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.

Background Per- and polyfluoroalkyl substances (PFAS) are a class of persistent organic pollu-tants. Industrial production and consumer use of PFAS are the primary sources of exposure in urban areas. E-waste recycling activities are also a significant source of environmental PFAS exposure. Objective To compare exposure profiles between traditional and emerging PFAS in neonatal cord blood collected from an e-waste recycling area and a general exposure area characterized by modern economic development (hereafter referred to as general exposure area). Methods Based on a birth cohort study conducted in 2018, 85 pregnant women were recruited (36 participants from an e-waste recycling area and 49 participants from a general exposure area). Neonatal cord blood was collected at delivery. Ultra-high performance liquid chromatography-tandem mass spectrometry (UPLC-MS/MS) was used to detect 28 common PFAS in the blood. A structured questionnaire was used to gather sociodemographic characteristics of the pregnant women. Mann-Whitney U tests were used to compare PFAS exposure levels in neonatal cord blood between the e-waste recycling area and the general exposure area. Multiple linear regression models were used to explore the influence of residing in the e-waste recycling area on neonatal PFAS exposure, with area as the independent variable and the natural logarithm of PFAS exposure levels as the dependent variable. Results A total of 22 PFAS were positive in neonatal cord blood, of which 13 congeners were 100% detectable in the samples from both areas. The median ∑PFAS exposure levels in neonatal cord blood were 14.19 ng·mL⁻¹ and 14.02 ng·mL⁻¹ for the e-waste recycling area and the general exposure area, respectively, with linear perfluorooctanoic acid (L-PFOA) showing the highest median concentration (5.49 ng·mL⁻¹ and 6.39 ng·mL⁻¹, respectively). The results of Mann-Whitney U tests showed that the median exposure levels of long-chain perfluorodecanoic acid (PFDA), perfluoroundecanoic acid (PFUnDA), perfluorododecanoic acid (PFDoDA), and perfluorotridecanoic acid (PFTrDA), as well as emerging alternatives 6:2 chlorinated polyfluorinated ether sulfonate (6:2 Cl-PFESA) and 8:2 chlorinated polyfluorinated ether sulfonate (8:2 Cl-PFESA), were higher in the e-waste recycling area than in the general exposure area. In contrast, the median exposure levels of short-chain perfluoropentanoic acid (PFPeA) and perfluorohexanoic acid (PFHxA), as well as perfluorooctanoic acid (PFOA) branched isomers, including perfluoro-6-methylheptanoic acid (iso-PFOA), perfluoro-5-methylheptanoic acid (5m-PFOA), and perfluoro-4-methylheptanoic acid (4m-PFOA), were lower in the e-waste recycling area than in the general exposure area (P<0.05). The multiple linear regression models showed that, compared to the general exposure area, neonatal cord blood in the e-waste recycling area had significantly higher exposure levels of long-chain PFDA, PFUnDA, PFDoDA, PFTrDA, and emerging alternatives 6:2 Cl-PFESA and 8:2 Cl-PFESA, with odds ratios of 1.95 (95%CI: 1.39-2.75), 2.10 (95%CI: 1.58-2.75), 2.12 (95%CI: 1.39-3.25), 2.64 (95%CI: 1.63-4.22), 3.46 (95%CI: 2.34-5.10), and 3.25 (95%CI: 2.01-5.26), respectively. Conversely, the exposure levels of short-chain PFPeA, PFHxA, and branched PFOA (br-PFOA) were significantly lower, with odds ratios of 0.44 (95%CI: 0.38-0.52), 0.30 (95%CI: 0.16-0.57), and 0.50 (95%CI: 0.38-0.67), respectively. Conclusion PFAS are widely present in neonatal cord blood in both the e-waste recycling area and the general exposure area. Compared to the general exposure area, the neonatal cord blood samples in the e-waste recycling area show higher exposure levels of certain long-chain perfluoroalkyl carboxylic acids (PFCA) and emerging PFAS alternatives, while the neonatal cord blood samples in the general exposure area show higher exposure levels of some short-chain PFCA and PFOA branched isomers.

