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.Compression Neuropathy Caused by Pelvic Lymphocele after Laparoscopic Surgical Staging
Dong Jin CHAE ; Jong Bum PARK ; Mi Jin HONG ; Jungyun KIM ; Cho E. SIM ; Seung-Eun KIM ; Yung Jin LEE
Journal of Electrodiagnosis and Neuromuscular Diseases 2024;26(2):29-34
Lymphocele is a complication of pelvic surgery that infrequently leads to compressive neuropathy. We present a case of compressive obturator neuropathy resulting from lymphocele development after pelvic surgery. Electrodiagnostic studies revealed severe axonal disruption in the left obturator nerve, which is associated with poor functional recovery. This case underscores the role of electrodiagnostic testing in the diagnosis and rehabilitation of patients experiencing lower limb weakness following gynecological pelvic surgery.
3.Diagnosis of ADSSL1 Mutation-Induced Myopathy Through Electrophysiology and Genetic Tools
Dong Jin CHAE ; Yung Jin LEE ; Mi Jin HONG ; Cho E. SIM ; Seung-Eun KIM ; Jong Bum PARK
Journal of Electrodiagnosis and Neuromuscular Diseases 2024;26(2):35-39
Mutations in the adenylosuccinate synthase 1 (ADSSL1) gene, resulting in adenylosuccinate synthase deficiency, are a rare genetic anomaly characterized by muscular weakness, elevated serum creatine kinase levels, and pathological muscle findings. However, these clinical symptoms are similar to those observed in many other myopathies, increasing the risk of misdiagnosis. In an era of rapidly expanding genetic knowledge, the authors sought to verify the diagnostic utility of electromyography for genetic disorders. Through combined electrophysiological and genetic studies, a patient initially thought to have Becker’s muscular dystrophy was conclusively diagnosed with ADSSL1 mutagenic myopathy. This case underscores the importance of re-evaluating diseases that do not follow the typical clinical progression of traditional myopathies, especially in light of recent diagnostic advancements.
4.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.
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.A 10-Gene Signature to Predict the Prognosis of Early-Stage Triple-Negative Breast Cancer
Chang Min KIM ; Kyong Hwa PARK ; Yun Suk YU ; Ju Won KIM ; Jin Young PARK ; Kyunghee PARK ; Jong-Han YU ; Jeong Eon LEE ; Sung Hoon SIM ; Bo Kyoung SEO ; Jin Kyeoung KIM ; Eun Sook LEE ; Yeon Hee PARK ; Sun-Young KONG
Cancer Research and Treatment 2024;56(4):1113-1125
Purpose:
Triple-negative breast cancer (TNBC) is a particularly challenging subtype of breast cancer, with a poorer prognosis compared to other subtypes. Unfortunately, unlike luminal-type cancers, there is no validated biomarker to predict the prognosis of patients with early-stage TNBC. Accurate biomarkers are needed to establish effective therapeutic strategies.
Materials and Methods:
In this study, we analyzed gene expression profiles of tumor samples from 184 TNBC patients (training cohort, n=76; validation cohort, n=108) using RNA sequencing.
Results:
By combining weighted gene expression, we identified a 10-gene signature (DGKH, GADD45B, KLF7, LYST, NR6A1, PYCARD, ROBO1, SLC22A20P, SLC24A3, and SLC45A4) that stratified patients by risk score with high sensitivity (92.31%), specificity (92.06%), and accuracy (92.11%) for invasive disease-free survival. The 10-gene signature was validated in a separate institution cohort and supported by meta-analysis for biological relevance to well-known driving pathways in TNBC. Furthermore, the 10-gene signature was the only independent factor for invasive disease-free survival in multivariate analysis when compared to other potential biomarkers of TNBC molecular subtypes and T-cell receptor β diversity. 10-gene signature also further categorized patients classified as molecular subtypes according to risk scores.
Conclusion
Our novel findings may help address the prognostic challenges in TNBC and the 10-gene signature could serve as a novel biomarker for risk-based patient care.
