Objective:To understand the mental health of nurses, and to explore the influence of general information, coping styles, social support and work adaptation barriers on the mental health of nurses, and to initially construct a prediction model of clinical nurses' mental health.Methods:In February 2020, convenience sampling was used to select 374 clinical nurses from two hospitals in a city as the research objects. All nurses were investigated with the self-designed general information questionnaire, Symptom Checklist 90 (SCL-90) , Coping Style Questionnaire, Social Support Rating Scale (SSRS) and Work Adjustment Disorder Scale. The mental health was processed as binary data, and the multi-layer perceptron in the neural network was used to construct a prediction model of the clinical nurses' mental health, and the model was verified and analyzed.Results:Among 374 clinical nurses, the scores of SCL-90, Coping Style Questionnaire, SSRS and Work Adjustment Disorder Scale were (123.06±41.70) , (27.90±12.14) , (38.84±8.46) and (9.72±6.35) respectively. Correlation analysis results showed that working years, self-blame, fantasy, avoidance, rationalization and work adjustment disorder were positively correlated with mental health ( P<0.05) ; whether they were authorized strength, problem solving, asking for help, subjective support, support utilization were negatively correlated with mental health ( P<0.05) . The above variables related to mental health were incorporated into the prediction model, and 374 samples were divided into training samples (177) , test samples (81) and persistence samples (116) . The results showed that the modeling accuracy of training, testing and persistence samples were 79.7%, 86.4% and 81.0%, respectively, and the area under the receiver operating characteristic curve was 0.810. The variable which normalization importance was 100% in the prediction model was the work adjustment disorder. Conclusions:The prediction model of clinical nurses' mental health constructed in this study has good accuracy, and the application of neural network model is relatively simple, which can be used as an effective method to evaluate the mental health of clinical nurses.

Objective:To establish a model for predicting the mental health status of nurses based on machine learning algorithm.Methods:In February 2020, the nurses from Shantou Central Hospital and Cancer Hospital of Shantou University Medical College were recruited by convenience sampling, investigated using the Self-reporting Inventory, Coping Style Questionnaire, Social Support Rating Scale and Work Attitude Scale. Mental health status was treated as a dichotomous variable, and candidate predictors were screened out by univariate and multivariate Logistic regression analysis. The subjects were randomly divided into a training set (80%) and a test set (20%). Then five prediction models of nursing staff mental health status were constructed using the five machine learning methods (Logistic Regression, Artificial Neural Network, C5.0 Decision Tree, Bayesian Network and Support Vector Machine), verified and compared to screen out the model with the highest predictive efficiency.Results:A total of 415 nurses were enrolled, and the positive detection rate of mental health symptoms was 20.48%. According to univariate and multiple Logistic regression analysis, candidate predictors were work attitude ( OR=1.098, 95% CI 1.028-1.174), self-accusation ( OR=7.703, 95% CI 2.014-29.468), problem-solving( OR=0.131, 95% CI 0.025-0.686), the number of night shifts per month ( OR=0.204, 95% CI 0.073-0.573)and support availability ( OR=0.830, 95% CI 0.701-0.984). The accuracy of prediction of Logistic Regression, Artificial Neural Network, C5.0 Decision Tree, Bayesian Network and Support Vector Machine were 84.21%, 85.53%, 82.89%, 78.95%, 84.21%. The area under the ROC curve was 0.801, 0.825, 0.777, 0.583, 0.774. Artificial Neural Network was significantly more effective than Logistic regression, C5.0 Decision Tree, Bayesian Network and Support Vector Machine (DeLong test, P<0.05). Conclusions:The machine learning based predictive models for nursing staff mental health status has higher predictive value, which can be applied into nursing staff mental health screening decisions to accurately grasp its dynamic changes, early identification of high-risk mental health abnormalities and early intervention. Work attitude, self-accusation, problem-solving, the number of night shifts per month and support availability was predictors to construct predictive models.

Objective:To explore the influence of family function and personal characteristics on death anxiety in patients with advanced cancer, providing reference for finding methods and approaches to alleviate death anxiety in advanced cancer patients.Methods:From March to June 2023, convenience sampling was used to select 182 advanced cancer patients admitted to the Cancer Center of the Fifth Affiliated Hospital of Sun Yat-sen University. The Chinese Version of Death and Dying Distress Scale and Family APGAR Index were used to investigate patients' death anxiety and family function. The Numerical Rating Scale and Kamofsky Performance Status were used to assess patients' pain and performance status. Single factor analysis and multiple linear regression were used to analyze the influencing factors of death anxiety in advanced cancer patients.Results:A total of 182 questionnaires were distributed, and 165 valid questionnaires were collected, with a valid response rate of 90.7%. The death anxiety score of advanced cancer patients was (22.52±15.27), and 10.3% (17/165) of patients had moderate or above death anxiety. The patients' total family function score was (8.62±1.97), and 86.7%(143/165) patients self-reported good family function. The death anxiety score was negatively correlated with the family function score ( P<0.05). Multiple linear regression analysis showed that Kamofsky Performance Status score, pre-illness employment, family function, place of residence, and pain score were the influencing factors of death anxiety in advanced cancer patients, and the differences were statistically significant ( R2=0.196, P<0.01) . Conclusions:The advanced cancer patients have low levels of death anxiety in our study. Advanced cancer patients with moderate family dysfunction, living in rural areas, working before illness, and high pain scores have high levels of death anxiety, while patients with good performance status have low levels of death anxiety. It is recommended that clinical workers strengthen the assessment of death anxiety and family function in patients with advanced cancer, take timely and effective measures based on influencing factors, and help alleviate death anxiety in patients with advanced cancer.