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.Colon cancer: the 2023 Korean clinical practice guidelines for diagnosis and treatment
Hyo Seon RYU ; Hyun Jung KIM ; Woong Bae JI ; Byung Chang KIM ; Ji Hun KIM ; Sung Kyung MOON ; Sung Il KANG ; Han Deok KWAK ; Eun Sun KIM ; Chang Hyun KIM ; Tae Hyung KIM ; Gyoung Tae NOH ; Byung-Soo PARK ; Hyeung-Min PARK ; Jeong Mo BAE ; Jung Hoon BAE ; Ni Eun SEO ; Chang Hoon SONG ; Mi Sun AHN ; Jae Seon EO ; Young Chul YOON ; Joon-Kee YOON ; Kyung Ha LEE ; Kyung Hee LEE ; Kil-Yong LEE ; Myung Su LEE ; Sung Hak LEE ; Jong Min LEE ; Ji Eun LEE ; Han Hee LEE ; Myong Hoon IHN ; Je-Ho JANG ; Sun Kyung JEON ; Kum Ju CHAE ; Jin-Ho CHOI ; Dae Hee PYO ; Gi Won HA ; Kyung Su HAN ; Young Ki HONG ; Chang Won HONG ; Jung-Myun KWAK ;
Annals of Coloproctology 2024;40(2):89-113
Colorectal cancer is the third most common cancer in Korea and the third leading cause of death from cancer. Treatment outcomes for colon cancer are steadily improving due to national health screening programs with advances in diagnostic methods, surgical techniques, and therapeutic agents.. The Korea Colon Cancer Multidisciplinary (KCCM) Committee intends to provide professionals who treat colon cancer with the most up-to-date, evidence-based practice guidelines to improve outcomes and help them make decisions that reflect their patients’ values and preferences. These guidelines have been established by consensus reached by the KCCM Guideline Committee based on a systematic literature review and evidence synthesis and by considering the national health insurance system in real clinical practice settings. Each recommendation is presented with a recommendation strength and level of evidence based on the consensus of the committee.
5.Reference Standard of Median Nerve Conduction Study in Korea
Jae Hyun LEE ; Eunkyung KIM ; Hyung-Seok SHIM ; Min-Gu KANG ; Keewon KIM ; Sang Yoon LEE ; Goo Joo LEE ; Shi-Uk LEE ; Jae-Young LIM ; Sun Gun CHUNG ; Byung-Mo OH
Annals of Rehabilitation Medicine 2024;48(4):259-270
Objective:
To establish the reference standard of the median nerve conduction study (NCS) in Korea.
Methods:
A total of 648 median motor and 602 median sensory NCSs from 349 Korean healthy volunteers were tested and analyzed prospectively. Equipment calibration, assessment of intraand inter-rater reliability, and the NCSs per se were conducted according to a predetermined protocol. A reference standard was established from uncertainty components for the following parameters: the onset and peak latencies; the baseline-to-peak and peak-to-peak amplitudes; the area and duration of the negative wave; and the nerve conduction velocity. The effects of sex, age and stimulation intensity were analyzed.
Results:
Each measured value of 648 median motor and 602 median sensory nerves were obtained and presented with both mean and expanded uncertainties, as well as mean and standard deviations. The cut-off values with expanded uncertainty were determined for different age and sex groups. After adjusting for anthropometric covariates, all parameters except duration were affected by age, and sex appeared to influence both duration and area. While stimulation intensity significantly affected some parameters including latencies, the effect sizes were negligible.
Conclusion
We propose the median NCS reference standard using the largest Korean dataset ever available. The use of the traceable and reliable reference standard is anticipated to promote more accurate and dependable diagnosis and appropriate management of median neuropathies in Korea.
6.Investigation of Working Conditions and Health Status in Platform Workers in the Republic of Korea
Hyoungseob YOO ; Munyoung YANG ; Ji-Hun SONG ; Jin-Ha YOON ; Wanhyung LEE ; Jinhee JANG ; Minjoo YOON ; Mo-Yeol KANG
Safety and Health at Work 2024;15(1):17-23
Background:
The present study aimed to analyze several aspects of the working conditions and health status of platform workers in the Republic of Korea, such as ergonomic and emotional hazards. We also compared the health status of the platform workers with that of the general population.
Methods:
A total of 1,000 platform workers participated in this survey from August 7 to August 17, 2022. The participants included 400 designated drivers, 400 food-delivery drivers, and 200 housekeeping managers. A face-to-face survey with a structured questionnaire was conducted by researchers who had received specific instructions. The focus of the survey extended to the work environment, encompassing factors such as workplace violence, as well as physical, chemical, and ergonomic hazards. Health-related data for the previous year were also collected, covering a range of issues such as hearing problems, skin problems, musculoskeletal symptoms, headaches, injuries, mental health issues, and digestive problems. Subsequently, we compared the health symptom data of the responders with those of the general population in the Republic of Korea.