7.Importation and Transmission of SARS-CoV-2 B.1.1.529 (Omicron) Variant of Concern in Korea, November 2021
Ji Joo LEE ; Young June CHOE ; Hyeongseop JEONG ; Moonsu KIM ; Seonggon KIM ; Hanna YOO ; Kunhee PARK ; Chanhee KIM ; Sojin CHOI ; JiWoo SIM ; Yoojin PARK ; In Sil HUH ; Gasil HONG ; Mi Young KIM ; Jin Su SONG ; Jihee LEE ; Eun-Jin KIM ; Jee Eun RHEE ; Il-Hwan KIM ; Jin GWACK ; Jungyeon KIM ; Jin-Hwan JEON ; Wook-Gyo LEE ; Suyeon JEONG ; Jusim KIM ; Byungsik BAE ; Ja Eun KIM ; Hyeonsoo KIM ; Hye Young LEE ; Sang-Eun LEE ; Jong Mu KIM ; Hanul PARK ; Mi YU ; Jihyun CHOI ; Jia KIM ; Hyeryeon LEE ; Eun-Jung JANG ; Dosang LIM ; Sangwon LEE ; Young-Joon PARK
Journal of Korean Medical Science 2021;36(50):e346-
In November 2021, 14 international travel-related severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) B.1.1.529 (omicron) variant of concern (VOC) patients were detected in South Korea. Epidemiologic investigation revealed community transmission of the omicron VOC. A total of 80 SARS-CoV-2 omicron VOC-positive patients were identified until December 10, 2021 and 66 of them reported no relation to the international travel.There may be more transmissions with this VOC in Korea than reported.
8.Exploratory evaluation of the role of cardiac troponin on the clinical outcome of patients visiting emergency department with or without chronic kidney disease
Minseok SONG ; Eun-Jin KANG ; Taerim KIM ; Jong Eun PARK ; Gun Tak LEE ; Hee YOON ; Sung Yeon HWANG ; Won Chul CHA ; Tae Gun SHIN ; Min Seob SIM ; Ik Joon JO ; Jin-Ho CHOI
Journal of the Korean Society of Emergency Medicine 2021;32(6):548-560
Objective:
Elevated levels of cardiac troponin in chronic kidney disease (CKD) patients admitted to the emergency department (ED) is not well understood and is often ignored. This study aimed to investigate the impact of cardiac troponin I (TnI) levels on the clinical outcome of patients visiting the ED with or without CKD.
Methods:
In this retrospective single-center cohort study, we enrolled patients visiting the ED without a diagnosis of coronary artery disease (CAD). Elevated cardiac TnI was defined as being ≥99th percentile of the normal population (Siemens ADVIA Centaur TnI-Ultra≥0.040 ng/mL). The clinical outcomes of patients with CKD stage≤2 and CKD stage ≥3 were compared. The primary endpoint was the 180-day all-cause death, including cardiovascular and non-cardiovascular deaths.
Results:
Among a total of 30,472 patients (median age, 61 years; male sex, 54.3%), elevated TnI was found in 4,377 patients (14.4%). There were 3,634 deaths (11.9%) including 584 cardiovascular (1.9%) and 3,050 non-cardiovascular deaths (10.0%). The risk of all-cause death increased in patients with elevated TnI in both CKD stage≤2 (hazard ratio [HR], 2.1; 95% confidence interval [CI], 1.9-2.3) and CKD stage≥3 (HR, 1.5; 95% CI, 1.4-1.7), and so did the risks of cardiovascular and non-cardiovascular death (HR, 1.2-4.7) (P<0.05, all). The association of elevated TnI with death risk was consistent in multivariate analyses and in most clinical subgroup analyses.
Conclusion
Elevated TnI was associated with higher 180-day mortality irrespective of renal function among patients visiting the ED without documented CAD. CKD patients visiting the ED with elevated TnI may warrant additional evaluation or careful follow-up even without the presence of CAD.
