Investigation on the Prevalence of Anxiety and Depression among Operating Room Nurses in Guangdong Province and Construction of Machine Learning Prediction Models
ZHANG Jiamin
CHEN Xiaoxia
LI Shaorong
PAN Lifeng
Abstract：Objective To understand the prevalence of anxiety and depression among operating room nurses in Guangdong Province and the influencing factors,and to construct prediction models using machine learning.Methods Twelve medical institutions were randomly selected,and cluster sampling was used to conduct a survey of all operating room nurses through WeChat questionnaire star.The 7-item generalized anxiety disorder scale(GAD-7)and the patient health questionnaire-9(PHQ-9)were used to evaluate anxiety and depression,respectively.Chi-square test and Logistic regression were used for group comparison and multivariate analysis.The recursive feature elimination with cross-validation(RFECV)method was used to select the optimal predictive variables.Five methods,including logistic regression(LR),decision tree(DT),support vector machine(SVM),random forest(RF),and extreme gradient boosting(XGBoost),were used for model training,and the optimal model was selected.The Shapley additive explanations(SHAP)method was used for visualization interpretation.Results A total of 389 surveys were completed,with a prevalence rate of 57.3%for anxiety symptoms and 72.5%for depression symptoms.The XGBoost and LR models performed best in predicting anxiety and depression,respectively.Income,years of service,and daily working hours were important indicators for predicting anxiety,while occupational exposure,daily sleep time,and years of service were important indicators for predicting depression.Conclusion The prevalence of anxiety and depression among operating room nurses is relatively high and is influenced by multiple factors such as years of service,sleep,income,and occupational exposure.
Keywords：AnxietyDepressionOperating room nursesMachine learningInfluencing factorsPrediction models
Publication Date：2025-09-30
Online Publishing Date：2025-12-22(First online date of this platform, not the publication date of the document)
Pages：6( 16-20,后插1-后插2 )