1 March 2021 in Safety and Health at Work
A job-exposure matrix (JEM) is an important surrogate indicator to evaluate past exposure levels. Although a Korean asbestos JEM has been constructed previously, this JEM includes only a few industrial and occupational groups. This study aimed to reconstruct the JEM by integrating the latest organized data to improve its utility. We used recent Korean standard industry and occupation codes and extracted 36 articles from a systematic literature review to initiate the reconstruction of the previous Korean asbestos JEM. The resulting data consisted of 141 combinations of industrial and occupational groups. Data from the Netherlands's JEM were also reviewed and categorized into 70 industrial and 117 occupational groups by matching with the Korean data. We also utilized Germany's data, which consisted of 10 industrial and 14 occupational groups. The reconstructed Korean asbestos JEM had 141 combinations of industries and occupations. The time periods are from the 1980s to the 2000s in 10-year intervals. Most of the data were distributed between the 1990s and the 2000s. Occupations with high exposure to asbestos included knitting and weaving machine operators, automobile mechanics or assemblers, ship mechanics or assemblers, mineral ore and stone products processing mechanics, and metal casting machine operators or mold makers. The reconstructed Korean asbestos JEM has expanded the type and duration of the occupational groups of the previous JEM and can serve as an important reference tool for evaluating asbestos exposure and designing compensation and prevention policies in Korea.
26 October 2022 in Annals of Occupational and Environmental Medicine
Cha EW, et al. Ann Occup Environ Med. 2022 Oct;34:e31. https://doi.org/10.35371/aoem.2022.34.e31
1 January 2020 in Annals of Occupational and Environmental Medicine
Jung S, et al. Ann Occup Environ Med. 2020 Jun;32:e21. https://doi.org/10.35371/aoem.2020.32.e21
21 January 2025 in Safety and Health at Work
This study aimed to develop prediction models for the work-relatedness of shoulder diseases through machine learning algorithms. The dataset comprised 7,270 cases of 8,302 individuals who applied for occupational diseases and received the final approval decision from the Korea Workers' Compensation and Welfare Service's Disease Evaluation Committee, which is related to shoulder musculoskeletal disorders between January 2020 and December 2021. In this study, demographic analysis and difference of approval rate by shoulder diseases were performed. Additionally, machine learning algorithms, including logistic regression, support vector machine, decision tree, random forest, and the XGBoost, were utilized to construct prediction models for work-relatedness assessment. The performance of each model was evaluated. XGBoost showed an accuracy of 81.64% and an area under the curve of 0.73, and random forest showed an accuracy of 84.46% and an area under the curve of 0.73. Key factors influencing work-relatedness assessment were employment period, physical burden score, gender, and age. The application of various machine learning techniques showed high performance score, representing that it would be helpful to reduce the differences in judgment between occupational environment medicine physicians.