Results:
Platform workers, including designated drivers, food-delivery drivers, and housekeeping managers, existed in the blind spot of social insurance, facing frequent exposure to physical and chemical hazards, ergonomic risk factors, and direct or indirect violence. The prevalence of health problems, including musculoskeletal symptoms, general fatigue, and depressive symptoms, in each occupational group was statistically higher than that in the general population after standardization for age and gender.
Conclusion
The results revealed unfavorable working environment and inferior occupational health of platform workers compared with those of the general population.
7.Psychometric Properties of the Korean Version of Functioning Assessment Short Test in Bipolar Disorder
Hangoeunbi KANG ; Bo-Hyun YOON ; Won-Myong BAHK ; Young Sup WOO ; Won KIM ; Jonghun LEE ; InKi SOHN ; Sung-Yong PARK ; Duk-In JON ; Myung Hun JUNG ; Moon-Doo KIM ; Young-Eun JUNG ; Hyung-Mo SUNG ; Young-Min PARK ; Jung Goo LEE ; Sang-Yeol LEE ; Seung-Ho JANG ; Eun-Sung LIM ; In Hee SHIM ; Kwanghun LEE ; Sae-Heon JANG
Clinical Psychopharmacology and Neuroscience 2023;21(1):188-196
Objective:
The Functioning Assessment Short Test (FAST) is a relatively specific test for bipolar disorders designed to assess the main functioning problems experienced by patients. This brief instrument includes 24 items assessing impairment or disability in 6 domains of functioning: autonomy, occupational functioning, cognitive functioning, financial issues, interpersonal relationships, and leisure time. It has already been translated into standardized versions in several languages. The aim of this study is to measure the validity and reliability of the Korean version of FAST (K-FAST).
Methods:
A total of 209 bipolar disorder patients were recruited from 14 centers in Korea. K-FAST, Young Mania Rating Scale (YMRS), Bipolar Depression Rating Scale (BDRS), Global Assessment of Functioning (GAF) and the World Health Organization Quality of Life Assessment Instrument Brief Form (WHOQOL-BREF) were administered, and psychometric analysis of the K-FAST was conducted.
Results:
The internal consistency (Cronbach’s alpha) of the K-FAST was 0.95. Test-retest reliability analysis showed a strong correlation between the two measures assessed at a 1-week interval (ICC = 0.97; p < 0.001). The K-FAST exhibited significant correlations with GAF (r = −0.771), WHOQOL-BREF (r = −0.326), YMRS (r = 0.509) and BDRS (r = 0.598). A strong negative correlation with GAF pointed to a reasonable degree of concurrent validity. Although the exploratory factor analysis showed four factors, the confirmatory factor analysis of questionnaires had a good fit for a six factors model (CFI = 0.925; TLI = 0.912; RMSEA = 0.078).
Conclusion
The K-FAST has good psychometric properties, good internal consistency, and can be applicable and acceptable to the Korean context.
8.Subclassification of advanced-stage hepatocellular carcinoma with macrovascular invasion: combined transarterial chemoembolization and radiotherapy as an alternative first-line treatment
Sujin JIN ; Won-Mook CHOI ; Ju Hyun SHIM ; Danbi LEE ; Kang Mo KIM ; Young-Suk LIM ; Han Chu LEE ; Jinhong JUNG ; Sang Min YOON ; Jonggi CHOI
Journal of Liver Cancer 2023;23(1):177-188
Background:
/Aim: The Barcelona Clinic Liver Cancer (BCLC) guidelines recommend systemic therapy as the only first-line treatment for patients with BCLC stage C hepatocellular carcinoma (HCC) despite its heterogeneity of disease extent. We aimed to identify patients who might benefit from combined transarterial chemoembolization (TACE) and radiation therapy (RT) by subclassifying BCLC stage C.
Methods:
A total of 1,419 treatment-naïve BCLC stage C patients with macrovascular invasion (MVI) who were treated with combined TACE and RT (n=1,115) or systemic treatment (n=304) were analyzed. The primary outcome was overall survival (OS). Factors associated with OS were identified and assigned points by the Cox model. The patients were subclassified into three groups based on these points.
Results:
The mean age was 55.4 years, and 87.8% were male. The median OS was 8.3 months. Multivariate analysis revealed a significant association of Child-Pugh B, infiltrative-type tumor or tumor size ≥10 cm, main or bilateral portal vein invasion, and extrahepatic metastasis with poor OS. The sub-classification was categorized into low (point ≤1), intermediate (point=2), and high (point ≥3) risks based on the sum of points (range, 0–4). The OS in the low, intermediate, and high-risk groups was 22.6, 8.2, and 3.8 months, respectively. In the low and intermediate-risk groups, patients treated with combined TACE and RT exhibited significantly longer OS (24.2 and 9.5 months, respectively) than those who received systemic treatment (6.4 and 5.1 months, respectively; P<0.0001).
