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.Piperacillin-Tazobactam versus Cefotaxime as Empiric Treatment for Febrile Urinary Tract Infection in Hospitalized Children
Kyoung Hee HAN ; Min-su OH ; Jungmin AHN ; Juyeon LEE ; Youn Woo KIM ; Young Mi YOON ; Yoon-Joo KIM ; Hyun Sik KANG ; Ki-Soo KANG ; Larry A. GREENBAUM ; Jae Hong CHOI
Infection and Chemotherapy 2024;56(2):266-275
Background:
According to international pediatric urinary tract infection (UTI) guidelines, selecting ampicillin/ sulbactam or amoxicillin/clavulanate is recommended as the first-line treatment for pediatric UTI. In Korea, elevated resistance to ampicillin and ampicillin/sulbactam has resulted in the widespread use of third-generation cephalosporins for treating pediatric UTIs. This study aims to compare the efficacy of piperacillin-tazobactam (TZP) and cefotaxime (CTX) as first-line treatments in hospitalized children with UTIs.
Materials and Methods:
The study, conducted at Jeju National University Hospital, retrospectively analyzed medical records of children hospitalized for febrile UTIs between 2014 and 2017. UTI diagnosis included unexplained fever, abnormal urinalysis, and the presence of significant uropathogens. Treatment responses, recurrence, and antimicrobial susceptibility were assessed.
Results:
Out of 323 patients, 220 met the inclusion criteria. Demographics and clinical characteristics were similar between TZP and CTX groups. For children aged ≥3 months, no significant differences were found in treatment responses and recurrence. Extended-spectrum beta-lactamase (ESBL)-positive strains were associated with recurrence in those <3 months.
Conclusion
In Korea, escalating resistance to empirical antibiotics has led to the adoption of broad-spectrum empirical treatment. TZP emerged as a viable alternative to CTX for hospitalized children aged ≥3 months with UTIs.Consideration of ESBL-positive strains and individualized approaches for those <3 months are crucial.
5.Erratum: Correction of Figure in the Article “Viral, Immunologic, and Laboratory Parameters in Patients With and Without Post-Acute Sequelae of SARS-CoV-2 Infection (PASC)”
Sang Hyun RA ; Euijin CHANG ; Ji-Soo KWON ; Ji Yeun KIM ; JuYeon SON ; Woori KIM ; Choi Young JANG ; Hyeon Mu JANG ; Seongman BAE ; Jiwon JUNG ; Min Jae KIM ; Yong Pil CHONG ; Sang-Oh LEE ; Sang-Ho CHOI ; Yang Soo KIM ; Keun Hwa LEE ; Sung-Han KIM
Journal of Korean Medical Science 2024;39(38):e304-
6.Viral, Immunologic, and Laboratory Parameters in Patients With and Without Post-Acute Sequelae of SARS-CoV-2 Infection (PASC)
Sang Hyun RA ; Euijin CHANG ; Ji-Soo KWON ; Ji Yeun KIM ; JuYeon SON ; Woori KIM ; Choi Young JANG ; Hyeon Mu JANG ; Seongman BAE ; Jiwon JUNG ; Min Jae KIM ; Yong Pil CHONG ; Sang-Oh LEE ; Sang-Ho CHOI ; Yang Soo KIM ; Keun Hwa LEE ; Sung-Han KIM
Journal of Korean Medical Science 2024;39(35):e237-
Background:
The pathophysiological mechanisms underlying the post-acute sequelae of severe acute respiratory syndrome coronavirus 2 infection (PASC) are not well understood.Our study aimed to investigate various aspects of theses mechanisms, including viral persistence, immunological responses, and laboratory parameters in patients with and without PASC.
Methods:
We prospectively enrolled adults aged ≥ 18 years diagnosed with coronavirus disease 2019 (COVID-19) between August 2022 and July 2023. Blood samples were collected at three time-points: within one month of diagnosis (acute phase) and at 1 month, and 3 months post-diagnosis. Following a recent well-designed definition of PASC, PASC patients were defined as those with a questionnaire-based PASC score ≥ 12 persisting for at least 4 weeks after the initial COVID-19 diagnosis.
Results:
Of 57 eligible COVID-19 patients, 29 (51%) had PASC, and 28 (49%) did not. The PASC group had significantly higher nucleocapsid protein (NP) antigenemia 3 months after COVID-19 diagnosis (P = 0.022). Furthermore, several cytokines, including IL-2, IL-17A, VEGF, RANTES, sCD40L, IP-10, I-TAC, and granzyme A, were markedly elevated in the PASC group 1 and/or 3 month(s) after COVID-19 diagnosis. In contrast, the median values of several serological markers, including thyroid markers, autoimmune indicators, and stress-related hormones, were within the normal range.
Conclusion
Levels of NP antigen and of various cytokines involved in immune responses become significantly elevated over time after COVID-19 diagnosis in PASC patients compared to non-PASC patients. This suggests that PASC is associated with prolonged immune dysregulation resulting from heightened antigenic stimulation.
7.Effect of local anesthetic volume (20 vs. 40 ml) on the analgesic efficacy of costoclavicular block in arthroscopic shoulder surgery: a randomized controlled trial
Yumin JO ; Chahyun OH ; Woo-Yong LEE ; Hyung-Jin CHUNG ; Hanmi PARK ; Juyeon PARK ; Jieun LEE ; Yoon-Hee KIM ; Youngkwon KO ; Woosuk CHUNG ; Boohwi HONG
Korean Journal of Anesthesiology 2024;77(1):85-94
Background:
Among the various diaphragm-sparing alternatives to interscalene block, costoclavicular block (CCB) demonstrated a low hemidiaphragmatic paresis (HDP) occurrence but an inconsistent analgesic effect in arthroscopic shoulder surgery. We hypothesized that a larger volume of local anesthetic for CCB could provide sufficient analgesia by achieving sufficient supraclavicular spreading.
Methods:
Sixty patients scheduled for arthroscopic rotator cuff repair were randomly assigned to receive CCB using one of two volumes of local anesthetic (CCB20, 0.75% ropivacaine 20 ml; CCB40, 0.375% ropivacaine 40 ml). The primary outcome was the rate of complete analgesia (0 on the numeric rating scale of pain) at 1 h postoperatively. The secondary outcomes included a sonographic assessment of local anesthetic spread, diaphragmatic function, pulmonary function, postoperative opioid use, and other pain-related experiences within 24 h postoperatively.
Results:
The rates of complete analgesia were not significantly different (23.3% [7/30] and 33.3% [10/30] in the CCB20 and CCB40 groups, respectively; risk difference 10%, 95% CI [–13, 32], P = 0.567). There were no significant differences in other pain-related outcomes. Among the clinical factors considered, the only factor significantly associated with postoperative pain was the sonographic observation of supraclavicular spreading. There were no significant differences in the incidence of HDP and the change in pulmonary function between the two groups.
Conclusions
Using 40 ml of local anesthetic does not guarantee supraclavicular spread during CCB. Moreover, it does not result in a higher rate of complete analgesia compared to using 20 ml of local anesthetic in arthroscopic shoulder surgery.
8.Comparison of the Association Between Presenteeism and Absenteeism among Replacement Workers and Paid Workers: Cross-sectional Studies and Machine Learning Techniques
Heejoo PARK ; Juho SIM ; Juyeon OH ; Jongmin LEE ; Chorom LEE ; Yangwook KIM ; Byungyoon YUN ; Jin-ha YOON
Safety and Health at Work 2024;15(2):151-157
Background:
Replacement drivers represent a significant portion of platform labor in the Republic of Korea, often facing night shifts and the demands of emotional labor. Research on replacement drivers is limited due to their widespread nature. This study examined the levels of presenteeism and absenteeism among replacement drivers in comparison to those of paid male workers in the Republic of Korea.
Methods:
This study collected data for replacement drivers and used data from the 6th Korean Working Conditions Survey for paid male workers over the age of 20 years. Propensity score matching was performed to balance the differences between paid workers and replacement drivers. Multivariable logistic regression was used to estimate the adjusted odds ratio (OR) and 95% confidence intervals for presenteeism and absenteeism by replacement drivers. Stratified analysis was conducted for age groups, educational levels, income levels, and working hours. The analysis was adjusted for variables including age, education, income, working hours, working days per week, and working duration.
