1.Occupation classification model based on DistilKoBERT: using the 5th and 6th Korean Working Condition Surveys
Tae-Yeon KIM ; Seong-Uk BAEK ; Myeong-Hun LIM ; Byungyoon YUN ; Domyung PAEK ; Kyung Ehi ZOH ; Kanwoo YOUN ; Yun Keun LEE ; Yangho KIM ; Jungwon KIM ; Eunsuk CHOI ; Mo-Yeol KANG ; YoonHo CHO ; Kyung-Eun LEE ; Juho SIM ; Juyeon OH ; Heejoo PARK ; Jian LEE ; Jong-Uk WON ; Yu-Min LEE ; Jin-Ha YOON
Annals of Occupational and Environmental Medicine 2024;36(1):e19-
Accurate occupation classification is essential in various fields, including policy development and epidemiological studies. This study aims to develop an occupation classification model based on DistilKoBERT. This study used data from the 5th and 6th Korean Working Conditions Surveys conducted in 2017 and 2020, respectively. A total of 99,665 survey participants, who were nationally representative of Korean workers, were included. We used natural language responses regarding their job responsibilities and occupational codes based on the Korean Standard Classification of Occupations (7th version, 3-digit codes). The dataset was randomly split into training and test datasets in a ratio of 7:3. The occupation classification model based on DistilKoBERT was fine-tuned using the training dataset, and the model was evaluated using the test dataset. The accuracy, precision, recall, and F1 score were calculated as evaluation metrics. The final model, which classified 28,996 survey participants in the test dataset into 142 occupational codes, exhibited an accuracy of 84.44%. For the evaluation metrics, the precision, recall, and F1 score of the model, calculated by weighting based on the sample size, were 0.83, 0.84, and 0.83, respectively. The model demonstrated high precision in the classification of service and sales workers yet exhibited low precision in the classification of managers. In addition, it displayed high precision in classifying occupations prominently represented in the training dataset. This study developed an occupation classification system based on DistilKoBERT, which demonstrated reasonable performance. Despite further efforts to enhance the classification accuracy, this automated occupation classification model holds promise for advancing epidemiological studies in the fields of occupational safety and health.
2.Cooking oil fume exposure and Lung-RADS distribution among school cafeteria workers of South Korea
Minjun KIM ; Yangho KIM ; A Ram KIM ; Woon Jung KWON ; Soyeoun LIM ; Woojin KIM ; Cheolin YOO
Annals of Occupational and Environmental Medicine 2024;36(1):e2-
Cooking oil fumes (COFs) from cooking with hot oil may contribute to the pathogenesis of lung cancer. Since 2021, occupational lung cancer for individual cafeteria workers has been recognized in South Korea. In this study, we aimed to identify the distribution of lung-imaging reporting and data system (Lung-RADS) among cafeteria workers and to determine factors related to Lung-RADS distribution. We included 203 female participants who underwent low-dose computed tomography (LDCT) screening at a university hospital and examined the following variables: age, smoking status, second-hand smoke, height, weight, and years of service, mask use, cooking time, heat source, and ventilation. We divided all participants into culinary and non-culinary workers. Binomial logistic regression was conducted to determine the risk factors on LDCT of Category ≥ 3, separately for the overall group and the culinary group. In this study, Lung-RADS-positive occurred in 17 (8.4%) individuals, all of whom were culinary workers. Binary logistic regression analyses were performed and no variables were found to have a significant impact on Lung-RADS results. In the subgroup analysis, the Lung-RADS-positive, and -negative groups differed only in ventilation. Binary logistic regression showed that the adjusted odds ratio (aOR) of the Lung-RADS-positive group for inappropriate ventilation at the workplace was 14.89 (95% confidence interval [CI]: 3.296–67.231) compared to appropriate ventilation as the reference, and the aOR for electric appliances at home was 4.59 (95% CI: 1.061–19.890) using liquid fuel as the reference. The rate of Lung-RADS-positive was significantly higher among culinary workers who performed actual cooking tasks than among nonculinary workers. In addition, appropriate ventilation at the workplace made the LDCT results differ. More research is needed to identify factors that might influence LDCT findings among culinary workers, including those in other occupations.
