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.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.
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.Association between Chronic Obsructive Pulmonary Disease and Dietary Inflammatory Index in Korean Men Over 40s-based on the 2016-2019 Korea National Health and Nutrition Examination Survey
Korean Journal of Health Promotion 2023;23(4):182-189
Background:
This study aimed to explore the association between chronic obsructive pulmonary disease (COPD) and dietary inflammatory index (DII) in Korean male adults.
Methods:
The subjects consisted of 4,267 Korean male adults aged over 40 years in the National Health and Nutrition Examination Survey from 2016-2019. Subjects were categorized into four groups based on quartiles of dietary inflammatory index score.
Results:
Individuals with high DII score had poor health habits such as drinking, smoking, activity limitations. The intake of anti-inflammatory items except monounsaturated fatty acid decreased as the DII item score increased. The higher the score of DII, the lower the forced expiratory volumn in 1 sec (FEV1), forced vital capacity (FVC), FEV1/FVC which are lung function measures. The prevalence of COPD increased in the highest quartile of the DII score.
Conclusions
It was found that dietary inflammatory index was significantly associated with lung function and COPD. The promotion of a healthy diet with anti-inflammatory properties may help to prevent COPD in male adults.
5.Comparison of Eating Habits and Behaviors of Young Single-Person Households based on Food-Related Lifestyle
Korean Journal of Health Promotion 2023;23(3):117-129
Background:
This study aimed to investigate the dietary habit problems related to lifestyle by analyzing health behaviors and dietary habits in Korean young adults.
Methods:
Adults aged 20≥ and ≥39 years single-person households who participated in the survey were included in the study. Subjects were classified into food related lifestyle. Subsequently, characteristics, health behaviors, dietary habits were analyzed.
Results:
The participants of the study were classified into five types: a ‘taste-type’, an ‘economy-type’, a ‘convenience-type’, a ‘health-type’, and a ‘safety-type’. As a result of comparing eating habits by food-related lifestyles, the ‘economy-type’ showed the highest dietary assessment with a score of 3.18, while the ‘safety-type’ ranked the lowest, a score of 2.54. The ‘economy-type’ scored highest they ate out less, cooked more, suggesting a need for nutritious cooking classes. The ‘health-type’, with more men and price-conscious individuals, sought healthier convenience options. The ‘taste-type’ preferred food delivery and dining out, needing balanced menus. In contrast, the ‘convenience-type’ overate, scoring low in habits, emphasizing the need for healthier menus and support. The ‘safety-type’ which has a high percentage of jobs in the service industry and high school graduates, showed the need for policy support for better diet.
Conclusions
Young single-person households have different dietary problems depending on their food-related lifestyle. Therefore, we recommended for the customized dietary education considering the characteristics of each type.
6.Guidelines for Cancer Care during the COVID-19 Pandemic in South Korea
Jii Bum LEE ; Minkyu JUNG ; June Hyuk KIM ; Bo Hyun KIM ; Yeol KIM ; Young Seok KIM ; Byung Chang KIM ; Jin KIM ; Sung Ho MOON ; Keon-Uk PARK ; Meerim PARK ; Hyeon Jin PARK ; Sung Hoon SIM ; Hong Man YOON ; Soo Jung LEE ; Eunyoung LEE ; June Young CHUN ; Youn Kyung CHUNG ; So-Youn JUNG ; Jinsoo CHUNG ; Eun Sook LEE ; Hyun Cheol CHUNG ; Tak YUN ; Sun Young RHA
Cancer Research and Treatment 2021;53(2):323-329
At the end of 2019, the cause of pneumonia outbreaks in Wuhan, China, was identified as severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection. In February 2020, the World Health Organization named the disease cause by SARS-CoV-2 as coronavirus disease 2019 (COVID-19). In response to the pandemic, the Korean Cancer Association formed the COVID-19 task force to develop practice guidelines. This special article introduces the clinical practice guidelines for cancer patients which will help oncologists best manage cancer patients during the COVID-19 pandemic.
7.The Study of Dietary Habits and Health Behaviors according to Physical Activity Type in Korean Adults -Based on the 2016~2018 Korea National Health and Nutrition Examination Survey-
Korean Journal of Community Nutrition 2021;26(2):122-133
Objectives:
This study evaluated the dietary habits and health behaviors of Korean adults according to their physical activity.
Methods:
Adults aged 19~64 years, who participated in the 2016~2018 National Health and Nutrition Examination Survey, were enrolled in this study. The subjects were classified into the physical inactivity group, aerobic physical activity group, strength exercise group, and combined exercise group.
