Predicting type 2 diabetes using genetic and environmental risk factors in a multi-ethnic Malaysian cohort

Abdullah, Nor Azizan; Murad, Nor Azian Abdul; Haniff, Ezanee Azlina Mohd; Syafruddin, Saiful Effendi; Attia, John; Oldmeadow, Christopher; Kamaruddin, Mohd Arman; Jalal, Nazihah Abd; Ismail, Noorhassim; Ishak, Muhiddin; Jamal, Rahman; Scott, Rodney J.; Holliday, Elizabeth G.

doi:10.1016/j.puhe.2017.04.003

Cited by 11 publications

(7 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This discrepancy could be attributed to the heterogeneity in linkage disequilibrium among subjects of different ethnicities, which is a common concern in genetic association studies involving multiple populations 36,37 . Moreover, genetic association is known to be affected by gene-gene, gene-environment and gene-nutrient interactions, which might explain the disagreement in study findings between the two subgroups 38,39 . It is also worthy of mention that among the 14 studies included in the meta-analysis, only three were conducted among Caucasians.…”

Section: Discussionmentioning

confidence: 98%

Association between MIR499A rs3746444 polymorphism and breast cancer susceptibility: a meta-analysis

Tan

Lim

Fang

et al. 2020

Sci Rep

View full text Add to dashboard Cite

Numerous studies have investigated the association of MIR499A rs3746444 polymorphism with breast cancer susceptibility, but the results have been inconsistent. In this work, we performed a meta-analysis to obtain a more reliable estimate of the association between the polymorphism and susceptibility to breast cancer. A comprehensive literature search was conducted on PubMed, Scopus, Web of Science (WoS), China National Knowledge Infrastructure (CNKI), VIP and Wanfang databases up to January 2020. A total of 14 studies involving 6,797 cases and 8,534 controls were included for analysis under five genetic models: homozygous (GG vs. AA), heterozygous (AG vs. AA), dominant (AG + GG vs. AA), recessive (GG vs. AA + AG) and allele (G vs. A). A statistically significant association was observed between the polymorphism and an increased breast cancer susceptibility under all genetic models (homozygous, OR = 1.33, 95% CI = 1.03-1.71, P = 0.03; heterozygous, OR = 1.08, 95% ci = 1.00-1.16, P = 0.04; dominant, OR = 1.15, 95% CI = 1.02-1.30; P = 0.03; recessive, OR = 1.35, 95% ci = 1.06-1.72, P = 0.01; allele, OR = 1.12, 95% CI = 1.00-1.26, P = 0.04). Subgroup analysis based on ethnicity suggested that significant association was present only among Asians, but not Caucasians. In conclusion, MIR499A rs3746444 polymorphism was significantly associated with breast cancer susceptibility among Asians, suggesting its potential use as a genetic risk marker in this population.

show abstract

Section: Discussionmentioning

confidence: 98%

Association between MIR499A rs3746444 polymorphism and breast cancer susceptibility: a meta-analysis

Tan

Lim

Fang

et al. 2020

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Previous studies have shown that logistic regression models are often applied in single-element or multi-element diabetes risk assessment, such as Abdullah et al [ 13 ] making use of environmental and genetic risk factors to predict the risk of type 2 diabetes in Malaysia with a fitted multiple logistic regression model and as a result, the AUC value was 0.75–0.83. However, the logistic regression model can’t both carry out feature study of sample data and obtain the prediction results of unknown samples, which means it has great limitations.…”

Section: Discussionmentioning

confidence: 99%

Prediction of Type 2 Diabetes Risk and Its Effect Evaluation Based on the XGBoost Model