3.Occupation classification model based on DistilKoBERT: using the 5th and 6th Korean Working Condition Surveys
Tae-Yeon KIM ; Seong-Uk BAEK ; Myeong-Hun LIM ; Byungyoon YUN ; Domyung PAEK ; Kyung Ehi ZOH ; Kanwoo YOUN ; Yun Keun LEE ; Yangho KIM ; Jungwon KIM ; Eunsuk CHOI ; Mo-Yeol KANG ; YoonHo CHO ; Kyung-Eun LEE ; Juho SIM ; Juyeon OH ; Heejoo PARK ; Jian LEE ; Jong-Uk WON ; Yu-Min LEE ; Jin-Ha YOON
Annals of Occupational and Environmental Medicine 2024;36(1):e19-
Accurate occupation classification is essential in various fields, including policy development and epidemiological studies. This study aims to develop an occupation classification model based on DistilKoBERT. This study used data from the 5th and 6th Korean Working Conditions Surveys conducted in 2017 and 2020, respectively. A total of 99,665 survey participants, who were nationally representative of Korean workers, were included. We used natural language responses regarding their job responsibilities and occupational codes based on the Korean Standard Classification of Occupations (7th version, 3-digit codes). The dataset was randomly split into training and test datasets in a ratio of 7:3. The occupation classification model based on DistilKoBERT was fine-tuned using the training dataset, and the model was evaluated using the test dataset. The accuracy, precision, recall, and F1 score were calculated as evaluation metrics. The final model, which classified 28,996 survey participants in the test dataset into 142 occupational codes, exhibited an accuracy of 84.44%. For the evaluation metrics, the precision, recall, and F1 score of the model, calculated by weighting based on the sample size, were 0.83, 0.84, and 0.83, respectively. The model demonstrated high precision in the classification of service and sales workers yet exhibited low precision in the classification of managers. In addition, it displayed high precision in classifying occupations prominently represented in the training dataset. This study developed an occupation classification system based on DistilKoBERT, which demonstrated reasonable performance. Despite further efforts to enhance the classification accuracy, this automated occupation classification model holds promise for advancing epidemiological studies in the fields of occupational safety and health.
4.Cooking oil fume exposure and Lung-RADS distribution among school cafeteria workers of South Korea
Minjun KIM ; Yangho KIM ; A Ram KIM ; Woon Jung KWON ; Soyeoun LIM ; Woojin KIM ; Cheolin YOO
Annals of Occupational and Environmental Medicine 2024;36(1):e2-
Cooking oil fumes (COFs) from cooking with hot oil may contribute to the pathogenesis of lung cancer. Since 2021, occupational lung cancer for individual cafeteria workers has been recognized in South Korea. In this study, we aimed to identify the distribution of lung-imaging reporting and data system (Lung-RADS) among cafeteria workers and to determine factors related to Lung-RADS distribution. We included 203 female participants who underwent low-dose computed tomography (LDCT) screening at a university hospital and examined the following variables: age, smoking status, second-hand smoke, height, weight, and years of service, mask use, cooking time, heat source, and ventilation. We divided all participants into culinary and non-culinary workers. Binomial logistic regression was conducted to determine the risk factors on LDCT of Category ≥ 3, separately for the overall group and the culinary group. In this study, Lung-RADS-positive occurred in 17 (8.4%) individuals, all of whom were culinary workers. Binary logistic regression analyses were performed and no variables were found to have a significant impact on Lung-RADS results. In the subgroup analysis, the Lung-RADS-positive, and -negative groups differed only in ventilation. Binary logistic regression showed that the adjusted odds ratio (aOR) of the Lung-RADS-positive group for inappropriate ventilation at the workplace was 14.89 (95% confidence interval [CI]: 3.296–67.231) compared to appropriate ventilation as the reference, and the aOR for electric appliances at home was 4.59 (95% CI: 1.061–19.890) using liquid fuel as the reference. The rate of Lung-RADS-positive was significantly higher among culinary workers who performed actual cooking tasks than among nonculinary workers. In addition, appropriate ventilation at the workplace made the LDCT results differ. More research is needed to identify factors that might influence LDCT findings among culinary workers, including those in other occupations.
