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.Effectiveness of Malaria Antibody Test for Screening Blood Donors
Jungwon KANG ; Jaehyun KIM ; Jaesook LEE ; Deuk Yeong KO ; Hwang Min KIM ; Kyoung Young CHOI
Korean Journal of Blood Transfusion 2023;34(1):21-25
		                        		
		                        			
		                        			 The Republic of Korea has been using malaria antibody assays to screen blood donors and reduce the risk of transfusion-transmitted malaria (TTM). This study examined the effectiveness of the current malaria antibody test for screening blood donors and calculated the positive predictive value (PPV) with the real-time polymerase chain reaction (RT-PCR) as the reference. The reactive rate and PPV of the malaria antibody screening assay during particular period from 2020 to 2021 were 0.82% (248/30,309) and 0.40% (1/248), respectively. The low PPV of current malaria antibody screening in blood donors suggests that the effectiveness of this test is limited in terms of balancing blood safety and supply in low-prevalence situations. 
		                        		
		                        		
		                        		
		                        	
5.Inflammatory Markers and Brain Volume in Patients with Post-traumatic Stress Disorder
Chaeyeon YANG ; Kang-Min CHOI ; Jungwon HAN ; Hyang Sook KIM ; Sang-Shin PARK ; Seung-Hwan LEE
Clinical Psychopharmacology and Neuroscience 2023;21(2):359-369
		                        		
		                        			 Objective:
		                        			Posttraumatic stress disorder (PTSD) is characterized by increased inflammatory processing and altered brain volume. In this study, we investigated the relationship between inflammatory markers and brain volume in patients with PTSD. 
		                        		
		                        			Methods:
		                        			Forty-five patients with PTSD, and 70 healthy controls (HC) completed clinical assessments and self-reported psychopathology scales. Factors associated with inflammatory responses including brain-derived neurotrophic factor and four inflammatory biomarkers (C-reactive protein, cortisol, Interleukin-6, and homocysteine) and T1-magnetic resonance imaging of the brain were measured. 
		                        		
		                        			Results:
		                        			In the PTSD group, cortisol level was significantly lower (t = 2.438, p = 0.046) than that of the HC. Cortisol level was significantly negatively correlated with the left thalamus proper (r = −0.369, p = 0.035), right thalamus proper (r = −0.394, p = 0.014), right frontal pole (r = −0.348, p = 0.039), left occipital pole (r = −0.338, p = 0.044), and right superior occipital gyrus (r = −0.397, p = 0.008) in patients with PTSD. However, these significant correlations were not observed in HC. 
		                        		
		                        			Conclusion
		                        			Our results indicate that increased cortisol level, even though its average level was lower than that of HC, is associated with smaller volumes of the thalamus, right frontal pole, left occipital pole, and right superior occipital gyrus in patients with PTSD. Cortisol, a major stress hormone, might be a reliable biomarker to brain volumes and pathophysiological pathways in patients with PTSD. 
		                        		
		                        		
		                        		
		                        	
6.Analysis of HCV Genotype with Low Titer of HCV RNA Using the Methods of Concentration
JungWon KANG ; Jae-won KANG ; Dae Ho KO ; Miae YOUN ; So-Yong KWON
Korean Journal of Blood Transfusion 2021;32(1):43-48
		                        		
		                        			
		                        			Analysis of HCV genotypes can help identify infection routes and the development of treatment methods. However, in some samples with a low titer of HCV RNA, it is difficult to analyze their genotypes. In our previous study about HCV genotyping, we could not identify 12 cases among the 175 HCV NAT reactive samples due to their low titer. In this study, we adopted three different kinds of virus concentration methods to identify the genotypes of the 12 unidentified cases and compared their efficacy. The three virus concentration methods were automatic nucleic acid extraction, polyethyleneimine-magnetic bead-based extraction, and sucrose cushion ultracentrifugation. After virus concentration using every three methods, we analyzed HCV RNA genotypes using the concentrated sample of the best efficacy. Among the 12 cases, six were identified as 1b, four as mixed types, and two were unidentified. Here we could validate that the sample concentration method is useful to identify the HCV genotypes, especially in samples with low HCV RNA titers. Furthermore, considering the convenience, high efficacy, and time-saving, automatic nucleic acid extraction is considered the most useful concentration method for samples with titer lower than 50 IU/mL.
		                        		
		                        		
		                        		
		                        	
7.Analysis of Malaria Nucleic Acid Amplification Test Under the Temporary Permission in Malaria Blood Donation Restricted Area
JungWon KANG ; JaeSook LEE ; Dae Ho KO ; Jae-won KANG ; Yu Soek JUNG ; Miae YOUN
Korean Journal of Blood Transfusion 2021;32(2):123-128
		                        		
		                        			
		                        			There were 10 cases of transfusion-transmitted P. vivax malaria from 1990 to 2021. The Korean Centers for Disease Control and Prevention (KCDC) designated the areas showing a high frequency of malaria as a malaria-endemic area and has restricted whole blood donation from these areas. While the number of malaria infections has declined in recent years, the blood inventory has declined sharply due to the COVID-19 pandemic. Accordingly, the Ministry of Health and Welfare temporarily approved the donation of whole blood from malaria-endemic areas to secure the supply of blood products. In the present study, an anti-malaria screening and nucleic acid amplification test (NAT) was performed on samples collected from the malaria-endemic areas from May 20 to June 30, 2020. A total of 14,741 samples were collected and tested. NAT was performed for 1096 runs to test all the collected samples. The 117 (0.79%) samples showed initial reactive results due to the contamination of abnormal PCR results. Negative results were obtained for the samples showing initial reactive results using a duplicated re-test. From the NAT tests, no sample showed a true positive result. The results of the malaria antibody screening test were reactive in 10 out of the 14,741 samples. The malaria antibody screening needs to be reviewed through further study because of its insufficient sensitivity and specificity. According to this study, excluding the 10 reactive malaria antibodies, additional blood components could be secured from 14,731 blood donors for a stable blood supply.
		                        		
