Aim: To explore the influencing factors of Type 2 diabetes mellitus (T2DM) in the rural population of Henan Province and evaluate the predictive ability of non-invasive factors to T2DM.
Methods: A total of 30,020 participants from the Henan Rural Cohort Study in China were included in this study. The dataset was randomly divided into a training set and a testing set with a 50:50 split for validation purposes. We used logistic regression analysis to investigate the association between 56 factors and T2DM in the training set (false discovery rate < 5 %) and significant factors were further validated in the testing set (P < 0.05). Gradient Boosting Machine (GBM) model was used to determine the ability of the non-invasive variables to classify T2DM individuals accurately and the importance ranking of these variables.
Results: The overall population prevalence of T2DM was 9.10 %. After adjusting for age, sex, educational level, marital status, and body measure index (BMI), we identified 13 non-invasive variables and 6 blood biochemical indexes associated with T2DM in the training and testing dataset. The top three factors according to the GBM importance ranking were pulse pressure (PP), urine glucose (UGLU), and waist-to-hip ratio (WHR). The GBM model achieved a receiver operating characteristic (AUC) curve of 0.837 with non-invasive variables and 0.847 for the full model.
Conclusions: Our findings demonstrate that non-invasive variables that can be easily measured and quickly obtained may be used to predict T2DM risk in rural populations in Henan Province.
Keywords: Gradient Boosting Machine; Non-invasive factors; Rural population; Type 2 Diabetes Mellitus.
Copyright © 2023 Elsevier B.V. All rights reserved.