5.Occupation classification model based on DistilKoBERT: using the 5th and 6th Korean Working Condition Surveys
Tae-Yeon KIM ; Seong-Uk BAEK ; Myeong-Hun LIM ; Byungyoon YUN ; Domyung PAEK ; Kyung Ehi ZOH ; Kanwoo YOUN ; Yun Keun LEE ; Yangho KIM ; Jungwon KIM ; Eunsuk CHOI ; Mo-Yeol KANG ; YoonHo CHO ; Kyung-Eun LEE ; Juho SIM ; Juyeon OH ; Heejoo PARK ; Jian LEE ; Jong-Uk WON ; Yu-Min LEE ; Jin-Ha YOON
Annals of Occupational and Environmental Medicine 2024;36(1):e19-
Accurate occupation classification is essential in various fields, including policy development and epidemiological studies. This study aims to develop an occupation classification model based on DistilKoBERT. This study used data from the 5th and 6th Korean Working Conditions Surveys conducted in 2017 and 2020, respectively. A total of 99,665 survey participants, who were nationally representative of Korean workers, were included. We used natural language responses regarding their job responsibilities and occupational codes based on the Korean Standard Classification of Occupations (7th version, 3-digit codes). The dataset was randomly split into training and test datasets in a ratio of 7:3. The occupation classification model based on DistilKoBERT was fine-tuned using the training dataset, and the model was evaluated using the test dataset. The accuracy, precision, recall, and F1 score were calculated as evaluation metrics. The final model, which classified 28,996 survey participants in the test dataset into 142 occupational codes, exhibited an accuracy of 84.44%. For the evaluation metrics, the precision, recall, and F1 score of the model, calculated by weighting based on the sample size, were 0.83, 0.84, and 0.83, respectively. The model demonstrated high precision in the classification of service and sales workers yet exhibited low precision in the classification of managers. In addition, it displayed high precision in classifying occupations prominently represented in the training dataset. This study developed an occupation classification system based on DistilKoBERT, which demonstrated reasonable performance. Despite further efforts to enhance the classification accuracy, this automated occupation classification model holds promise for advancing epidemiological studies in the fields of occupational safety and health.
6.Cooking oil fume exposure and Lung-RADS distribution among school cafeteria workers of South Korea
Minjun KIM ; Yangho KIM ; A Ram KIM ; Woon Jung KWON ; Soyeoun LIM ; Woojin KIM ; Cheolin YOO
Annals of Occupational and Environmental Medicine 2024;36(1):e2-
Cooking oil fumes (COFs) from cooking with hot oil may contribute to the pathogenesis of lung cancer. Since 2021, occupational lung cancer for individual cafeteria workers has been recognized in South Korea. In this study, we aimed to identify the distribution of lung-imaging reporting and data system (Lung-RADS) among cafeteria workers and to determine factors related to Lung-RADS distribution. We included 203 female participants who underwent low-dose computed tomography (LDCT) screening at a university hospital and examined the following variables: age, smoking status, second-hand smoke, height, weight, and years of service, mask use, cooking time, heat source, and ventilation. We divided all participants into culinary and non-culinary workers. Binomial logistic regression was conducted to determine the risk factors on LDCT of Category ≥ 3, separately for the overall group and the culinary group. In this study, Lung-RADS-positive occurred in 17 (8.4%) individuals, all of whom were culinary workers. Binary logistic regression analyses were performed and no variables were found to have a significant impact on Lung-RADS results. In the subgroup analysis, the Lung-RADS-positive, and -negative groups differed only in ventilation. Binary logistic regression showed that the adjusted odds ratio (aOR) of the Lung-RADS-positive group for inappropriate ventilation at the workplace was 14.89 (95% confidence interval [CI]: 3.296–67.231) compared to appropriate ventilation as the reference, and the aOR for electric appliances at home was 4.59 (95% CI: 1.061–19.890) using liquid fuel as the reference. The rate of Lung-RADS-positive was significantly higher among culinary workers who performed actual cooking tasks than among nonculinary workers. In addition, appropriate ventilation at the workplace made the LDCT results differ. More research is needed to identify factors that might influence LDCT findings among culinary workers, including those in other occupations.
