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.Familial male-limited precocious puberty due to an activating mutation of the LHCGR: a case report and literature review
Jihyun HA ; Yunha CHOI, ; Mo Kyung JUNG ; Eun-Gyong YOO ; Han-Wook YOO
Annals of Pediatric Endocrinology & Metabolism 2024;29(1):60-66
Familial male-limited precocious puberty (FMPP) is a rare form of gonadotropin-independent precocious puberty that is caused by an activating mutation of the LHCGR gene. Herein, we report a case of FMPP with a mutation of the LHCGR gene in a Korean boy with familial history of precocious puberty through 3 generations. A 16-month-old boy presented with signs of precocious puberty, including pubic hair, acne, and increased growth velocity. The patient's grandfather and father had a history of precocious puberty and profound short stature. On physical examination, the patient had prepubertal testes with pubic hair development appropriate for Tanner stage II. The stretched penile length was 7 cm (>2 standard deviation score), and observed bone age was that of a 4-year-old boy. Laboratory findings showed high serum testosterone (5.74 ng/mL [appropriate for Tanner IV–V]; normal range, <0.05 ng/mL) with suppressed luteinizing hormone (<0.07 mIU/mL) and normal serum level of follicular stimulating hormone (0.56 mIU/mL; normal range, 0.38–1.11 mIU/mL). Genetic testing revealed a pathogenic variant of LHCGR (c.1730 C>T (p.Thr577Ileu)), confirming FMPP. Bicalutamide and anastrozole were administered, and pubertal progression was sufficiently suppressed without any specific side effects. To our knowledge, this is the first case of genetically confirmed FMPP in Korea.
6.The Profile of Early Sedation Depth and Clinical Outcomes of Mechanically Ventilated Patients in Korea
Dong-gon HYUN ; Jee Hwan AHN ; Ha-Yeong GIL ; Chung Mo NAM ; Choa YUN ; Jae-Myeong LEE ; Jae Hun KIM ; Dong-Hyun LEE ; Ki Hoon KIM ; Dong Jung KIM ; Sang-Min LEE ; Ho-Geol RYU ; Suk-Kyung HONG ; Jae-Bum KIM ; Eun Young CHOI ; JongHyun BAEK ; Jeoungmin KIM ; Eun Jin KIM ; Tae Yun PARK ; Je Hyeong KIM ; Sunghoon PARK ; Chi-Min PARK ; Won Jai JUNG ; Nak-Jun CHOI ; Hang-Jea JANG ; Su Hwan LEE ; Young Seok LEE ; Gee Young SUH ; Woo-Sung CHOI ; Keu Sung LEE ; Hyung Won KIM ; Young-Gi MIN ; Seok Jeong LEE ; Chae-Man LIM
Journal of Korean Medical Science 2023;38(19):e141-
Background:
Current international guidelines recommend against deep sedation as it is associated with worse outcomes in the intensive care unit (ICU). However, in Korea the prevalence of deep sedation and its impact on patients in the ICU are not well known.
Methods:
From April 2020 to July 2021, a multicenter, prospective, longitudinal, noninterventional cohort study was performed in 20 Korean ICUs. Sedation depth extent was divided into light and deep using a mean Richmond Agitation–Sedation Scale value within the first 48 hours. Propensity score matching was used to balance covariables; the outcomes were compared between the two groups.
Results:
Overall, 631 patients (418 [66.2%] and 213 [33.8%] in the deep and light sedation groups, respectively) were included. Mortality rates were 14.1% and 8.4% in the deep and light sedation groups (P = 0.039), respectively. Kaplan-Meier estimates showed that time to extubation (P < 0.001), ICU length of stay (P = 0.005), and death P = 0.041) differed between the groups. After adjusting for confounders, early deep sedation was only associated with delayed time to extubation (hazard ratio [HR], 0.66; 95% confidence inter val [CI], 0.55– 0.80; P < 0.001). In the matched cohort, deep sedation remained significantly associated with delayed time to extubation (HR, 0.68; 95% 0.56–0.83; P < 0.001) but was not associated with ICU length of stay (HR, 0.94; 95% CI, 0.79–1.13; P = 0.500) and in-hospital mortality (HR, 1.19; 95% CI, 0.65–2.17; P = 0.582).
Conclusion
In many Korean ICUs, early deep sedation was highly prevalent in mechanically ventilated patients and was associated with delayed extubation, but not prolonged ICU stay or in-hospital death.
7.Establishing molecular pathology curriculum for pathology trainees and continued medical education: a collaborative work from the Molecular Pathology Study Group of the Korean Society of Pathologists
Jiwon KOH ; Ha Young PARK ; Jeong Mo BAE ; Jun KANG ; Uiju CHO ; Seung Eun LEE ; Haeyoun KANG ; Min Eui HONG ; Jae Kyung WON ; Youn-La CHOI ; Wan-Seop KIM ; Ahwon LEE ;
Journal of Pathology and Translational Medicine 2023;57(5):265-272
Background:
The importance of molecular pathology tests has increased during the last decade, and there is a great need for efficient training of molecular pathology for pathology trainees and as continued medical education.
Methods:
The Molecular Pathology Study Group of the Korean Society of Pathologists appointed a task force composed of experienced molecular pathologists to develop a refined educational curriculum of molecular pathology. A 3-day online educational session was held based on the newly established structure of learning objectives; the audience were asked to score their understanding of 22 selected learning objectives before and after the session to assess the effect of structured education.
