Predicting factors associated with anxiety by patients undergoing treatment for infectious diseases using a random-forest machine learning approach.

Patients with infectious diseases are often at increased risk of anxiety during treatment. The prevalence of anxiety and depression in infected people increased significantly during the COVID-19 pandemic, and the risk factors for these mental health problems need to be urgently investigated. In this study, a cross-sectional study was conducted in Shanghai in 2022, which included 1283 patients and systematically assessed their sociodemographic characteristics and mental health status. A random forest classifier combined with the Boruta algorithm was used to screen predictors, and a nomogram was constructed based on the screening results. The results of the study showed that entrapment (OR 1.07, 95% CI 1.05-1.09, P < 0.001), defeat (OR 1.04, 95% CI 1.01-1.07, P < 0.01) and stigma (OR 1.05, 95% CI 1.03-1.06, P < 0.001) were positively associated with anxiety, whereas social support (OR 0.97, 95% CI 0.96-0.98, P < 0.001) was negatively associated with anxiety. The C-index of the model was 0.858, the area under the ROC curve (AUC) was 0.861 (95% CI 0.834-0.888), and the P value of the Hosmer-Lemeshow test was 0.07, indicating that the model fit well. Based on the Random Forest machine learning method, this study successfully constructed a prediction model for anxiety risk in COVID-19 patients, screening out key risk factors such as feeling trapped, frustration, stigma and social support, providing a scientific basis for clinical practice and public health, and helping to promote personalized interventions for anxiety and the building of a mental health support system.