7.Characteristics of Work-related Fatal Injuries Among Aged Workers in Republic of Korea
Jungsun PARK ; Jong-shik PARK ; Younghoon JUNG ; Minoh NA ; Yangho KIM
Safety and Health at Work 2024;15(2):158-163
Objectives:
The present paper aimed to examine whether an aging workforce is associated with an increase in work-related fatal injuries and to explore the underlying reasons for this potential increase.Material and methodsAged workers were defined as those who were at least 55 years old. Work-related fatalities were assessed in aged and young workers who were registered with the workers' compensation system in 2021 in the Republic of Korea. Total waged workers, based on raw data from the Local Area Labor Force Survey in 2021, were used as the denominator to estimate the work-related fatality rates.
Results:
Most work-related fatalities in the aged workers occurred among individuals working in the “construction sector” (58.9%), those with “elementary occupations (unskilled workers)” (46.1%), and those with the employment status of “daily worker” (60.8%). The estimated incidence (0.973/10,000) of work-related fatalities among aged workers was about four times higher than that (0.239/10,000) among younger workers. “Falling,” “collision,” “struck by an object,” and “trip and slip” were more frequent types of work-related fatalities among aged workers relative to young workers. The category of “buildings, structures, and surfaces” was a more frequent cause of work-related fatalities among aged workers than among young workers.
Conclusions
Aged workers had a higher incidence of work-related fatalities than young workers. Frequent engagement in precarious employment and jobs, coupled with the greater physical vulnerability of aged workers, were likely causes of their higher level of work-related fatal injuries.
8.Decrease in Weekly Working Hours of Korean Workers From 2010 to 2020According to Employment Status and Industrial Sector
Journal of Korean Medical Science 2023;38(22):e171-
Background:
The present study examined changes in the working hours of Korean workers from 2010 to 2020 according to employment status and industrial sector.
Methods:
This was a secondary analysis of data from the third (2010), fourth (2014), fifth (2017) and sixth (2020) Korean Working Conditions Surveys, which were conducted by the Korea Occupational Safety and Health Agency.
Results:
During the past 10 years, workers classified as employees, self-employed, or employers experienced clear declines in average weekly working hours and in the percentages of individuals who worked more than 48 hours per week. During 2020, the largest proportion of employees (52.8%) had 40-hour work weeks, whereas the largest proportions of selfemployed individuals (26.8%) and employers (25.1%) had very long work weeks (≥ 60 h/ week). Also during 2020, individuals who were self-employed or employers in the sectors of ‘Accommodation and food service’ had the longest weekly work hours, whereas employees in the sector of ‘Transportation’ had the longest weekly work hours. All three groups (employees, self-employed, and employers) in all 21 industrial sectors experienced declines in average weekly working hours from 2017 to 2020.
Conclusion
From 2010 to 2020, employees, self-employed individuals, and employers experienced clear declines in average weekly working hours, and in the percentages of individuals with long weekly working hours. However, there were also differences in the weekly working hours of those who had different employment status and who worked in different industrial sectors. The implementation of the 40-hour work-week and the 52-hour maximum work-week in Korea reduced excessive work hours by individuals who had different employment status and who worked in different industrial sectors, and probably improved worker quality-of-life. We recommend extension of these regulations to workplaces with fewer than 5 employees.
