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.Tumor Microenvironment Modulation by Neoadjuvant Erlotinib Therapy and Its Clinical Impact on Operable EGFR-Mutant Non–Small Cell Lung Cancer
Beung-Chul AHN ; Charny PARK ; Moon Soo KIM ; Jong Mog LEE ; Jin Ho CHOI ; Hyae Young KIM ; Geon Kook LEE ; Namhee YU ; Youngjoo LEE ; Ji-Youn HAN
Cancer Research and Treatment 2024;56(1):70-80
Purpose:
Epidermal growth factor receptor (EGFR) tyrosine kinase inhibitors have greatly improved survival in EGFR-mutant (EGFRm) non–small cell lung cancer (NSCLC); however, their effects on the tumor microenvironment (TME) are unknown. We assessed the changes induced by neoadjuvant erlotinib therapy (NE) in the TME of operable EGFRm NSCLC.
Materials and Methods:
This was a single-arm phase II trial for neoadjuvant/adjuvant erlotinib therapy in patients with stage II/IIIA EGFRm NSCLC (EGFR exon 19 deletion or L858R mutations). Patients received up to 2 cycles of NE (150 mg/day) for 4 weeks, followed by surgery and adjuvant erlotinib or vinorelbine plus cisplatin therapy depending on observed NE response. TME changes were assessed based on gene expression analysis and mutation profiling.
Results:
A total of 26 patients were enrolled; the median age was 61, 69% were female, 88% were stage IIIA, and 62% had L858R mutation. Among 25 patients who received NE, the objective response rate was 72% (95% confidence interval [CI], 52.4 to 85.7). The median disease-free and overall survival (OS) were 17.9 (95% CI, 10.5 to 25.4) and 84.7 months (95% CI, 49.7 to 119.8), respectively. Gene set enrichment analysis in resected tissues revealed upregulation of interleukin, complement, cytokine, transforming growth factor β, and hedgehog pathways. Patients with upregulated pathogen defense, interleukins, and T-cell function pathways at baseline exhibited partial response to NE and longer OS. Patients with upregulated cell cycle pathways at baseline exhibited stable/progressive disease after NE and shorter OS.
Conclusion
NE modulated the TME in EGFRm NSCLC. Upregulation of immune-related pathways was associated with better outcomes.
5.Erratum: A Comparison Between the Performances of Verbal and Nonverbal Fluency Tests in Discriminating Between Mild Cognitive Impairments and Alzheimer’s Disease Patients and Their Brain Morphological Correlates
Seyul KWAK ; Seong A SHIN ; Hyunwoong KO ; Hairin KIM ; Dae Jong OH ; Jung Hae YOUN ; Jun-Young LEE ; Yu Kyeong KIM
Dementia and Neurocognitive Disorders 2023;22(2):85-85
6.Multidisciplinary Shared Decision Making for Fertility Preservation in Young Women With Breast Cancer
Soo Yeon BAEK ; Hong-Kyu KIM ; Seho PARK ; Jong Han YU ; Min Hyuk LEE ; Hyun Jo YOUN ; Hyun-Ah KIM ; Jai Hong HAN ; Jung Eun CHOI ; Jung Ryeol LEE ; Kyung-Hun LEE ; Seockhoon CHUNG ; Hee Dong CHAE ; Seonok KIM ; Soyoung YOO ; Sang Keun HAHM ; Hee Jeong KIM
Journal of Breast Cancer 2023;26(6):582-592
Purpose:
Fertility preservation (FP) is an important issue for young survivors of breast cancer. Although international guidelines recommend pre-treatment fertility counseling for women with breast cancer, there is no standardized protocol or referral system for FP in South Korea. There are also barriers to discussing FP that make patient-centered decision making difficult. This study aimed to develop a shared decision making program for FP and compare the rates of FP procedures between the usual care and shared decision making groups. We hypothesized that multidisciplinary shared decision making for FP would increase the rate of FP procedures and patient satisfaction.