Results:
Among the 1,417 participants, the prevalence of presenteeism and absenteeism among replacement drivers was 53.6% (n = 210) and 51.3% (n = 201), respectively. The association of presenteeism and absenteeism (adjusted OR [95% CI] = 8.42 [6.36−11.16] and 20.80 [95% CI = 14.60−29.62], respectively) with replacement drivers being significant, with a prominent association among the young age group, high educational, and medium income levels.
Conclusion
The results demonstrated that replacement drivers were more significantly associated with presenteeism and absenteeism than paid workers. Further studies are necessary to establish a strategy to decrease the risk factors among replacement drivers.
9.Association Between Organizational Downsizing and Depressive Symptoms Among Korean Workers: A Cross-sectional Analysis
Youngsun PARK ; Juyeon OH ; Heejoo PARK ; Jian LEE ; Byungyoon YUN ; Jin-Ha YOON
Safety and Health at Work 2024;15(3):352-359
Background:
Organizational downsizing may be significantly linked to depressive symptoms, yet research on this impact in Asian contexts is limited. This study investigates the association between downsizing during the COVID-19 pandemic and depressive symptoms across diverse employment statuses.
Methods:
This study used the data from 6th Korean Working Conditions Survey. Depressive symptoms were measured using WHO-5 well-being index with a cut-off of 50. Downsizing was defined as decrease in the number of employees during last three years. Multivariable logistic regression adjusted for socio-demographic and occupational factors was used to estimate the adjusted odds ratio (OR) and 95% confidence interval (CI) for depressive symptoms associated with downsizing, including subgroup analyses.
Results:
Among 26,247 Korean workers (mean age: 43.4, men: 47.5%), the prevalence of depressive symptoms was 29.5% (n = 7,751), and the proportion of downsizing was 15.2% (n = 3,978). The prevalence of depressive symptoms was significantly higher among the downsizing group (36.7%, n = 1,460) than among the no-downsizing group (28.3%, n = 6,291). The result of logistic regression revealed a significant association between downsizing and depressive symptoms (adjusted OR [95% CI]: 1.39 [1.29–1.50]), particularly pronounced among high socioeconomic status workers.
Conclusion
This study underscores the significant association between depressive symptoms and organizational downsizing, especially high vulnerability of socioeconomically advantaged and stable workers. These findings highlight the necessity for targeted mental health support and further longitudinal research to clarify the relationship between employment changes and mental health within the Korean workforce.
10.Did the socioeconomic inequalities in avoidable and unavoidable mortality worsen during the first year of the COVID-19 pandemic in Korea?
Rora OH ; Myoung-Hee KIM ; Juyeon LEE ; Rangkyoung HA ; Jungwook KIM
Epidemiology and Health 2023;45(1):e2023072-
OBJECTIVES:
This study examined changes in socioeconomic inequalities in mortality in Korea before and after the outbreak of coronavirus disease 2019 (COVID-19).
METHODS:
From 2017 to 2020, age-standardized mortality rates were calculated for all-cause deaths, avoidable deaths (preventable deaths, treatable deaths), and unavoidable deaths using National Health Insurance claims data and Statistics Korea’s cause of death data. In addition, the slope index of inequality (SII) and the relative index of inequality (RII) by six income levels (Medical Aid beneficiary group and quintile of health insurance premiums) were computed to analyze the magnitude and change of mortality inequalities.
RESULTS:
All-cause and avoidable mortality rates decreased steadily between 2017 and 2020, whereas unavoidable mortality remained relatively stable. In the case of mortality inequalities, the disparity in all-cause mortality between income classes was exacerbated in 2020 compared to 2019, with the SII increasing from 185.44 to 189.22 and the RII increasing from 3.99 to 4.29. In particular, the preventable and unavoidable mortality rates showed an apparent increase in inequality, as both the SII (preventable: 91.31 to 92.01, unavoidable: 69.99 to 75.38) and RII (preventable: 3.42 to 3.66, unavoidable: 5.02 to 5.89) increased.
CONCLUSIONS
In the first year of the COVID-19 pandemic, mortality inequality continued to increase, although there was no sign of exacerbation. It is necessary to continuously evaluate mortality inequalities, particularly for preventable and unavoidable deaths.

Result Analysis
Print
Save
E-mail