Impact factor selection for non-fatal occupational injuries among manufacturing workers by LASSO regression

Yingheng XIAO; Chunhua LU; Juan QIAN; Ying CHEN; Yishuo GU; Zeyun YANG; Daozheng DING; Liping LI; Xiaojun ZHU

Return

Impact factor selection for non-fatal occupational injuries among manufacturing workers by LASSO regression

VernacularTitle:基于LASSO回归模型的制造业工人非致命性职业伤害影响因素分析
Author: Yingheng XIAO ^{1
,

2} ; Chunhua LU ³ ; Juan QIAN ⁴ ; Ying CHEN ³ ; Yishuo GU ⁵ ; Zeyun YANG ³ ; Daozheng DING ⁴ ; Liping LI ² ; Xiaojun ZHU ⁵
Author Information

1. National Center for Occupational Safety and Health, National Health Commission of the People's Republic of China, NHC Key Laboratory for Engineering Control of Dust Hazard, Beijing 102308, China
2. School of Public Health, Shantou University, Shantou, Guangdong 515041, China.
3. Nantong Center for Disease Control and Prevention, Nantong, Jiangsu 226007, China.
4. Yixing Center for Disease Control and Prevention, Yixing, Jiangsu 214206, China.
5. National Center for Occupational Safety and Health, National Health Commission of the People's Republic of China, NHC Key Laboratory for Engineering Control of Dust Hazard, Beijing 102308, China.
Publication Type:Specialcolumn:Occupationalinjuriesandtheirinfluencingfactors
Keywords: non-fatal occupational injury; influencing factor; LASSO regression; machine learning; manufacture
From: Journal of Environmental and Occupational Medicine 2025;42(2):133-139
CountryChina
Language:Chinese
Abstract: Background As a pillar industry in China, the manufacturing sector has a high incidence of non-fatal occupational injuries. The factors influencing non-fatal occupational injuries in this industry are closely related at various levels, including individual, equipment, environment, and management, making the analysis of these influencing factors complex. Objective To identify influencing factors of non-fatal occupational injuries among manufacturing workers, providing a basis for targeted interventions and surveillance. Methods A total of 2243 frontline workers from cable and shipbuilding enterprises were selected as study subjects to investigate the incidence of non-fatal occupational injuries and collect information at four levels: individual, equipment, management, and environment in past 12 months. Data balancing was performed using resampling, and LASSO regression was used to select factors of non-fatal occupational injuries. The influence degree and type of variables were judged based on the magnitude of the estimated coefficients of each variable, where variables with estimated coefficients > 0 are risk factors, and those <0 are protective factors. The area under the receiver operating characteristic (ROC)curve (AUC) was used to test the performance of the model, with an AUC value > 0.7 indicating good model performance. Results Among the 2243 frontline workers, males accounted for 77.7% (1742 out of 2243), with the main age range being 40-49 years old, representing 29.5% (661 out of 2243), 82.7% of the workers (1854 out of 2243) were married, and 55.6% (1248 out of 2243) had a junior middle school education level. The average monthly income for 51.0% (1144 out of 2243) of the workers was between 5000 and 6999 Chinese Yuan. The incidence of non-fatal occupational injuries among the manufacturing workers was 8.4% (189/2243) in the past 12 months. Among the 22 factors associated with the occurrence of non-fatal occupational injuries (P<0.05), 10 were individual-level factors, including gender, smoking, alcohol consumption, colleague relationships, average exercise duration, job burnout, work fatigue, musculoskeletal disorders, cardiovascular diseases, and neurological and sensory organ diseases; 3 were equipment-level factors, including equipment operability, hazardous workpieces, and safety hazards; 5 were environmental-level factors, including low temperatures, special operations, noise, workspace size, and dirty and disorderly environment; and 4 were management-level factors, including daily working hours, weekly working days, overtime, and pre-job technical training. The AUC value of the LASSO regression model was 0.704 and the final model retained a total of 10 variables. Among them, there were 7 risk factors for non-fatal occupational injuries (coefficient > 0), including safety hazards, musculoskeletal disorders, dangerous workpieces, job burnout, dirty and disorderly environment, smoking, and male gender; and 3 protective factors (coefficient < 0), including pre-job technical training, good colleague relationship, and long working days per week. Conclusion Manufacturing enterprises need to focus on the incidence of non-fatal occupational injuries and conduct targeted interventions for non-fatal occupational injuries by controlling potential safety hazards, providing pre-job technical training, reducing dangerous workpieces, rectifying working environment, and reasonably arranging working hours.