC of the receiver operating characteristic curve for clinical variables for prediction of incident type 2 diabetes was 0.728; with the PS, 0.735. The PS's HR was 1.27 per SD (p=1.6 × 10-8; 95% CI 1.17, 1.38). In youth, corresponding AUCs were 0.805 and 0.812, with HR 1.49 (p=4.3 × 10-8; 95% CI 1.29, 1.72). In the birth cohort, AUCs were 0.614 and 0.685, with HR 1.48 (p=2.8 × 10-16; 95% CI 1.35, 1.63). To further assess the potential impact of including PS for assessing individual risk, net reclassification improvement (NRI) was calculated: NRI for the PS was 0.270, 0.268 and 0.362 for adult, youth and birth cohorts, respectively. For comparison, NRI for HbA1c was 0.267 and 0.173 for adult and youth cohorts, respectively. In decision curve analyses across all cohorts, the net benefit of including the PS in addition to clinical variables was most pronounced at moderately stringent threshold probability values for instituting a preventive intervention.Conclusions/interpretationThis study demonstrates that a European-derived PS contributes significantly to prediction of type 2 diabetes incidence in addition to information provided by clinical variables in this Indigenous study population. Discriminatory power of the PS was similar to that of other commonly measured clinical variables (e.g. HbA1c). Including type 2 diabetes PS in addition to clinical variables may be clinically beneficial for identifying individuals at higher risk for the disease, especially at younger ages.

Project description:Identifying patients with new-onset type 2 diabetes who have insulin deficiency can aid in timely insulin replacement therapy. In this study, we measured fasting C-peptide concentration to assess endogenous insulin secretion and determine the prevalence and characteristics of patients with insulin deficiency in adult Ugandan patients with confirmed type 2 diabetes at presentation.MethodsAdult patients with new-onset diabetes were recruited from seven tertiary hospitals in Uganda. Participants who were positive for the three islet autoantibodies were excluded. Fasting C-peptide concentrations were measured in 494 adult patients, and insulin deficiency was defined as a fasting C-peptide concentration <0.76 ng/ml. The socio-demographic, clinical, and metabolic characteristics of participants with and without insulin deficiency were compared. Multivariate analysis was performed to identify independent predictors of insulin deficiency.ResultsThe median (IQR) age, glycated haemoglobin (HbA1c), and fasting C-peptide of the participants was 48 (39-58) years,10.4 (7.7-12.5) % or 90 (61-113) mmol/mol, and 1.4 (0.8-2.1) ng/ml, respectively. Insulin deficiency was present in 108 (21.9%) participants. Participants with confirmed insulin deficiency were more likely to be male (53.7% vs 40.4%, p=0.01), and had a lower body mass index or BMI [p<0.001], were less likely to be hypertensive [p=0.03], had reduced levels of triglycerides, uric acid, and leptin concentrations [p<0.001]), but higher HbA1c concentration (p=0.004). On multivariate analysis, BMI (AOR 0.89, 95% CI 0.85-0.94, p<0.001), non-HDLC (AOR 0.77, 95% CI 0.61-0.97, p=0.026), and HbA1c concentrations (AOR 1.08, 95% CI 1.00-1.17, p=0.049) were independent predictors of insulin deficiency.ConclusionInsulin deficiency was prevalent in this population, occurring in about 1 in every 5 patients. Participants with insulin deficiency were more likely to have high HbA1c and fewer markers of adiposity and metabolic syndrome. These features should increase suspicion of insulin deficiency and guide targeted testing and insulin replacement therapy.

Dataset Information

Genotype prediction of adult type 2 diabetes from adolescence in a multiracial population.

Publications

Genotype prediction of adult type 2 diabetes from adolescence in a multiracial population.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets