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.Related Factors for Not Washing Hands at School among Adolescents
Hyo Jin SAGONG ; Yu-Mi LEE ; Eunsuk CHOI ; Keonyeop KIM
Journal of Agricultural Medicine & Community Health 2022;47(1):14-26
Objectives:
Handwashing is one of the most effective methods to prevent the spread of infectious diseases. This study assessed the related factors and reasons for not practicing handwashing at school among adolescents.
Methods:
We analyzed data collected from 57,303 adolescents who participated in the 15th Korea Youth Risk Behavior Survey 2019.
Results:
The proportions of not washing hands “before meals at school” and “after using the toilet at school” were 15.9% and 4.4%, respectively. The adjusted odds ratio for not washing hands before meals at school was significantly higher in girls (Odds Ratio [OR]=1.52, 95% Confidence Intervals [CI]=1.42-1.63), metropolitan city (OR=1.32, 95% CI=1.11-1.56), city (OR=1.29, 95% CI=1.08-1.54), higher grade, higher academic performance, lower economic status, not handwashing at home (OR=14.36, 95% CI=13.37-15.42), and without annual personal hygiene education (OR=1.41, 95% CI=1.33-1.49). Reasons for not washing hands at school among adolescents who do not wash their hands before meals at school included ‘it is bothersome (52.3%)’, ‘there is no soap or hand sanitizer (13.8%)’, and ‘I do not feel the need (9.5%)’.
Conclusions
Improving handwashing before meals at school among adolescents requires raising awareness of the importance of handwashing before meals and establishing a suitable environment and handwashing-encouraging culture.
5.Impact of Conventional and Electronic Cigarette Use on the Adolescents’ Experience of Periodontal Disease Symptoms
Journal of Dental Hygiene Science 2021;21(3):133-139
Background:
Smoking in adolescence leads to an intensified addiction to nicotine when physical and mental growth has not yet been completed. With the advent of e-cigarettes, the rate of e-cigarette use among Korean adolescents has been steadily increasing. To date, studies on e-cigarettes and oral health, especially on the relationship between smoking styles and oral health in adolescents, are limited. Therefore, this study aimed to identify the risk factors for oral health problems caused by the repeated use of conventional cigarettes and e-cigarettes.
Methods:
This explanatory research study compared the adolescents’ experiences of periodontal disease symptoms according to smoking type through a secondary analysis of the original data from the 15th Adolescent Health Behavior Survey (2019).Cross-analysis was performed to compare the smoking patterns according to the adolescents’ general characteristics. Finally, a binary logistic regression analysis was performed to determine how smoking characteristics affect the adolescents’ experience of periodontal disease symptoms.
Results:
In terms of patients’ general characteristics, significant differences were observed in sex, school level, grades, household economic status, type of residence, and father’s education level between adolescents who smoked conventional cigarettes alone and those who smoked both conventional cigarettes and e-cigarettes (p<0.05). After checking the factors affecting the smoking pattern and the experience of periodontal disease symptoms in adolescents, it was found that the duplicate smoking group was more likely to experience periodontal disease symptoms (odds ratio, 1.20) than the group that smoked conventional cigarettes alone (p<0.05).
Conclusion
Duplicate smokers experienced more symptoms of periodontal disease than those who smoked cigarettes alone. Based on the findings of this study, smoking cessation counseling according to the smoking type and differentiated education for oral health promotion should be provided.
6.Analysis of the Effects of a Health Policy Capacity Development Education Program as a Public-Private Partnership Model in Official Development Assistance for Health Policy Administrators
Sang Hun LEE ; Kyung Min PARK ; Eunsuk LEE
Korean Journal of Occupational Health Nursing 2020;29(2):140-149
Purpose:
This study analyzed the effects of a health policy capacity development education program as a publicprivate partnership (PPP) model in official development assistance (ODA) for health policy administrators.
Methods:
Between October 2015 and September 2017, 41 participants from underdeveloped countries completed the three-week education program at K university, following the official selection process of the Korea International Cooperation Agency (KOICA) and each country’s embassy.
Results:
The effects of the health policy capacity development education program differed significantly according to participants' age (p=.043), country region (p=.045), and academic or professional degree (p=.007). Academic or professional degree significantly predicted the effects of the program (β=.41, p=.007), explaining 21.7% of the variance in the regression model.
Conclusion
The current selection process for ODA program participants considers recommendations from each country’s embassy to determine eligible candidates. The hosting institution’s opinions or suggestions regarding participants’ professional expertise or work experience, country region, or demographic characteristics should also be considered in the participant selection process.
7.Impact of Social Support on Subjective Oral Health Status among Elderly People
Eunsuk AHN ; Jin-Ha LEE ; Sun-Mi KIM
Journal of Dental Hygiene Science 2020;20(2):67-73
Background:
Owing to the increase in the aging population, the health problems of the elderly have become important social problems. Social support has a positive effect on improving the quality of life and prolonging the life of elderly people. It is one of the major factors that affects the oral health status of elderly people. The purpose of this study was to examine the relationship between oral health status and social support in elderly people using representative data.
Methods:
In this study, data from a community health survey in 2015 involving 63,929 elderly people aged over 65 years were analyzed. T-test and ANOVA analyses were performed to compare the general characteristics of and perception about social support. Additionally, a linear regression analysis was performed to confirm the relationship between perceptions about social support and subjective oral health status.
Results:
We found that sex, age, household income, education level, the presence of a spouse, existence of an unmet dental need, and regular oral check-up had a significant effect on subjective oral health status (p<0.05). In addition, when controlled for all factors, social support has a significant impact on subjective oral health status.
Conclusion
The findings indicate that social support is associated with the subjective oral health status of Korean elderly. This suggests that community-level or government investment is required to improve the oral health of the elderly. In particular, policy interventions such as the establishment of facilities that promote social networks, especially facilities based on friendship networks, are needed.
8.Factors Affecting Dental Utilization and Dental Expenses in the Economically Active Population: Based on the 2010~2014 Korea Health Panel Data
Journal of Dental Hygiene Science 2019;19(1):23-30
BACKGROUND: The health of the economically active population contributes to increased corporate productivity by reducing the productivity loss caused by disease and increasing job efficiency, which in turn is a national benefit. Since the economically active population is a concept encompassing workers and a source of economic development for a country, that population's health should be treated with importance not only from a personal standpoint but also at a national level. METHODS: In this study, data of 11,007 adults aged 20 years and older who participate in economic activities were analyzed in the five-year Korea Health Panel Study from 2010 to 2014 including the number of dental visits and dental medical expenses. RESULTS: Factors related to “gender,” “education level,” “age,” “duty category,” “income level,” “employment type,” “national health insurance,” and “chronic disease status” of the economically active population are affected in relation to the number of visits and dental medical expenses. The number of dental visits increased with higher education levels (p<0.001), and the number of visits to the dentist increased with older age (p <0.001). Dental medical expenses were 91,806 Korean won (KRW) more for “white-collar workers” than for “blue-collar workers” (p<0.03), and 127,674 KRW more for “regular workers” than for “atypical workers” (p<0.02). CONCLUSION: When it is necessary to improve policies to enhance the efficiency of the distribution of health and medical resources in the overall balance of the dental health sector, we should try to identify various factors of oral health disorder due to income inequality among the classes according to the country's employment type in order to find ways to reduce the health gap among the social classes.
Adult
;
Dentists
;
Economic Development
;
Education
;
Efficiency
;
Employment
;
Humans
;
Korea
;
Oral Health
;
Social Class
;
Socioeconomic Factors
9.Cytotoxicity of Various Calcium Silicate-based Materials with Stem Cells from Deciduous Teeth
Jihye YUN ; Yong Ouk YOU ; Eunsuk AHN ; Jun LEE ; So Youn AN
Journal of Korean Academy of Pediatric Dentistry 2019;46(1):85-92
The purpose of this study was to compare and evaluate the cytotoxicity of 3 calcium silicate-based materials (CSMs) on stem cells from human exfoliated deciduous teeth (SHEDs). The powder of Retro MTA® (RM), EZ-Seal™ (EZ) and ENDOCEM Zr® (EN) was eluted with SHED culture media and then filtered. The SHEDs were cultured in the presence of the various concentrations of the eluate. To investigate the effect of the 3 CSMs on SHED proliferation, the MTS (3-(4,5-dimethylthiazol-2-yl)-5-(3-carboxymethoxyphenyl)-2-(4-sulfophenyl)-2H-tetrazolium) assay was performed. Flow cytometry analysis was also performed to identify any changes in the cellular phenotype. The absorbance values of the SHEDs cultured in the eluate of samples at a 10% concentration showed the following relation: RM > EN > EZ (p = 0.0439). However, the SHEDs maintained their mesenchymal phenotype regardless of product exposure. Although the 3 CSMs did not alter the SHED stem cell markers, EZ may be a less cytocompatible than RM and EN.
Calcium
;
Culture Media
;
Flow Cytometry
;
Humans
;
Phenotype
;
Stem Cells
;
Tooth, Deciduous
10.The Relationship between Hormone Replacement Therapy and Periodontal Disease in Postmenopausal Women
Journal of Dental Hygiene Science 2018;18(1):9-17
The purpose of this study was to investigate the relationship between hormone replacement therapy (HRT) and periodontal disease in postmenopausal women using data from the 4th and 5th Korea National Health and Nutrition Examination Survey. A total of 5,482 postmenopausal women aged 45~75 years were included as study subjects in the final analysis. The HRT group comprised 1,035 postmenopausal women who had received HRT for at least one month, and the non-HRT group comprised 4,447 postmenopausal women who did not receive HRT. The chi-square test was used to confirm the bivariate relationship between the variables. Multinomial logistic regression analysis was used to adjust for covariance (age, education, family income, body mass index, age of menopause, alcohol, smoking, dental visit < 1 per year, use of oral care products, and frequency of tooth brushing per day). After adjusting for all covariates, HRT was found to be associated with periodontal disease. In particular, the relationship between HRT and periodontal disease was more evident in older women and women younger than 45 years of menopausal age. The relationship between HRT and periodontal disease was stronger in women who brushed their teeth less than 3 times per day, women without regular oral examination, and women who did not use oral hygiene products. The results of this study confirmed the importance of actively considering hormone therapy when determining policy recommendations for postmenopausal women. Especially, health programs such as HRT, regular dental examination, and oral care are needed for older women who have undergone premature menopause.
Body Mass Index
;
Diagnosis, Oral
;
Education
;
Female
;
Hormone Replacement Therapy
;
Humans
;
Korea
;
Logistic Models
;
Menopause
;
Menopause, Premature
;
Nutrition Surveys
;
Oral Hygiene
;
Periodontal Diseases
;
Smoke
;
Smoking
;
Tooth

Result Analysis
Print
Save
E-mail