Methods
The multidisciplinary shared decision making for FP in young women with breast cancer (MYBC) is a multicenter, clustered, stepped-wedge, randomized trial. A total of 1100patients with breast cancer, aged 19–40 years, from nine hospitals in South Korea, will be enrolled. They will be randomized at the institutional level and assigned to usual care and shared decision making groups. Four institutions, each of which can recruit more than 200 patients, will each become a cluster, whereas five institutions, each of which can recruit more than 50 patients, will become one cluster, for a total of five clusters. The shared decision making groups will receive multidisciplinary programs for FP developed by the investigator. The primary outcome is the rate of FP procedures; secondary outcomes include fertility results, satisfaction, and quality of life. Outcomes will be measured at enrollment, treatment initiation, and the 1-, 3-, and 5-year follow-ups after starting breast cancer treatment.Discussion: A multidisciplinary shared decision making program for FP is expected to increase fertility rates and satisfaction among young patients with breast cancer. This study will provide the evidence to implement a multidisciplinary system for patients with breast cancer.
7.Effects of Gait Training Using a Shoulder-Back Orthosis on Balance and Gait in Patients with Stroke
Han-Byul YOUN ; Jong-Kyung LEE ; Yu-Min KO ; Ji-Won PARK
Journal of Korean Physical Therapy 2023;35(6):200-205
Purpose:
The purpose of this study is to find out how gait training with shoulder-back assistive device affects dynamic and static balance, gait of patients with stroke and to help improve body alignment, balance, and gait ability in stroke patients.
Methods:
Measurements were taken of the 20 subjects before intervention without shoulder-back assistive device, after intervention with device, and follow up after an hour compared. Berg balance scale used to evaluate dynamic balance; wii balance board was used to measure static balance; and gait ability were measured by timed up and go test and 10-meter walk test. To analyze the results, a one-way repeated measures analysis of variance was implemented to compare the measurements.
Results:
The results showed that, after wearing the shoulder-back assistive device, the subjects’ dynamic balance statistically significantly improved; no statistically significant difference was observed in static balance, although their balance ability was enhanced; and their increase in gait ability was statistically significant.
Conclusion
This study proved that gait training combined with a shoulder-back assistive device positively impacted dynamic and static balance, gait of patients with stroke.
8.Korean Practice Guidelines for Gastric Cancer 2022: An Evidence-based, Multidisciplinary Approach
Tae-Han KIM ; In-Ho KIM ; Seung Joo KANG ; Miyoung CHOI ; Baek-Hui KIM ; Bang Wool EOM ; Bum Jun KIM ; Byung-Hoon MIN ; Chang In CHOI ; Cheol Min SHIN ; Chung Hyun TAE ; Chung sik GONG ; Dong Jin KIM ; Arthur Eung-Hyuck CHO ; Eun Jeong GONG ; Geum Jong SONG ; Hyeon-Su IM ; Hye Seong AHN ; Hyun LIM ; Hyung-Don KIM ; Jae-Joon KIM ; Jeong Il YU ; Jeong Won LEE ; Ji Yeon PARK ; Jwa Hoon KIM ; Kyoung Doo SONG ; Minkyu JUNG ; Mi Ran JUNG ; Sang-Yong SON ; Shin-Hoo PARK ; Soo Jin KIM ; Sung Hak LEE ; Tae-Yong KIM ; Woo Kyun BAE ; Woong Sub KOOM ; Yeseob JEE ; Yoo Min KIM ; Yoonjin KWAK ; Young Suk PARK ; Hye Sook HAN ; Su Youn NAM ; Seong-Ho KONG ;
Journal of Gastric Cancer 2023;23(1):3-106
Gastric cancer is one of the most common cancers in Korea and the world. Since 2004, this is the 4th gastric cancer guideline published in Korea which is the revised version of previous evidence-based approach in 2018. Current guideline is a collaborative work of the interdisciplinary working group including experts in the field of gastric surgery, gastroenterology, endoscopy, medical oncology, abdominal radiology, pathology, nuclear medicine, radiation oncology and guideline development methodology. Total of 33 key questions were updated or proposed after a collaborative review by the working group and 40 statements were developed according to the systematic review using the MEDLINE, Embase, Cochrane Library and KoreaMed database. The level of evidence and the grading of recommendations were categorized according to the Grading of Recommendations, Assessment, Development and Evaluation proposition. Evidence level, benefit, harm, and clinical applicability was considered as the significant factors for recommendation. The working group reviewed recommendations and discussed for consensus. In the earlier part, general consideration discusses screening, diagnosis and staging of endoscopy, pathology, radiology, and nuclear medicine. Flowchart is depicted with statements which is supported by meta-analysis and references. Since clinical trial and systematic review was not suitable for postoperative oncologic and nutritional follow-up, working group agreed to conduct a nationwide survey investigating the clinical practice of all tertiary or general hospitals in Korea. The purpose of this survey was to provide baseline information on follow up. Herein we present a multidisciplinary-evidence based gastric cancer guideline.