9.Relationship of Bone Mineral Density and Knee Osteoarthritis (Kellgren-Lawrence Grade):Fifth Korea National Health and Nutrition Examination Survey
Eun-Seok CHOI ; Hyun Dae SHIN ; Jae Ang SIM ; Young Gon NA ; Won-Jun CHOI ; Dae-Do SHIN ; Jong-Min BAIK
Clinics in Orthopedic Surgery 2021;13(1):60-66
Background:
Osteoarthritis (OA) and osteoporosis (OP) are the 2 most common bone disorders associated with aging. We can simply assume that older patients have a higher incidence of OA and OP with more severity. Although several papers have conducted studies on the relationship between OA and OP, none of them has demonstrated a conclusive link. In this study, we used radiological knee OA and bone mineral density (BMD; T-score of the total hip and lumbar spine) to analyze the incidence of OA and OP in a large population. We aimed to determine the relationship between OA and OP and investigate the associated risk factors.
Methods:
This cross-sectional study used data extracted from the 2010–2012 Korea National Health and Nutrition Examination Survey. We evaluated a total of 4,250 participants aged ≥ 50 years who underwent knee radiography and dual-energy X-ray absorptiometry and their laboratory results. The relationship between radiological knee OA and BMD was assessed. The generalized linear model was used to evaluate the relationship between BMD and Kellgren-Lawrence (KL) grade.
Results:
The higher KL grade was associated with older age, higher body mass index (BMI), female sex, and lower hemoglobin level (p < 0.001). No significant association was found between OA and the following variables: white blood cell, platelet, total cholesterol, vitamin D, alkaline phosphatase, parathyroid hormone, hypertension, diabetes, asthma, dyslipidemia, smoking status, alcohol consumption, and regular exercise (p > 0.05). After adjusting for confounding factors (age, BMI, diabetes, hypertension, smoking, and alcohol consumption), the average T-scores of total hip and lumbar spine were the highest in the mild OA group with KL grade 2 (–0.22 ± 1.08 and –0.89 ± 1.46, respectively,p < 0.001). The average T-scores of the total hip and lumbar spine significantly decreased as OA progressed from moderate (KL grade 3; –0.49 ± 1.05 and –1.33 ± 1.38, respectively, p < 0.001) to severe (KL grade 4; –0.73 ± 1.13 and –1.74 ± 1.75, respectively, p < 0.001). T-scores of the moderate-to-severe OA group were significantly lower than those of the non-OA group (KL grades 0 and 1, p < 0.001).
Conclusions
Compared with the non-OA group, BMD (T-scores of the total hip and lumbar spine) was higher in the mild OA group and lower in the moderate-to-severe OA group.
10.Effectiveness of Mass Drug Administration on Neglected Tropical Diseases in Schoolchildren in Zanzibar, Tanzania
Ju Yeong KIM ; Seobo SIM ; Eun Joo CHUNG ; Han-Jong RIM ; Jong-Yil CHAI ; Duk-Young MIN ; Keeseon S. EOM ; Khalfan A. MOHAMMED ; Iddi S. KHAMIS ; Tai-Soon YONG
The Korean Journal of Parasitology 2020;58(2):109-119
Soil-transmitted helminths and Schistosoma haematobium affect more than 3 billion people globally and mainly occur in sub-Saharan Africa. The present study assessed the overall infection status of a 1716-student cohort of school-children in Zanzibar and applied mass drug administration (MDA) to the cohort from 2007 to 2009. Schools in Pemba, Zanzibar, had a much higher prevalence of soil-transmitted helminth infections than those in Unguja, and the Chaani, Ghana, and Machui schools of Unguja exhibited high S. haematobium infection rates. The MDA program only partially controlled parasite infections, owing to high rates of re-infection. The infection rate of S. haematobium across all 10 schools, for example, was only reduced by 1.8%, and even this change not significant, even though the S. haematobiuminfection rates of the Chaani and Mzambarauni schools were significantly reduced from 64.4 and 23.4%, respectively, at the first screening, to 7.3 and 2.3% at the last screening. The overall infection rate of Ascaris lumbricoides was reduced from 36.0% at the first screening to 22.6% at the last screening. However, the infection rates for both Trichuris trichiuraand hookworm were generally unaffected by MDA. In the future, parasite control programs should involve strategically designed MDA schedules and holistic intervention (e.g., sanitation improvement, hygiene behavior changes, and control of intermediated hosts).

Result Analysis
Print
Save
E-mail