Results:
The structured objectives and goals of molecular pathology was established and posted as a web-based interface which can serve as a knowledge bank of molecular pathology. A total of 201 pathologists participated in the educational session. For all 22 learning objectives, the scores of self-reported understanding increased after educational session by 9.9 points on average (range, 6.6 to 17.0). The most effectively improved items were objectives from next-generation sequencing (NGS) section: ‘NGS library preparation and quality control’ (score increased from 51.8 to 68.8), ‘NGS interpretation of variants and reference database’ (score increased from 54.1 to 68.0), and ‘whole genome, whole exome, and targeted gene sequencing’ (score increased from 58.2 to 71.2). Qualitative responses regarding the adequacy of refined educational curriculum were collected, where favorable comments dominated.
Conclusions
Approach toward the education of molecular pathology was refined, which would greatly benefit the future trainees.
8.A 14-year-old male with rhabdomyolysis associated with psychogenic polydipsia and hyponatremia
Youn Shin JUNG ; Yunha CHOI ; Jihyun HA ; Eun-Gyong YOO ; So Hyun PAEK ; Mo Kyung JUNG
Pediatric Emergency Medicine Journal 2023;10(4):160-164
Rhabdomyolysis associated with psychogenic polydipsia and hyponatremia is a rare condition that can cause substantial morbidity and mortality. We report a 14-year-old boy with psychogenic polydipsia who experienced recurrent hyponatremia and subsequent rhabdomyolysis. Treatment involved intravenous fluids and restriction of oral water intake. This case emphasizes the importance of early recognition and management of this condition. The possibility of rhabdomyolysis should be considered in patients with hyponatremia who have myalgia.
9.Changes in proteinuria and the associated risks of ischemic heart disease, acute myocardial infarction,and angina pectoris in Korean population
Sung Keun PARK ; Ju Young JUNG ; Min-Ho KIM ; Chang-Mo OH ; Eunhee HA ; Eun Hye YANG ; Hyo Choon LEE ; Soonsu SHIN ; Woo Yeon HWANG ; Sangho LEE ; So Youn SHIN ; Jae-Hong RYOO
Epidemiology and Health 2023;45(1):e2023088-
OBJECTIVES:
Proteinuria is widely used to predict cardiovascular risk. However, there is insufficient evidence to predict how changes in proteinuria may affect the incidence of cardiovascular disease.
METHODS:
The study included 265,236 Korean adults who underwent health checkups in 2003-2004 and 2007-2008. They were categorized into 4 groups based on changes in proteinuria (negative: negative → negative; resolved: proteinuria ≥1+ → negative; incident: negative → proteinuria ≥1+; persistent: proteinuria ≥1+ → proteinuria ≥1+). We conducted 6 years of follow-up to identify the risks of developing ischemic heart disease (IHD), acute myocardial infarction (AMI), and angina pectoris according to changes in proteinuria. A multivariate Cox proportional-hazards model was used to calculate adjusted hazard ratios (HRs) and 95% confidence intervals (CIs) for incident IHD, AMI, and angina pectoris.
RESULTS:
The IHD risk (expressed as HR [95% CI]) was the highest for persistent proteinuria, followed in descending order by incident and resolved proteinuria, compared with negative proteinuria (negative: reference, resolved: 1.211 [95% CI, 1.104 to 1.329], incident: 1.288 [95% CI, 1.184 to 1.400], and persistent: 1.578 [95% CI, 1.324 to 1.881]). The same pattern was associated with AMI (negative: reference, resolved: 1.401 [95% CI, 1.048 to 1.872], incident: 1.606 [95% CI, 1.268 to 2.035], and persistent: 2.069 [95% CI, 1.281 to 3.342]) and angina pectoris (negative: reference, resolved: 1.184 [95% CI, 1.065 to 1.316], incident: 1.275 [95% CI, 1.160 to 1.401], and persistent: 1.554 [95% CI, 1.272 to 1.899]).
CONCLUSIONS
Experiencing proteinuria increased the risks of IHD, AMI, and angina pectoris even after proteinuria resolved.
10.The association of pancreatic cancer incidence with smoking status and smoking amount in Korean men
Do Jin NAM ; Chang-Mo OH ; Eunhee HA ; Min-Ho KIM ; Eun Hye YANG ; Hyo Choon LEE ; Soon Su SHIN ; Woo Yeon HWANG ; Ann Hee YOU ; Jae-Hong RYOO
Epidemiology and Health 2022;44(1):e2022040-
OBJECTIVES:
Our study examined the dose-response relationship between smoking amounts (pack-years) and the risk of developing pancreatic cancer in Korean men.
METHODS:
Of 125,743 participants who underwent medical health checkups in 2009, 121,408 were included in the final analysis and observed for the development of pancreatic cancer. We evaluated the associations between smoking amounts and incident pancreatic cancer in 4 groups classified by pack-year amounts. Cox proportional hazards models were used to estimate the adjusted hazard ratios (HRs) and 95% confidence intervals (CIs) of incident pancreatic cancer by comparing groups 2 (<20 pack-year smokers), 3 (20-≤40 pack-year smokers), and 4 (>40 pack-year smokers) with group 1 (never smokers).
RESULTS:
During 527,974.5 person-years of follow-up, 245 incident cases of pancreatic cancer developed between 2009 and 2013. The multivariate-adjusted HRs (95% CIs) for incident pancreatic cancer in groups 2, 3, and 4 were 1.05 (0.76 to 1.45), 1.28 (0.91 to 1.80), and 1.57 (1.00 to 2.46), respectively (p for trend=0.025). The HR (95% CI) of former smokers showed a dose-response relationship in the unadjusted model, but did not show a statistically significant association in the multivariate-adjusted model. The HR (95% CI) of current smokers showed a dose-response relationship in both the unadjusted (p for trend=0.020) and multivariate-adjusted models (p for trend=0.050).
CONCLUSIONS
The risk of developing pancreatic cancer was higher in current smokers status than in former smokers among Korean men, indicating that smoking cessation may have a protective effect.

Result Analysis
Print
Save
E-mail