Full
Outline
To compare the performance of back propagation artificial neural network (BP-ANN) and logistic regression models in predicting the risk of cumulative fatigue among petrochemical employees and evaluate the prediction models for early identification and intervention of cumulative fatigue in these employees.
A total of 4 066 employees of a petrochemical enterprise in Jiangsu province were selected by cluster sampling for a cross-sectional study from July to October 2021. A web-based questionnaire was designed to investigate the general information, work conditions, occupational stress, and prevalence of cumulative fatigue among employees. SPSS 23.0 was used to analyze the influencing factors of cumulative fatigue among petrochemical employees through non-parametric tests. BP-ANN and logistic regression models were established and receiver operating characteristic (ROC) curves were plotted to compare the prediction performance of models based on sensitivity, specificity, Youden index, and area under the curve (AUC) value.
A total of 3 763 valid questionnaires were collected, which showed that 63.2% (2 377/3 763) of petrochemical employees experienced cumulative fatigue. The comprehensive analysis of the two models indicated that age, weekly working hours, shift work, occupational stress, and regular exercise were the key factors influencing employees’ cumulative fatigue. Both models had AUC values > 0.7. Sensitivity was comparable between the BP-ANN and logistic models (BP 75.7%, logistic 75.6%). The BP-ANN model achieved higher specificity (BP 76.3%, logistic 69.3%), Youden index (BP 51.9%, logistic 44.9%), and AUC value (BP 84.4%, logistic 79.9%) than the logistic model. Both models can be used to predict the incidence of cumulative fatigue among petrochemical employees, while the overall prediction performance of the BP-ANN model was superior to that of the logistic model.
Both BP-ANN and logistic regression models can be adopted to predict cumulative fatigue among petrochemical employees, with the BP-ANN model showing better prediction performance.
97
39
| 科 Family | 属数 Number of genus | 种数 Number of species | 占总种数比例 Percentage of total species (%) | 属 Genus | 种数 Number of species | 占总种数比例 Percentage of total species (%) |
|---|---|---|---|---|---|---|
| 鹅膏菌科Amanitaceae | 2 | 11 | 5.26 | 鹅膏菌属 Amanita | 10 | 4.78 |
| 小菇科 Mycenaceae | 2 | 12 | 5.74 | 丝盖伞属 Inocybe | 5 | 2.39 |
| 多孔菌科 Polyporaceae | 8 | 14 | 6.70 | 蜡蘑属 Laccaria | 5 | 2.39 |
| 红菇科 Russulaceae | 3 | 23 | 11.00 | 小皮伞属 Marasmius | 6 | 2.87 |
| 小菇属 Mycena | 11 | 5.26 | ||||
| 光柄菇属 Pluteus | 5 | 2.39 | ||||
| 红菇属 Russula | 17 | 8.13 | ||||
| 栓菌属 Trametes | 5 | 2.39 |
关闭全屏
No. 86 Xueyuan South Road, Haidian District, Beijing
010-62662699(Operation and Technical Support)
qkjq@cast.org.cn
Copyright © 2025 China Association for Science and Technology. All rights reserved. For all open access content, the relevant licensing terms apply.
Sponsored by the Office of the Leading Group for Cybersecurity and Informatization of CAST, and supported by Science and Technology Review Publishing House
