Preliminary construction of prediction model of clinical nurses' mental health
10.3760/cma.j.cn115682-20200504-03145
- VernacularTitle:临床护士心理健康状况预测模型的初步构建
- Author:
Zebing LUO
1
;
Peiru WANG
;
Yiru WANG
Author Information
1. 汕头大学医学院 515041
- Keywords:
Nurses;
Mental health;
Neural networks;
Prediction model
- From:
Chinese Journal of Modern Nursing
2021;27(3):328-333
- CountryChina
- Language:Chinese
-
Abstract:
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.
