1.Neural network analysis of mechanization's impact on coal miner's occupational health
Chinese Journal of Industrial Hygiene and Occupational Diseases 2024;42(5):374-380
In order to clarify the transmission mechanism of the impact of mechanization on the occupational health of miners and to provide empirical evidence for the development of new quality productivity in the coal industry that balances health and efficiency. In August 2022, we selected a typical coal mine, constructed a comprehensive evaluation index of miners' occupational health through a questionnaire survey based on the fully connected neural network model. A Bayesian model was used to verify the influence of mechanization level on miners' occupational health. We found that: the predicted probability of occupational diseases could be used as a comprehensive indicator of the level of occupational health, providing a basis for early intervention and prevention of occupational diseases. Mechanization could directly promote the improvement of miners' occupational health level, and also indirectly affect occupational health level by influencing hazards level and work intensity. The indirect effect of mechanization on work intensity was positive, and the indirect effect of mechanization on hazards level was positive. Presented the "inverted U-shaped" process in the mechanization breakthrough semi-mechanized level would realize the economies of scale of health protection, its impact on the prevention and control of occupational hazards would turn from negative to positive.
2.Neural network analysis of mechanization's impact on coal miner's occupational health
Chinese Journal of Industrial Hygiene and Occupational Diseases 2024;42(5):374-380
In order to clarify the transmission mechanism of the impact of mechanization on the occupational health of miners and to provide empirical evidence for the development of new quality productivity in the coal industry that balances health and efficiency. In August 2022, we selected a typical coal mine, constructed a comprehensive evaluation index of miners' occupational health through a questionnaire survey based on the fully connected neural network model. A Bayesian model was used to verify the influence of mechanization level on miners' occupational health. We found that: the predicted probability of occupational diseases could be used as a comprehensive indicator of the level of occupational health, providing a basis for early intervention and prevention of occupational diseases. Mechanization could directly promote the improvement of miners' occupational health level, and also indirectly affect occupational health level by influencing hazards level and work intensity. The indirect effect of mechanization on work intensity was positive, and the indirect effect of mechanization on hazards level was positive. Presented the "inverted U-shaped" process in the mechanization breakthrough semi-mechanized level would realize the economies of scale of health protection, its impact on the prevention and control of occupational hazards would turn from negative to positive.
3.Improving the Efficiency of Emergency and Critical Care Platform Based on OKR Mode
Lanfang DU ; Mingxue LI ; Yipei WANG ; Li MA ; Xueqian MA ; Hongxia GE ; Shuo LI ; Qingbian MA
Chinese Hospital Management 2023;43(12):49-51
The shortage of emergency and critical care resources has become increasingly prominent,seriously reducing the quality and safety of care.How to improve the efficiency of the emergency and critical care platform is an urgent problem to be solved.Since 2020,the emergency department of Peking University Third Hospital has achieved an increase of 10%-20%in the annual visits of emergency and critically ill patients,the reduction of the emergency department length of stay and the improvement of survival rate using Objectives and Key Results(OKR)as an advanced management tool.It provides a new paradigm for improving efficiency of emergency department in large general hospitals.
4.Predictive value of Pv-aCO 2/Ca-vO 2 combined blood lactate concentration for primary peritonitis-related septic shock in children
Le MA ; Jiahao TIAN ; Yipei LI ; Ying WANG ; Yanqiang DU ; Yi WANG
Chinese Critical Care Medicine 2023;35(1):77-81
Objective:To investigate the prognostic value of the ratio of veno-arterial carbon dioxide partial pressure difference to arterio-venous oxygen content difference (Pv-aCO 2/Ca-vO 2) in children with primary peritonitis-related septic shock. Methods:A retrospective study was conducted. Sixty-three children with primary peritonitis-related septic shock admitted to department of intensive care unit of the Children's Hospital Affiliated to Xi'an Jiaotong University from December 2016 to December 2021 were enrolled. The 28-day all-cause mortality was the primary endpoint event. The children were divided into survival group and death group according to the prognosis. The baseline data, blood gas analysis, blood routine, coagulation, inflammatory status, critical score and other related clinical data of the two groups were statistics. The factors affecting the prognosis were analyzed by binary Logistic regression, and the predictability of risk factors were tested by the receiver operator characteristic curve (ROC curve). The risk factors were stratified according to the cut-off, Kaplan-Meier survival curve analysis compared the prognostic differences between the groups.Results:A total of 63 children were enrolled, including 30 males and 33 females, the average age (5.6±4.0) years old, 16 cases died in 28 days, with mortality was 25.4%. There were no significant differences in gender, age, body weight and pathogen distribution between the two groups. The proportion of mechanical ventilation, surgical intervention, vasoactive drug application, and procalcitonin, C-reactive protein, activated partial thromboplastin time, serum lactate (Lac), Pv-aCO 2/Ca-vO 2, pediatric sequential organ failure assessment, pediatric risk of mortality Ⅲ in the death group were higher than those in the survival group. Platelet count, fibrinogen, mean arterial pressure were lower than those in the survival group, and the differences were statistically significant. Binary Logistic regression analysis showed that Lac and Pv-aCO 2/Ca-vO 2 were independent risk factors affecting the prognosis of children [odds ratio ( OR) and 95% confidence interval (95% CI) were 2.01 (1.15-3.21), 2.37 (1.41-3.22), respectively, both P < 0.01]. ROC curve analysis showed that the area under curve (AUC) of Lac, Pv-aCO 2/Ca-vO 2 and their combination were 0.745, 0.876 and 0.923, the sensitivity were 75%, 85% and 88%, and the specificity were 71%, 87% and 91%, respectively. Risk factors were stratified according to cut-off, and Kaplan-Meier survival curve analysis showed that the 28-day cumulative probability of survival of Lac ≥ 4 mmol/L group was lower than that in Lac < 4 mmol/L group [64.29% (18/28) vs. 82.86% (29/35), P < 0.05]. Pv-aCO 2/Ca-vO 2 ≥ 1.6 group 28-day cumulative probability of survival was less than Pv-aCO 2/Ca-vO 2 < 1.6 group [62.07% (18/29) vs. 85.29% (29/34), P < 0.01]. After a hierarchical combination of the two sets of indicator variables, the 28-day cumulative probability of survival of Pv-aCO 2/Ca-vO 2 ≥ 1.6 and Lac ≥ 4 mmol/L group significantly lower than that of the other three groups (Log-rank test, χ2 = 7.910, P = 0.017). Conclusion:Pv-aCO 2/Ca-vO 2 combined with Lac has a good predictive value for the prognosis of children with peritonitis-related septic shock.