During the career life cycle, workers may face various health problems such as occupational injuries, occupational diseases, and work-related diseases. How to comprehensively protect the health of workers is a crucial scientific issue that needs to be solved urgently. Workers show the characteristics of co-exposure to multiple occupational risks or co-existence of multiple health conditions in their occupational activities. Occupational injuries are closely related to occupational diseases and work-related diseases. To carry out prevention and control of occupational injuries in the context of "big health", we should further strengthen the systematic approach and highlight the concept of "overall process" and "all-round". That is to establish an occupational injury surveillance system covering the whole process of surveillance-assessment-intervention and the evaluation of intervention effects, and to set up the joint prevention and control strategy of occupational injuries, occupational diseases, and work-related diseases. This will promote the implementation of efficient and intensive health management at government, society, employers, workers and other levels to achieve all-round protection of workers' health. When exploring the possible effects of job burnout, occupational stress, comorbidity, and other factors on occupational injuries, the introduction of machine learning methods provides a new approach to identifying and analyzing the influencing factors of occupational injuries and to exploring potential underlying mechanisms.

Background Workers in the cable manufacturing industry are exposed to high-speed machinery and equipment for a long time, coupled with heavy workload, which poses significant risks to their physical health. However, the issue of occupational injuries in this industry has not received enough attention yet. Objective To understand the incidence of occupational injury of workers in cable manufacturing industry and to analyze the influencing factors. Method A basic information questionnaire and an occupational injury questionnaire were developed to investigate the occupational injuries of 1 343 workers in a cable manufacturing enterprise in the past year, and a total of 1 225 valid questionnaires were recovered, with an effective rate of 91.2%. Descriptive statistics were used to characterize the causes, injury locations, injury types, and other characteristics of employees’ occupational injuries. Chi-square test was used to analyze the occupational injury status of groups with different demographic characteristics, occupational characteristics, lifestyles, and interpersonal relationships. Logistic regression was used to analyze the influencing factors of occupational injuries. Result The incidence of occupational injuries among workers in a cable manufacturing enterprise in the past year was 8.6%, which mainly happened in male workers (80.0%) and occurred from May to July in summer (45.7%). The main causes were mechanical injuries (32.4%) and object blows (27.6%). The main sources of damage were machinery and equipment (36.2%) as well as raw materials and products (15.2%). The main injuries were located in upper limbs (53.3%) and lower limbs (22.9%). The main types of injuries were fractures (33.3%) and abrasions/contusions/puncture wounds (19.0%). The results of univariate analysis showed that there were statistically significant variations in the incidence of occupational injuries by gender, overtime, pre-job training, years of service in current position, alcohol consumption, physical exercise per week, and co-worker relationship (P<0.05). The logistic regression model showed that workers who exercised less than twice a week, did not participate in pre-job training, worked overtime, and had fair/poor/very poor colleague relationship had a higher risk of occupational injury, while women had a lower risk of occupational injury. Conclusion The distribution of occupational injury population is mainly male, and the time distribution is mainly from May to July. Gender, physical exercise, pre-job training, overtime, and colleague relationship are the influencing factors of occupational injuries. We should strengthen pre-job training, arrange work hours reasonably, and create a good working atmosphere to reduce the occurrence of occupational injuries.

Background Social psychological factors have emerged as a key area of research in occupational injury prevention. Occupational stress, a significant component of social psychology, has garnered widespread attention due to its potential impact on occupational injury. Objective To analyze the factors influencing occupational stress among cable manufacturing workers and explore the relationship between occupational stress and occupational injury, and to provide scientific evidence for reducing occupational stress and injury. Methods A questionnaire on basic demographics, occupational injury, and occupational stress (Effort-Reward Imbalance, ERI) was used to investigate 1343 workers in a cable enterprise. Chi-square test was employed to analyze the distribution of occupational stress across different worker characteristics. Logistic regression was used to identify factors influencing occupational stress, and a decision tree model was applied to assess the impact of occupational stress on injury risk. Results A total of 1225 valid questionnaires were collected, yielding a response rate of 91.2%. The positive rate of occupational stress was 28.7%, while the incidence of occupational injury in the past year was 8.6%. The results of univariate analysis revealed that workers who had experienced occupational injuries had a higher positive rate of occupational stress compared to those without injuries (P<0.05), and there were significant differences in the distribution of occupational stress by genders, overtime work, shift work, daily working hours, fatigue levels, sleep duration, family relationships, and colleague relationships (P<0.05). The logistic regression results showed that individuals who worked shifts, had fair/poor/very colleague relationships, and frequently worked overtime had a higher risk of occupational stress (P<0.05). The final decision tree model confirmed that occupational stress was a risk factor for occupational injury. Additional factors influencing occupational injury included physical exercise, colleague relationships, pre-job training participation, and gender. Workers who exercised less than twice per week and experienced occupational stress had a significantly higher risk of injury (23.6%) compared to those without occupational stress (10.9%). Conclusion Shift work, colleague relationships, and overtime work are correlated with the positive rate of occupational stress among cable manufacturing workers. Implementing a reasonable work schedule and fostering a positive work environment are recommended. Reducing occupational stress may help lower the risk of occupational injuries in this industry.

