Search

The application of machine learning (ML) is increasingly growing in biomedical sciences. This study aimed to evaluate factors associated with type 2 diabetes mellitus (T2DM) and compare the performance of ML methods in identifying individuals with the disease in an Iranian setting. Using the baseline data from Fasa Adult Cohort Study (FACS) and in a sex‐stratified manner, we studied factors associated with T2DM by applying seven different ML methods including Logistic Regression (LR), Support Vector Machine (SVM), Random Forest (RF), K‐Nearest Neighbours (KNN), Gradient Boosting Machine (GBM), Extreme Gradient Boosting (XGB) and Bagging classifier (BAG). We further compared the performance of these methods; for each algorithm, accuracy, precision, sensitivity, specificity, F1 score, and Area Under Curve (AUC) were calculated. 10,112 participants were recruited between 2014 and 2016, of whom 1246 had T2DM at baseline. 4566 (45%) participants were males, aged between 35 and 70 years. For males, age, sugar consumption, and history of hospitalization were the most weighted variables regarding their importance in screening for T2DM using the GBM model, respectively; these variables were sugar consumption, urine blood, and age for females. GBM outperformed other models for both males and females with AUC of 0.75 (0.69–0.82) and 0.76 (0.71–0.80), and F1 score of 0.33 (0.27–0.39) and 0.42 (0.38–0.46), respectively. GBM also showed a sensitivity of 0.24 (0.19–0.29) and a specificity of 0.98 (0.96–1.0) in males and a sensitivity of 0.38 (0.34–0.42) and specificity of 0.92 (0.89–0.95) in females. Notably, close performance characteristics were detected among other ML models. GBM model might achieve better performance in screening for T2DM in a south Iranian population. Gradient Boosting Machine model might achieve better performance in screening for T2DM in a south Iranian population.

Background: The triglyceride glucose (TyG) and triglyceride-to-high-density lipoprotein cholesterol ratio (TG/HDL-c) are the indices that can predict the progression of pre-diabetes to type 2 diabetes mellitus (T2DM). This study aimed to examine the relationship between TyG and TG/HDL-c indices with the incidence of T2DM in pre-diabetes patients. Methods: A total of 758 pre-diabetic patients aged 35–70 years who were enrolled in a prospective Fasa Persian Adult Cohort were followed up for 60 months. TyG and TG/HDL-C indices were obtained at baseline data and divided into quartiles. The 5-year cumulative incidence of T2DM was analyzed by Cox proportional hazards regression analysis while controlling for baseline covariates. Results: During 5 years of follow-up, there were 95 incident cases of T2DM, with an overall incidence rate of 12.53%. After adjusting for age, sex, smoking, marital status, socioeconomic status, body mass index, waist circumference, hip circumference, hypertension, total cholesterol, and dyslipidemia, the multivariate-adjusted hazard ratios (HRs) demonstrated that patients with the highest TyG and TG/HDL-C indices quartile were at higher risk of T2DM (HR = 4.42, 95%CI 1.75–11.21) and (HR = 2.15, 95%CI 1.04–4.47), respectively, compared to participants in the lowest quartile. As the quantiles of these indices increase, the HR value shows a significant increment (P< 0.05). Conclusion: The results of our study showed that the TyG and TG/HDL-C indices can be important independent predictors for the progression of pre-diabetes to T2DM. Therefore, controlling the components of these indicators in pre-diabetes patients can prevent developing T2DM or delay its occurrence.