Conclusions
Combined TACE and RT may be considered as a first-line treatment option for HCC patients with MVI when classified into low- and intermediate-risk groups.
9.Imbalance in the spinal serotonergic pathway induces aggravation of mechanical allodynia and microglial activation in carrageenan inflammation
Junxiu JIN ; Dong Ho KANG ; Jin JEON ; Hyung Gon LEE ; Woong Mo KIM ; Myung Ha YOON ; Jeong Il CHOI
The Korean Journal of Pain 2023;36(1):51-59
Background:
This study investigated the effect of an excess and a deficit of spinal 5-hydroxytryptamine (5-HT) on the mechanical allodynia and neuroglia activation in a rodent pain model of carrageenan inflammation.
Methods:
Male Sprague–Dawley rats were implanted with an intrathecal (i.t.) catheter to administer the drug. To induce an excess or deficit of 5-HT in the spinal cord, animals were given either three i.t. 5-HT injections at 24-hour intervals or a single i.t. injection of 5,7-dihydroxytryptamine (5,7-DHT) before carrageenan inflammation.Mechanical allodynia was measured using the von Frey test for 0–4 hours (early phase) and 24–28 hours (late phase) after carrageenan injection. The changes in the activation of microglia and astrocyte were examined using immunofluorescence of the dorsal horn of the lumbar spinal cord.
Results:
Both an excess and a deficit of spinal 5-HT had no or a minimal effect on the intensity of mechanical allodynia during the early phase but prevented the attenuation of mechanical allodynia during the late phase, which was observed in animals not treated with i.t. 5-HT or 5,7-DHT. Animals with an excess or deficit of 5-HT showed stronger activation of microglia, but not astrocyte, during the early and late phases, than did normal animals.
Conclusions
Imbalance in the descending 5-HT pathway in the spinal cord could aggravate the mechanical allodynia and enhance the activation of microglia, suggesting that the spinal 5-HT pathway plays an essential role in maintaining the nociceptive processing in balance between facilitation and inhibition in inflammatory pain caused by carrageenan inflammation.
10.Long-term outcomes of carotid artery stenting in patients with carotid artery stenosis: A single-center 14-year retrospective analysis
Beom Mo KANG ; Seok Mann YOON ; Jae Sang OH ; Hyuk Jin OH ; Jae Min AHN ; Gi Yong YUN
Journal of Cerebrovascular and Endovascular Neurosurgery 2023;25(2):160-174
Objective:
Carotid artery stenting (CAS) is currently widely used for the treatment of carotid artery stenosis. The objective of this study was to analyze the outcomes of CAS performed in a single institution.
Methods:
We retrospectively analyzed 313 CAS cases from January 2007 to December 2020, including 206 (66%) symptomatic and 107 (34%) asymptomatic cases. Procedure-related morbidity and mortality were assessed. Rates of periprocedural (≤30 days after CAS) and postprocedural ipsilateral strokes (>30 days after CAS) were also assessed. Logistic regression analysis was used to identify risk factors for the periprocedural complication, in-stent restenosis (ISR), and ipsilateral stroke.
Results:
The success rate of CAS was 98%. Among 313 cases, 1 patient died due to hyperperfusion-related intracerebral hemorrhage (ICH). The CAS-related mortality rate was 0.31%. The overall incidence of periprocedural complications is 5.1%. A risk factor for periprocedural complication was a symptomatic carotid artery stenosis (7.3% vs. 0.9%, p=0.016). Twenty cases of ISR occurred during 63.7±42.1 months of follow-up. The overall incidence of ISR was 10.2% (20/196). A risk factors for ISR were diabetes mellitus (17.6% vs. 5.7%, p=0.008) and patients who used Open-cell stents (19.6% vs. 6.9%, p=0.010). The overall incidence of ipsilateral stroke is 5.6%. A risk factors for ipsilateral stroke was ISR (95% CI, p=0.002).
Conclusions
CAS is a safe and effective procedure for carotid artery stenosis. Although the incidence of complications is low, fatal complication such as hyperperfusion- related ICH can occur. To prevent hyperperfusion-related ICH, several methods such as strict blood pressure (BP) control, intentional less widening of stenotic segment should be used. To prevent ISR or stroke occurrence, special attention should be paid to patients who have ISR or ipsilateral stroke risk factors.

Result Analysis
Print
Save
E-mail