Results:
Significant differences in skipping breakfast, frequency of eating out, dietary supplements, and alcohol drinking status were observed among physical activity groups (P < 0.001). The combined exercise group had the highest % KDRI of protein, vitamin A, thiamin, riboflavin, niacin, calcium, potassium, and iron (P < 0.001). The physical inactivity group had the highest obesity rate (35.1%), and they perceived their body image type to be obese. In the combined exercise group, 47.8% of respondents said they were in good health (P < 0.001). The health-related quality of life score of the physical inactivity group was the lowest, with a score of 0.94. The metabolic syndrome risk rate of the combined exercise group was lower at 0.62 times (95% CI, 0.51-0.75) than the physical inactivity group.
Conclusions
The physical activity type was associated with metabolic syndrome.These results can be useful for supporting dietary education and physical activity programs for adults.
8.Analysis of Awareness, Knowledge, and Behavior about Food Hygiene·Safety Among the elderly
Korean Journal of Community Nutrition 2021;26(3):200-210
Objectives:
This study was conducted to investigate the awareness, knowledge, and behavior about food hygiene·safety among the elderly, and to provide basic data on this for their healthy dietary life.
Methods:
The study was conducted through a survey using a self-administered questionnaire on 473 elderly people over 60 years old living in Seoul and Gyeonggido. The questionnaire was designed to examine general characteristics, meal preparation status, the relation between awareness, knowledge, food hygiene behavior, and safety.
Results:
Among the particpants, 44.2% of the total people surveyed were elderly married couples, and 14.0% were single-person households. For men, most of the meals were prepared by the spouse (74.1%), and among women, 93.8% prepared their meals themselves (P < 0.001). 61.3% of the total subjects answered that they were very interested in food hygiene and safety. Men (32.4%) thought it was more difficult to collect food hygiene·safety information compared to women (14.0%, P < 0.001). The knowledge score about food hygiene·safety was 0.60 (P < 0.05) and the behavior score was 3.70 (P < 0.001). The correlation coefficient between knowledge and behavior according to food hygiene·safety was 0.371 (P < 0.001).
Conclusions
The food hygiene·safety behavior of the elderly was associated with knowledge (P < 0.001). Therefore, food hygiene·safety education is necessary to ensure information availability and promote the health of the elderly.
9.Guidelines for Cancer Care during the COVID-19 Pandemic in South Korea
Jii Bum LEE ; Minkyu JUNG ; June Hyuk KIM ; Bo Hyun KIM ; Yeol KIM ; Young Seok KIM ; Byung Chang KIM ; Jin KIM ; Sung Ho MOON ; Keon-Uk PARK ; Meerim PARK ; Hyeon Jin PARK ; Sung Hoon SIM ; Hong Man YOON ; Soo Jung LEE ; Eunyoung LEE ; June Young CHUN ; Youn Kyung CHUNG ; So-Youn JUNG ; Jinsoo CHUNG ; Eun Sook LEE ; Hyun Cheol CHUNG ; Tak YUN ; Sun Young RHA
Cancer Research and Treatment 2021;53(2):323-329
At the end of 2019, the cause of pneumonia outbreaks in Wuhan, China, was identified as severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection. In February 2020, the World Health Organization named the disease cause by SARS-CoV-2 as coronavirus disease 2019 (COVID-19). In response to the pandemic, the Korean Cancer Association formed the COVID-19 task force to develop practice guidelines. This special article introduces the clinical practice guidelines for cancer patients which will help oncologists best manage cancer patients during the COVID-19 pandemic.
10.The Study of Dietary Habits and Health Behaviors according to Physical Activity Type in Korean Adults -Based on the 2016~2018 Korea National Health and Nutrition Examination Survey-
Korean Journal of Community Nutrition 2021;26(2):122-133
Objectives:
This study evaluated the dietary habits and health behaviors of Korean adults according to their physical activity.
Methods:
Adults aged 19~64 years, who participated in the 2016~2018 National Health and Nutrition Examination Survey, were enrolled in this study. The subjects were classified into the physical inactivity group, aerobic physical activity group, strength exercise group, and combined exercise group.
Results:
Significant differences in skipping breakfast, frequency of eating out, dietary supplements, and alcohol drinking status were observed among physical activity groups (P < 0.001). The combined exercise group had the highest % KDRI of protein, vitamin A, thiamin, riboflavin, niacin, calcium, potassium, and iron (P < 0.001). The physical inactivity group had the highest obesity rate (35.1%), and they perceived their body image type to be obese. In the combined exercise group, 47.8% of respondents said they were in good health (P < 0.001). The health-related quality of life score of the physical inactivity group was the lowest, with a score of 0.94. The metabolic syndrome risk rate of the combined exercise group was lower at 0.62 times (95% CI, 0.51-0.75) than the physical inactivity group.
Conclusions
The physical activity type was associated with metabolic syndrome.These results can be useful for supporting dietary education and physical activity programs for adults.

Result Analysis
Print
Save
E-mail