Multifactorial Risk Assessment and Predictive Modeling of Glioma Based on NHANES Data

Background Glioma is one of the most common malignant tumors of the central nervous system, with a complex etiology influenced by genetic factors, metabolic diseases, lifestyle, and mental health. However, the specific roles and interactions of these factors remain inadequately studied. Methods This study utilized data from the National Health and Nutrition Examination Survey (NHANES), including 1,843 participants (163 glioma patients). Multivariate linear regression, neural network analysis, and correlation analysis were conducted to systematically evaluate the effects of age, gender, race, metabolic diseases, mental health, and lifestyle on glioma risk. A predictive risk model was also constructed. Results Age (OR = 1.081, P < 0.001), cardiovascular disease (OR = 2.042, P < 0.001), depression (OR = 2.348, P < 0.001), and alcohol consumption (P < 0.001) were identified as major risk factors for glioma, while diabetes (OR = 0.581, P = 0.003) appeared to have a protective effect. Predictive modeling highlighted age as the most critical predictor (importance score = 0.602), with an area under the ROC curve (AUC) of 0.76, indicating moderate predictive capability. Conclusion This study systematically analyzed multiple risk factors for glioma using NHANES data, identifying key risk factors and constructing a predictive model. The findings provide a theoretical basis for early screening, prevention strategies, and personalized interventions for glioma. Future research should integrate longitudinal data and molecular mechanism analyses to validate these findings and explore causal relationships.