Development and validation of a prediction model for the incidence of psychological disturbance in Chinese nurses: baseline data from a cohort study

Background Healthy psychology is a crucial factor in determining nurses’ ability to provide high-quality nursing care to patients. Therefore, it is essential to detect the risk of nurses’ psychological disturbance and provide early intervention. This study aimed to investigate the psychological status of nurses and develop a nomogram model to predict the incidence of psychological disturbance in Chinese nurses. Methods This study was part of the Chinese Nurse Cohort Study, and the data of 3,808 nurses were obtained from multiple tertiary hospitals in China. Data related to psychological disturbance were collected using the Symptom Checklist 90. Predictor selection was guided by the Job Demands-Resources model, encompassing 26 variables across three domains: living conditions, working situation and psychosocial indicators. Predictors were selected via stepwise regression, and a logistic regression model was developed to construct a predictive nomogram. Model performance was evaluated using the area under the receiver operating characteristic curve, decision curve analysis, bootstrap approach and 10-fold cross-validation. Results Independent protective indicators for nurses’ psychological disturbance included perceived social support, organizational career management, weekly leisure time, regular meals and published articles, while risk indicators included negative acts, working years, raising children, patients in day shift care and night shift work hours. All these variables were used to establish the nomogram. In the nomogram, the area under the ROC curves was 0.803 (95% CI : 0.786–0.819). The average AUC of bootstrap approach was 0.810 (95% CI : 0.785–0.817), and the average AUC of 10 fold cross-validation was 0.794 (ranging from 0.749 to 0.841), indicating that the model was stable. The DCA suggested good clinical application. Conclusion This study developed a prediction model to evaluate the risk of psychological disturbance among nurses for the first time. Nursing managers can use this visualized prediction model to predict the risk of nurses’ psychological disturbance, identify individualized risk factors, and implement preventive measures to reduce the occurrence of psychological disturbances among nurses.