9.Reduced Diffusing Capacity in Humidifier Disinfectant-Associated Asthma Versus Typical Asthma:A Retrospective Case Control Study
Chuiyong PAK ; Clayton T. COWL ; Jin Hyoung KIM ; Byung Ju KANG ; Taehoon LEE ; Yangjin JEGAL ; Seung Won RA ; Yangho KIM
Journal of Korean Medical Science 2022;37(44):e319-
Background:
Humidifier disinfectant-related lung injury (HDLI) is a severe form of toxic inhalational pulmonary parenchymal damage found in residents of South Korea previously exposed to specific guanidine-based compounds present in humidifier disinfectants (HD). HD-associated asthma (HDA), which is similar to irritant-induced asthma, has been recognized in victims with asthma-like symptoms and is probably caused by airway injury. In this study, diffusing capacity of the lung for carbon monoxide (DL CO ) in individuals with HDA was compared to that in individuals with pre-existing asthma without HD exposure.
Methods:
We retrospectively compared data, including DLCO values, of 70 patients with HDA with that of 79 patients having pre-existing asthma without any known exposure to HD (controls). Multiple linear regression analysis and logistic regression analysis were performed to confirm the association between HD exposure and DL CO after controlling for confounding factors. The correlation between DLCO and several indicators related to HD exposure was evaluated in patients with HDA.Result: The mean DLCO was significantly lower in the HDA group than in the control group (81.9% vs. 88.6%; P = 0.021). The mean DLCO of asthma patients with definite HD exposure was significantly lower than that of asthma patients with lesser exposure (P for trend = 0.002). In multivariable regression models, DLCO in the HDA group decreased by 5.8%, and patients with HDA were 2.1-fold more likely to have a lower DLCO than the controls. Pathway analysis showed that exposure to HD directly affected DLCO values and indirectly affected its measurement through a decrease in the forced vital capacity (FVC). Correlation analysis indicated a significant inverse correlation between DLCO % and cumulative HD exposure time.
Conclusion
DLCO was lower in patients with HDA than in asthma patients without HD exposure, and decreased FVC partially mediated this effect. Therefore, monitoring the DL CO may be useful for early diagnosis of HDA in patients with asthma symptoms and history of HD exposure.
10.Association of Participation in Health Check-ups with Risk Factors for Cardiovascular Diseases
Bok Hyun PARK ; Byung-Kook LEE ; Jaeouk AHN ; Nam-Soo KIM ; Jungsun PARK ; Yangho KIM
Journal of Korean Medical Science 2021;36(3):e19-
Background:
We compared the risk factors for cardiovascular diseases (CVDs) among Koreans who did and did not participate in national periodic health check-ups, after adjustment for demographic factors, socioeconomic status, and lifestyle factors.
Methods:
This cross-sectional study used data from the Korea National Health and Nutrition Examination Survey (KNHANES) from 2007 to 2018. Study subjects were classified as participants or non-participants in health check-ups, based on attendance at national periodic health check-ups during the previous two years.
Results:
Comparison of participants and non-participants in health check-ups indicated statistically significant differences in age, gender, region, education level, monthly income, employment status, obesity, smoking, alcohol consumption, exercise, and marital status. After adjustment for demographic, socioeconomic factors, and health-related behaviors, woman non-participants were more likely to have metabolic syndrome, pre-hypertension, hypertension, prediabetes, and diabetes, and man non-participants were more likely to have pre-diabetes and diabetes.
Conclusion
Subjects who participated in periodic health check-ups had fewer CVD-related risk factors than non-participants. Thus, health care providers should encourage nonparticipants to attend periodic health check-ups so that appropriate interventions can be implemented and decrease the risk for CVDs in these individuals.

Result Analysis
Print
Save
E-mail