Background Light gradient boosting machine (LightGBM) has become a popular choice in prediction models due to its high efficiency and speed. However, the "black box" issues in machine learning models lead to poor model interpretability. At present, few studies have evaluated the severity of occupational injuries from the perspective of LightGBM model and model interpretability. Objective To evaluate the application value of LightGBM models and model interpretability methods in occupational injury prediction. Methods The Mine Safety and Health Administration (MSHA) occupational injury data set of mining industry workers from 1983 to 2022 was used. Injury severity (death/fatal occupational injury and permanent/partial disability) was used as the outcome variable, and the predictor variables included the month of occurrence, age, sex, time of accident, time since beginning of shift, accident time interval from shift start, total experience, total mining experience, experience at this mine, cause of injury, accident type, activity of injury, source of injury, body part of injury, work environment type, product category, and nature of injury. Feature sets were screened using least absolute shrinkage and selection operator (Lasso) regression. A LightGBM model was then employed to predict occupational injury, with area under curve (AUC) of the model serving as the primary evaluation metric; an AUC closer to 1 indicates better predictive performance of the model. The interpretability of the model was evaluated using Shapley additive explanations (SHAP). Results Through Lasso regression, 7 key influencing factors were identified, including accident time interval from shift start, experience at this mine, cause of injury, accident type, body part of injury, nature of injury, and work environment type. A LightGBM model, constructed based on feature selection via Lasso regression, demonstrated good predictive performance with an AUC value of 0.9941 (95%CI: 0.9917, 0.9966), accuracy of 0.9743, specificity of 0.9781, and sensitivity of 0.9640. The predicted probability of fatal occupational injuries showed high consistency with the actual probability of fatal occupational injuries. In the occupational injury prediction model, the importance of each indicator was analyzed through its SHAP value, and it was found that the body part of injury and the nature of injury were the two main features that affected the prediction results of the model, and the impacts of other features were relatively small. The distribution of SHAP values across body part of injury was broad, with significant impacts on the model's prediction of fatal risk, particularly for injuries to the head and neck, as well as multi-part injuries. The nature of injury also exerted influences on the model in different directions, with suffocation/drowning, crushing, and multi-part injuries having a greater impact on the risk of fatal occupational injuries. Conclusion LightGBM model is capable of efficiently processing large-scale data and providing high-precision prediction results. Research on model interpretability aids in more accurately exploring and analyzing various key risk factors for fatal occupational injuries among mining workers, and further reveals the complex interactions among these factors. This, in turn, enables better preventive intervention and protection measures, as well as optimal resource allocation for labor workers.