Objective:To evaluate the effect of transcutaneous electrical acupoint stimulation (TEAS) on the intracranial pressure in patients undergoing laparoscopic hysterectomy by measuring the optic nerve sheath diameter (ONSD) via ultrasound.Methods:Forty-two American Society of Anesthesiologists Physical Status classification Ⅰ or Ⅱ patients, aged 18-60 yr, with a body mass index of 18-28 kg/m 2, scheduled for elective laparoscopic hysterectomy, were divided into 2 groups ( n=21 each) using a random number table method: control group (group C) and TEAS group (group T). In group T, TEAS was applied to the Yintang (EX-HN3) and Taiyang (EX-HN5) acupoints at 30 min before anesthesia, the stimulation used alternating dense-disperse waves at a frequency of 2/100 Hz, with the current intensity starting at 1 mA and increasing to the maximum tolerable level just below the pain threshold, and stimulation was maintained at the Hegu (LI4), Quanliao (SI18), and Fengchi (GB20) acupoints during surgery until the procedure was completed. Patients had electrode pads applied to the corresponding acupoints without electrical stimulation in group C. The ONSD was measured upon entry into the operating room (T 0), 3 min after anesthesia induction (T 1), 5 min after trendelenburg position (T 2), 30 min after trendelenburg position (T 3), 60 min after trendelenburg position (T 4), and immediately after the end of operation (T 5). Results:Compared to the baseline at T 0, the ONSD was significantly increased at T 3-5 in group C and at T 4, 5 in group T ( P<0.05). The ONSD was significantly lower at T 4, 5 in group T than in group C ( P<0.05). Conclusions:TEAS can reduce the intracranial pressure to some extent in patients undergoing laparoscopic hysterectomy.

The new business forms are the new patterns of the job market extended by the use of mobile internet, big data, cloud computing, and other information technologies in the context of a new round of information technology development. In recent years, under the catalysis of the new employment model, a large number of new business employees have emerged such as food delivery riders, couriers, and online car-hailing drivers, whose employment forms are flexible and don’t fully conform to the establishment of labor relations with the employers, and whose problem of overtime work is common. The employment characteristics of new business forms of "focusing on performance and ignoring responsibility" make workers at great risks of occupational injuries and occupational health problems such as work-related musculoskeletal disorders, mental disorders, and overwork. However, the current research on occupational safety and health of workers in new business forms is insufficient, and the experience of institutional practice and supervision is also limited. Therefore, based on relevant research progress at home and abroad, this paper discussed the health injuries of workers in new business forms, summarized associated influencing factors from four aspects: employment form, employment affiliation, long working hours exposure, and institutional guarantee, and then proposed countermeasures to strengthen occupational safety and health protection of workers. For the current problems in the employment of new business forms, the government, enterprises, and workers need to work together to improve the legal and regulatory system for employment of new business forms, and standardize occupational safety and health management, thus effectively protect the occupational safety and health rights and interests of workers in new business forms.

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.

Since its founding 100 years ago, the Communist Party of China (CPC) has attached great importance to the occupational health of workers, and closely linked the safeguard of occupational safety and health of workers with the missions of leading the people to stand up, get rich, and become strong. Based on this, the achievements of occupational health work made under the leadership of the CPC since the new democratic revolution, socialist revolution and construction, the new period of reform and opening up and socialist modernization, and socialism with Chinese characteristics for a new era were summarized, so as to provide reference for understanding the legacy of China's occupational health undertaking, and innovating to create the future.

Objective:To understand the current situation of the construction of occupational health information system in China and put forward countermeasures and suggestions for the construction of occupational health information system.Methods:In November 2019 and April 2020, a cross-sectional survey was conducted on the occupational health information systems of national, provincial and some central enterprises. A total of 57 occupational health information systems were investigated, including 4 national systems, 44 provincial systems and 9 industrial systems. The terminal type, main function, construction type, user classification and main authority, computer terminal structure, data collection mode, data transmission mode, data docking are analyzed.Results:The four national level systems all adopt B/S structure, and all transmit network data through computer terminals. The main data acquisition mode is online acquisition and external system docking. Among the 44 provincial-level systems, 41 (93.18%) were self built systems, 75.00% (33/44) were computer terminals, and 90.91% (40/44) were B/s structures; 17 (38.64%) systems used multiple data acquisition methods; 13.64% (6/44) systems used multiple data transmission methodsand the main way of data transmission method is network report (88.64%, 39/44) ; 84.09% (37/44) of the system network access mode was Internet mode. Among the nine industry systems, 66.67% (6/9) of them deployed servers in the form of self built computer rooms, 77.78% (7/9) of them supported docking and reserved ports; 66.67% (6/9) of them used computer terminals, and 100.00% (9/9) of them used B/S structure; 77.78% (7/9) of them used manual filling for data collection.Conclusion:The construction of occupational health information system in China has many problems, such as scattered and separate construction, and lack of effective data sharing between related systems, it＇s urgent to unify the standard and plan as a whole.