9.Erratum: Korean Practice Guidelines for Gastric Cancer 2022: An Evidencebased, Multidisciplinary Approach
Tae-Han KIM ; In-Ho KIM ; Seung Joo KANG ; Miyoung CHOI ; Baek-Hui KIM ; Bang Wool EOM ; Bum Jun KIM ; Byung-Hoon MIN ; Chang In CHOI ; Cheol Min SHIN ; Chung Hyun TAE ; Chung sik GONG ; Dong Jin KIM ; Arthur Eung-Hyuck CHO ; Eun Jeong GONG ; Geum Jong SONG ; Hyeon-Su IM ; Hye Seong AHN ; Hyun LIM ; Hyung-Don KIM ; Jae-Joon KIM ; Jeong Il YU ; Jeong Won LEE ; Ji Yeon PARK ; Jwa Hoon KIM ; Kyoung Doo SONG ; Minkyu JUNG ; Mi Ran JUNG ; Sang-Yong SON ; Shin-Hoo PARK ; Soo Jin KIM ; Sung Hak LEE ; Tae-Yong KIM ; Woo Kyun BAE ; Woong Sub KOOM ; Yeseob JEE ; Yoo Min KIM ; Yoonjin KWAK ; Young Suk PARK ; Hye Sook HAN ; Su Youn NAM ; Seong-Ho KONG
Journal of Gastric Cancer 2023;23(2):365-373
10.Current Status of Q Fever and the Challenge of Outbreak Preparedness in Korea: One Health Approach to Zoonoses
Yun Sang CHO ; Ji-Hyuk PARK ; Jong Wan KIM ; Jin-Ju LEE ; So Youn YOUN ; Hyeon Seop BYEON ; Hye Won JEONG ; Dong-Min KIM ; Shi Nae YU ; Jang Won YOON ; Dongmi KWAK ; Han Sang YOO ; Ji-Yeon LEE ; Jeong-Ran KWON ; Kyung-Won HWANG ; Jung Yeon HEO
Journal of Korean Medical Science 2023;38(24):e197-
Human Q fever, a zoonosis caused by Coxiella burnetii, presents with diverse clinical manifestations ranging from mild self-limited febrile illnesses to life-threatening complications such as endocarditis or vascular infection. Although acute Q fever is a benign illness with a low mortality rate, a large-scale outbreak of Q fever in the Netherlands led to concerns about the possibility of blood transfusion-related transmission or obstetric complications in pregnant women. Furthermore, a small minority (< 5%) of patients with asymptomatic or symptomatic infection progress to chronic Q fever. Chronic Q fever is fatal in 5–50% of patients if left untreated. In South Korea, Q fever in humans was designated as a notifiable infectious disease in 2006, and the number of Q fever cases has increased sharply since 2015. Nonetheless, it is still considered a neglected and under-recognized infectious disease. In this review, recent trends of human and animal Q fever in South Korea, and public health concerns regarding Q fever outbreaks are reviewed, and we consider how a One Health approach could be applied as a preventive measure to prepare for zoonotic Q fever outbreaks.

Result Analysis
Print
Save
E-mail