Background Coal workers' pneumoconiosis is a serious occupational disease in China. Exhaled volatile organic compounds (VOCs) can serve as the "breath fingerprint" of internal pathological processes, which provides a theoretical basis for exhaled VOCs to be used as potential non-invasive biomarkers for early diagnosis of coal workers' pneumoconiosis. Objective To screen out the characteristic VOCs and important characteristic VOCs of exhaled air in patients with coal workers' pneumoconiosis, and to explore the potential of these VOCs as biomarkers for early non-invasive diagnosis of the disease. Methods In this study, 27 VOCs in the exhaled breath of 22 patients with stage I coal workers' pneumoconiosis, 77 workers exposed to dust, and 92 healthy controls were quantitatively detected by thermal desorption gas chromatography-mass spectrometry (TD-GC-MS). Substances with P<0.05 in univariate analysis and variable importance projection (VIP) >1 in supervised orthogonal partial least squares discriminant analysis (OPLS-DA) model were selected as the characteristic VOCs for early diagnosis of coal workers' pneumoconiosis. Age was included in the LASSO regression model as a covariate to screen out important characteristic VOCs, and the diagnostic performance was evaluated by receiver operating characteristic (ROC) curve. Spearman correlation was further used to explore the correlation between important characteristic VOCs and clinical lung function indicators. Results Through univariate analysis and OPLS-DA modeling, 8 VOCs were selected, including 2-methylpentane, 3-methylpentane, n-hexane, methylcyclopentane, n-heptane, methylcyclohexane, 4-methyl-2-pentanone, and 2-hexanone, in exhaled breath of patients with coal workers' pneumoconiosis. The concentrations of 4 VOCs, including 3-methylpentane, n-hexane, 4-methyl-2-pentanone, and 2-hexanone, showed a decreasing trend with the increase of dust exposure years. By LASSO regression, the important characteristic VOCs of the coal workers' pneumoconiosis group and the dust exposure group were n-hexane, methylcyclohexane and 4-methyl-2-pentanone, and the important characteristic VOCs of the coal workers' pneumoconiosis group and the healthy group were 2-methyl-pentane and 4-methyl-2-pentanone. The ROC analysis showed that the area under the curve (AUC) of n-hexane, methylcyclohexane, and 4-methyl-2-pentanone were 0.969, 0.909, and 0.956, respectively, and the AUC of combined diagnosis was 0.988 and its Youden index was 0.961, suggesting that these results can serve as a valuable reference for further research on early diagnosis. The Correlation analysis found that there was a positive correlation between n-hexane and lung function indicators in the important characteristic VOCs, indicating that it could indirectly reflect the obstruction of lung function ventilation, further proving that important characteristic VOCs have the potential to monitor lung function decline. Conclusion Three important characteristic VOCs selected in this study have the potential to be used as non-invasive biomarkers for early diagnosis and disease monitoring of coal workers' pneumoconiosis, and are worthy of further study and verification.

The composition and concentration of volatile organic compounds (VOCs) in exhaled breath are closely related to human health and the analysis of VOCs by collecting human exhaled breath has been widely used in disease surveillance research. This article reviewed the collection, enrichment, and detection methods of exhaled VOCs, which can provide a reference for selecting appropriate technology for follow-up research. The exhaled breath collection devices mainly include sampling bags for mixed exhaled breath and biological volatile organic compound (Bio-VOC) samplers for alveolar air. The pre-enrichment equipment included thermal desorption (TD), solid-phase microextraction device (SPME), and needle trap device (NTD). The detection methods of exhaled VOCs include gas chromatography-mass spectrometry (GC-MS), proton transfer reaction mass spectrometry (PTR-MS), selective ion flow tube mass spectrometry (SIFT-MS), and electronic nose. At present, the collection and enrichment technology of exhaled breath is not mature yet, and its influence on the results of detection is lack of evaluation. In the future, the research on collection and enrichment technology of exhaled breath should be strengthened to further promote the application of exhaled breath in disease surveillance research.

Occupational injuries cause a large number of personal injuries, illnesses, or deaths, resulting in a huge burden of disease, and has become an important global occupational safety and health problem. Developed countries in Europe and the United States have provided strong support for occupational injury prevention and control by establishing continuous and stable occupational injury surveillance systems. The occupational injury problem has not attracted enough attention and concern in China, with few relevant research reports, and the current occupational injury surveillance system is far from perfection. From the perspective of protecting workers' occupational health, this paper analyzed and compared the classification and scope of occupational injuries at home and abroad, as well as the status quo of occupational injury surveillance and assessment, and proposed to set up an occupational injury surveillance system with multiple surveillance methods and multiple data sources that complement with each other, so as to strengthen the continuity of surveillance activities, consistency of data formats, and comparability of assessment indicators. Step by step, we can set up a surveillance system covering the whole process of surveillance, assessment, intervention, and evaluation of intervention effects.