Objective:To understand the current situation of the construction of occupational health information system in China and put forward countermeasures and suggestions for the construction of occupational health information system.Methods:In November 2019 and April 2020, a cross-sectional survey was conducted on the occupational health information systems of national, provincial and some central enterprises. A total of 57 occupational health information systems were investigated, including 4 national systems, 44 provincial systems and 9 industrial systems. The terminal type, main function, construction type, user classification and main authority, computer terminal structure, data collection mode, data transmission mode, data docking are analyzed.Results:The four national level systems all adopt B/S structure, and all transmit network data through computer terminals. The main data acquisition mode is online acquisition and external system docking. Among the 44 provincial-level systems, 41 (93.18%) were self built systems, 75.00% (33/44) were computer terminals, and 90.91% (40/44) were B/s structures; 17 (38.64%) systems used multiple data acquisition methods; 13.64% (6/44) systems used multiple data transmission methodsand the main way of data transmission method is network report (88.64%, 39/44) ; 84.09% (37/44) of the system network access mode was Internet mode. Among the nine industry systems, 66.67% (6/9) of them deployed servers in the form of self built computer rooms, 77.78% (7/9) of them supported docking and reserved ports; 66.67% (6/9) of them used computer terminals, and 100.00% (9/9) of them used B/S structure; 77.78% (7/9) of them used manual filling for data collection.Conclusion:The construction of occupational health information system in China has many problems, such as scattered and separate construction, and lack of effective data sharing between related systems, it＇s urgent to unify the standard and plan as a whole.

Objective:To analyze the correlation of phthalate metabolites in neonatal umbilical cord blood with birth indicators in Beijing, 2015.Method:From February to July in 2015, 161 pregnant women and their newborns who met the criteria were recruited from the Maternal and Child Health Hospital in Haidian District, Beijing. Questionnaires were used to collect the demographic information of pregnant women such as age, smoking, drinking, and cord blood after delivery. An ultra-high performance liquid chromatography-tandem mass spectrometry was used to determine the concentration of phthalate metabolites in umbilical cord blood. The multiple linear regression model was used to analyze the correlation of phthalate metabolites in umbilical cord blood with the neonatal weight, length, and ponderal index.Result:The age of 161 pregnant women was (30.3±3.0) years. The weight, length and ponderal index of 161 newborns were (3 447.2±413.0) kg, (50.2±1.1) cm, and (26.7±2.2) kg/m 3; 51.6% of newborns (83 cases) were boys. The concentrations of seven phthalate metabolites detected in umbilical cord blood, i.e., mono-methyl phthalate (MMP), mono-ethyl phthalate (MEP),mono-(2-isobutyl) phthalate (MiBP), mono-n-butyl phthalate (MBP), mono-ethylhexyl phthalate (MEHP), mono-(2-ethyl-5-oxohexyl) phthalate (MEOHP), and mono-(2-ethyl-5-carboxypentyl) phthalate (MECPP), was (3.50±0.28), (2.65±0.47), (4.31±0.55), (6.26±0.57), (1.71±0.13), (1.10±0.09) and (0.47±0.06) ng/ml, respectively. The result of multiple linear regression model analysis showed that the concentrations of seven phthalate metabolites were not related to the neonatal weight, length, and ponderal index (all P values> 0.05). Conclusion:The concentrations of phthalate metabolites in neonatal umbilical cord blood are low, and they are not related to the neonatal weight, length, and ponderal index.