Research of Anxiety, Depression, and PTSD among Reunited Populations based on Machine Learning

This study aimed to assess the prevalence of anxiety, depression, and posttraumatic stress disorder (PTSD) in the reunited population in China and examine influencing factors, including psychological flexibility, social support, and psychological resilience, to inform mental health interventions. Using an online survey, data were collected via Generalized Anxiety Disorder-7 (GAD-7), Patient Health Questionnaire-9 (PHQ-9), PTSD Checklist for DSM-5 (PCL-5), Acceptance and Action Questionnaire-II (AAQ-II), Perceived Social Support Scale (PSSS), and Connor-Davidson Resilience Scale (CD-RISC). Regression analysis was performed to explore significant predictors. Support Vector Machine (SVM) and Random Forest (RF) models were used for analysis of the collected survey data. Furthermore, this paper used Inter Quartile Range (IQR) and winsorizing methods for detection and handling of outliers. Incidence rates were 70.8%, 76.0%, and 60.1% for anxiety, depression, and PTSD, respectively. Psychological flexibility negatively associated with all three conditions. Social support and resilience, though positively associated, were insufficiently developed in this population. Both SVM and RM efficiently analyzed the collected data. Enhancing social support and fostering psychological flexibility are recommended to improve coping mechanisms and mental well-being.