Background Identification and analysis of influencing factors of occupational injury is an important research content of feature selection. In recent years, with the rise of machine learning algorithms, feature selection combined with Boosting algorithm provides a new analysis idea to construct occupational injury prediction models. Objective To evaluate applicability of Boosting algorithm-based model in predicting severity of miners' non-fatal occupational injuries, and provide a basis for rationally predicting the severity level of miners' non-fatal occupational injuries. Methods The publicly available data of the US Mine Safety and Health Administration (MSHA) from 2001 to 2021 on metal miners' non-fatal occupational injuries were used, and the outcome variables were lost working days < 105 d (minor injury) and ≥ 105 d (serious injury). Four different feature sets were screened out by four feature selection methods including least absolute shrinkage and selection operator (Lasso) regression, stepwise regression, single factor + Lasso regression, and single factor + stepwise regression. Logistic regression, gradient boosting decision tree (GBDT), and extreme gradient boosting (XGBoost) were selected to construct prediction models by training with the four feature sets. A total of 12 prediction models of severity of miners' non-fatal occupational injuries were built and their area under the curve (AUC), sensitivity, specificity, and Youden index were calculated for model evaluation. Results According to the results of four feature selection methods, age, time of accident occurrence, total length of service, cause of injury, activities that triggered injury occurrence, body part of injury, nature of injury, and outcome of injury were identified as influencing factors of non-fatal occupational injury severity in miners. Feature set 4 was the optimal set screened out by single factor+stepwise regression and the GBDT model presented the best predictive performance in predicting the severity of non-fatal occupational injuries. The associated specificity, sensitivity, and Youden index were 0.7530, 0.9490, and 0.7020, respectively. The AUC values of logistic regression, GBDT, and XGBoost models trained by feature set 4 were 0.8526 (95%CI: 0.8387, 0.8750), 0.8640 (95%CI: 0.8474, 0.8806), and 0.8603 (95%CI: 0.8439, 0.8773), respectively, higher than the AUC values trained by feature set 2 [0.8487 (95%CI: 0.8203, 0.8669), 0.8110 (95%CI: 0.8012, 0.8344), and 0.8439 (95%CI: 0.8245, 0.8561), respectively] . The AUC values of GBDT and XGBoost models trained by feature set 4 were higher than that of logistic regression model. Conclusion The performance of the prediction models constructed by predictors screened out by two feature selection methods is better than those by single feature selection methods. At the same time, under the condition of optimal feature set, the performance of model prediction based on Boosting is better than that of traditional logistic regression model.

Background The severity of occupational injury in countries such as the United Kingdom, the United States, and Germany is usually analyzed using lost workdays, but in existing occupational injury surveillance research in China, the application of this index is rare. Objective To evaluate the application value of lost workdays in non-fatal occupational injury surveillance, and provide a reference for the construction of occupational injury surveillance index system. Methods The public data of European Statistics on Accidents at Work (ESAW) from 2010 to 2019 on non-fatal injury accidents in 27 member states of the European Union were used. Non-fatal occupational injury is defined as an injury event during occupational activities or at work resulting a victim's absence from work for ≥4 d. According to the European Statistics on Accidents at Work-Summary methodology, the lost workdays were divided into 8 categories (4-6 d, 7-13 d, 14-20 d, 21-30 d, 31-91 d, 92-182 d, 183 d and above, and unknown). Annual percentage change (APC) and the average annual percentage change (AAPC) were used to evaluate the overall trend changes in the incidence rate of non-fatal occupational injury accidents in different lost workdays from 2010 to 2019, and the non-fatal occupational injury accidents in key industries. The characteristics of the occurrence of non-fatal occupational injuries were analyzed in conjunction with the changes in non-fatal occupational injuries in different lost workdays in the industry. Results From 2010 to 2019, the overall incidence of non-fatal occupational injury accidents in the European Union showed a downward trend, and the AAPC was −1.0% (P<0.05). The accident rates of lost workdays of 4-6 d and 92-182 d showed an upward trend, and the AAPC were 7.9% and 5.8% respectively (P<0.05). The average annual accident rates of non-fatal occupational injuries (≥4 d) in Categories C (manufacturing industry), E (water supply, sewage treatment, waste management and remediation), and F (construction industry) showed a linear downward trend, and the AAPC were −3.0%, −2.5%, and −1.5%, respectively (P<0.05). However, among them, the rate of non-fatal occupational injury accidents with 92-182 d of lost workdays in the manufacturing industry showed a significant upward trend, with an AAPC of 3.7% (P<0.001). Conclusion Using lost workdays combined with APC and AAPC by Join-point linear regression analysis can measure the severity and trend changes of non-fatal occupational injury accidents in different industries and different lost workdays. This indicator has an important practical significance in evaluating the effectiveness of occupational injury prevention and control strategies adopted by countries and enterprises.

In order to promote the development of China's occupational injury surveillance system, this paper presented the legal basis, project overview, reporting procedures, definitions and stati statistical scope, data sources and collection standards, statistical data management and analysis points of the European Statistics on Accidents at Work (ESAW), and combined with existing research and related surveillance management system in China, five key points were proposed for constructing China's occupational injury surveillance system: 1) Establish and improve laws and regulations related to occupational injury surveillance; 2) Promote utilization of nation-level data systems; 3) Establish and optimize a sound national occupational injury surveillance system; 4) Provide standardized protocols for data collection and data application of occupational injury statistics; 5) Strengthen supervision and law enforcement targeting industries and enterprises.