		                        		
		                        		
		                        	
8.Analysis of HCV Genotype with Low Titer of HCV RNA Using the Methods of Concentration
JungWon KANG ; Jae-won KANG ; Dae Ho KO ; Miae YOUN ; So-Yong KWON
Korean Journal of Blood Transfusion 2021;32(1):43-48
		                        		
		                        			
		                        			Analysis of HCV genotypes can help identify infection routes and the development of treatment methods. However, in some samples with a low titer of HCV RNA, it is difficult to analyze their genotypes. In our previous study about HCV genotyping, we could not identify 12 cases among the 175 HCV NAT reactive samples due to their low titer. In this study, we adopted three different kinds of virus concentration methods to identify the genotypes of the 12 unidentified cases and compared their efficacy. The three virus concentration methods were automatic nucleic acid extraction, polyethyleneimine-magnetic bead-based extraction, and sucrose cushion ultracentrifugation. After virus concentration using every three methods, we analyzed HCV RNA genotypes using the concentrated sample of the best efficacy. Among the 12 cases, six were identified as 1b, four as mixed types, and two were unidentified. Here we could validate that the sample concentration method is useful to identify the HCV genotypes, especially in samples with low HCV RNA titers. Furthermore, considering the convenience, high efficacy, and time-saving, automatic nucleic acid extraction is considered the most useful concentration method for samples with titer lower than 50 IU/mL.
		                        		
		                        		
		                        		
		                        	
9.Analysis of Malaria Nucleic Acid Amplification Test Under the Temporary Permission in Malaria Blood Donation Restricted Area
JungWon KANG ; JaeSook LEE ; Dae Ho KO ; Jae-won KANG ; Yu Soek JUNG ; Miae YOUN
Korean Journal of Blood Transfusion 2021;32(2):123-128
		                        		
		                        			
		                        			There were 10 cases of transfusion-transmitted P. vivax malaria from 1990 to 2021. The Korean Centers for Disease Control and Prevention (KCDC) designated the areas showing a high frequency of malaria as a malaria-endemic area and has restricted whole blood donation from these areas. While the number of malaria infections has declined in recent years, the blood inventory has declined sharply due to the COVID-19 pandemic. Accordingly, the Ministry of Health and Welfare temporarily approved the donation of whole blood from malaria-endemic areas to secure the supply of blood products. In the present study, an anti-malaria screening and nucleic acid amplification test (NAT) was performed on samples collected from the malaria-endemic areas from May 20 to June 30, 2020. A total of 14,741 samples were collected and tested. NAT was performed for 1096 runs to test all the collected samples. The 117 (0.79%) samples showed initial reactive results due to the contamination of abnormal PCR results. Negative results were obtained for the samples showing initial reactive results using a duplicated re-test. From the NAT tests, no sample showed a true positive result. The results of the malaria antibody screening test were reactive in 10 out of the 14,741 samples. The malaria antibody screening needs to be reviewed through further study because of its insufficient sensitivity and specificity. According to this study, excluding the 10 reactive malaria antibodies, additional blood components could be secured from 14,731 blood donors for a stable blood supply.
		                        		
		                        		
		                        		
		                        	
10.Risk Assessment of the Occurrence of Blood Products Infected with Dengue Virus Based on Travelers to the Areas of Dengue Outbreak
Dae Ho KO ; Jae-won KANG ; Jungwon KANG ; Miae YOUN
Korean Journal of Blood Transfusion 2020;31(3):230-238
		                        		
		                        			Background:
		                        			Dengue fever is considered one of the transfusion-transmissible emerging infectious diseases. Dengue fever has been reported every year by the Korea Disease Control and Prevention Agency (KDCA). Because a blood donor screening assay to detect the dengue virus (DENV) as an agent of dengue fever is not performed, the risk of transfusion-transmitted DENV infection needs to be assessed. 
		                        		
		                        			Methods:
		                        			This study collected the data of DENV infected cases from the Infectious Disease Portal of the KDCA, the data of blood donors and blood components from the Blood Information Management System of the Korean Red Cross, and the data of travelers to major dengue outbreak countries from the Korean Tourism Organization.All data were from 2016 to 2018. A risk assessment was performed using European Up-Front Risk Assessment Tool (EUFRAT). 
		                        		
		                        			Results:
		                        			The risk of DENV-infected red cells and platelet concentrate was higher than that of plasma and apheresis platelet. Nevertheless, the risk of the DENV infected blood component was shown to be less than one case per year for all kinds of blood components. 
		                        		
		                        			Conclusion
		                        			All the DENV infected cases in Korea were overseas travelers. Therefore, the risk of transfusiontransmissible DENV infection is very low. On the other hand, continuous observation and monitoring are required because Aedes albopictus as a vector of DENV is found in Korea, and the increase in reported cases may lead to domestic infections.
		                        		
		                        		
		                        		
		                        	
            
Result Analysis
Print
Save
E-mail