Construction of Xinjiang metabolic syndrome risk prediction model based on interpretable models

Abstract

Background We aimed to construct simple and practical metabolic syndrome (MetS) risk prediction models based on the data of inhabitants of Urumqi and to provide a methodological reference for the prevention and control of MetS. Methods This is a cross-sectional study conducted in the Xinjiang Uygur Autonomous Region of China. We collected data from inhabitants of Urumqi from 2018 to 2019, including demographic characteristics, anthropometric indicators, living habits and family history. Resampling technology was used to preprocess the data imbalance problems, and then MetS risk prediction models were constructed based on logistic regression (LR) and decision tree (DT). In addition, nomograms and tree diagrams of DT were used to explain and visualize the model. Results Of the 25,542 participants included in the study, 3,267 (12.8%) were diagnosed with MetS, and 22,275 (87.2%) were diagnosed with non-MetS. Both the LR and DT models based on the random undersampling dataset had good AUROC values (0.846 and 0.913, respectively). The accuracy, sensitivity, specificity, and AUROC values of the DT model were higher than those of the LR model. Based on a random undersampling dataset, the LR model showed that exercises such as walking (OR=0.769) and running (OR= 0.736) were protective factors against MetS. Age 60 ~ 74 years (OR=1.388), previous diabetes (OR=8.902), previous hypertension (OR=2.830), fatty liver (OR=3.306), smoking (OR=1.541), high systolic blood pressure (OR=1.044), and high diastolic blood pressure (OR=1.072) were risk factors for MetS; the DT model had 7 depth layers and 18 leaves, with BMI as the root node of the DT being the most important factor affecting MetS, and the other variables in descending order of importance: SBP, previous diabetes, previous hypertension, DBP, fatty liver, smoking, and exercise. Conclusions Both DT and LR MetS risk prediction models have good prediction performance and their respective characteristics. Combining these two methods to construct an interpretable risk prediction model of MetS can provide methodological references for the prevention and control of MetS.

Establishment of a Risk Prediction Model for Metabolic Syndrome in High Altitude Areas in Qinghai Province, China: A Cross-Sectional Study

“…This finding is similar to the research findings of Solam Lee 40 and Junho Kim. 41 In contrast, Yan Zhang et al 24 identified walking and running as factors protective against MetS, but our model does not include these. We did filter out these factors in our LASSO regression analysis.…”

“…Previous studies often employed univariate analysis to validate multivariate analysis results or used stepwise regression and logistic regression analyses to identify predictor variables in the model. For example, Yan Zhang etal 24 used a multivariate logistic regression analysis and decision tree to establish MetS risk prediction models, their data set was preprocessed with a multiple imputation method, and between-group comparisons and multivariate analyses were then performed to determine the independent variables, their results showed that high SBP, high DBP, fatty liver, high BMI, smoking status, previous diabetes, previous hypertension, and age were risk factors. In another study, a risk prediction model of MetS for oil workers was reported; although the authors established three models, their method for building these models and screening independent variables was to first conduct a single factor analysis and then a multivariate logistics regression analysis.…”

“…Apart from the prediction model developed in Urumqi, Xinjiang Uygur Autonomous Region, incorporating variables such as SBP, history of diabetes and hypertension, DBP, fatty liver, smoking, physical activity, and BMI. 24 There remains a relative scarcity of research on predictive models for MetS, particularly in high altitude areas like Qinghai. Therefore, the objective of this study is to develop a prediction model for MetS in the high-altitude regions of Qinghai Province; this model could serve as a valuable reference for the prevention and management of MetS in this area.…”

Analysis of factors affecting nonalcoholic fatty liver disease in Chinese steel workers and risk assessment studies

“…This suggests that all three models demonstrate commendable assessment performance. However, in practical implementations, it is imperative to consider both the interpretability and performance of the risk assessment model [ 48 ]. The logistic regression model, as a conventional modeling procedure, not only allows for the screening of potential influential factors of a disease but also provides a quantitative interpretation of the impact of each variable.…”

Classification and prediction of spinal disease based on the SMOTE-RFE-XGBoost model

“…The results show that the RFE-KNN model combined with RFE and the K-nearest neighbor (KNN) classifier has the best performance. Zhang et al (2022) , based on the physical examination data of a health examination institution in Urumqi in 2018, used three feature selection methods, RFE, measured resting metabolic rate (MRMR) and least absolute shrinkage and selection operator (LASSO), combined with two model explanatory methods of variable importance and linear interpolation with maximum entropy (LIME), to process the metabolic syndrome risk prediction model before and after modeling. Li & Liu (2020) used the gene epitope data of spontaneous premature birth (SPB) as a basis, used SVM-RFE for gene feature selection, and compared it with other machine learning and feature selection methods.…”