Wang

Chen

et al. 2020

Healthcare

View full text Add to dashboard Cite

In view of the harm of diabetes to the population, we have introduced an ensemble learning algorithm—EXtreme Gradient Boosting (XGBoost) to predict the risk of type 2 diabetes and compared it with Support Vector Machines (SVM), the Random Forest (RF) and K-Nearest Neighbor (K-NN) algorithm in order to improve the prediction effect of existing models. The combination of convenient sampling and snowball sampling in Xicheng District, Beijing was used to conduct a questionnaire survey on the personal data, eating habits, exercise status and family medical history of 380 middle-aged and elderly people. Then, we trained the models and obtained the disease risk index for each sample with 10-fold cross-validation. Experiments were made to compare the commonly used machine learning algorithms mentioned above and we found that XGBoost had the best prediction effect, with an average accuracy of 0.8909 and the area under the receiver’s working characteristic curve (AUC) was 0.9182. Therefore, due to the superiority of its architecture, XGBoost has more outstanding prediction accuracy and generalization ability than existing algorithms in predicting the risk of type 2 diabetes, which is conducive to the intelligent prevention and control of diabetes in the future.

show abstract

“…T2DM is a multifactorial disorder attributing to the coexistence of a variety of genetic and environmental factors (Abdullah et al, 2017 ). In the past decade, over 70 loci in the human genome have been identified as potential risk factors in T2DM by genome-wide association studies (GWAS), including transcription factor-7-like 2 (TCF7L2), forkhead box A1 (FOXA1), and A2 (FOXA2), hepatocyte nuclear factor 4alpha (HNF4A) and high-mobility group AT-hook 1 (HMGA1) (Pullinger et al, 2014 ; Cheng et al, 2017 ).…”

Section: Discussionmentioning

confidence: 99%

Ethnicity-Specific Association Between Ghrelin Leu72Met Polymorphism and Type 2 Diabetes Mellitus Susceptibility: An Updated Meta-Analysis

et al. 2018

View full text Add to dashboard Cite

Background: The Leu72Met polymorphism of ghrelin gene has been associated with genetic predisposition to type 2 diabetes mellitus (T2DM), while conclusions remain conflicting. Hence, we performed this updated meta-analysis to clarify the association between Leu72Met polymorphism and T2DM susceptibility.Methods: Six electronic databases were consulted for articles published before 1 January, 2018. Pooled odds ratios (OR) and 95% confidence intervals (CI) were calculated under five genetic models to assess this association. We used I2-test and Q statistics to measure heterogeneity across the included studies. Subgroup analyses and publication bias were also performed.Results: Thirteen case-control studies involving 4720 T2DM patients and 4206 controls were included in this meta-analysis. The overall results using fixed-effects models showed that Leu72Met polymorphism was significantly associated with an increased risk of T2DM under homozygous model (OR = 1.307, 95%CI 1.001–1.705, p = 0.049). Further subgroup analyses stratified by ethnicity revealed that the risk for T2DM was only increased in Asians (homozygous model: OR = 1.335, 95%CI 1.014–1.758, p = 0.040), while decreased in Caucasians (dominant model: OR = 0.788, 95%CI 0.635–0.978, p = 0.030; heterozygous model: OR = 0.779, 95%CI 0.626–0.969, p = 0.025; allelic model: OR = 0.811, 95%CI 0.661–0.995, p = 0.045). Funnel plots were basically symmetrical, and all p-values of Egger's test under five genetic models were >0.050, which indicated no evidence of publication bias.Conclusions: Our results demonstrate that the Leu72Met polymorphism of ghrelin gene may be protective against T2DM in Caucasians, while predisposing to T2DM in Asians.

show abstract

Predicting type 2 diabetes using genetic and environmental risk factors in a multi-ethnic Malaysian cohort

Cited by 11 publications

References 47 publications

Association between MIR499A rs3746444 polymorphism and breast cancer susceptibility: a meta-analysis

Association between MIR499A rs3746444 polymorphism and breast cancer susceptibility: a meta-analysis

Prediction of Type 2 Diabetes Risk and Its Effect Evaluation Based on the XGBoost Model

Ethnicity-Specific Association Between Ghrelin Leu72Met Polymorphism and Type 2 Diabetes Mellitus Susceptibility: An Updated Meta-Analysis

Contact Info

Product

Resources

About