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.Clinical and Imaging Features of a Focal Intrahepatic Biliary Stricture Visualized Only as Duct Dilatation
Byoung Je KIM ; Min Seong KIM ; Mi Jeong KIM ; Jae Hyuck YI ; Jin Hyuk PAEK ; Hye Won LEE ; Chan Hee PARK ; Gisu LEE ; Koo Jeong KANG
Journal of the Korean Society of Radiology 2024;85(6):1157-1168
Purpose:
We assessed the proportion of patients with a focal intrahepatic stricture (FIHS) that was a precursor lesion or malignancy and visualized only as a duct dilatation.
Materials and Methods:
This retrospective study assessed patients who underwent surgery or biopsy for an FIHS on CT or MRI between January 2010 and March 2022. The number and proportion of non-precursor benign lesions, precursors, and malignancies were calculated.Clinical variables and imaging features were compared between non-premalignant benign and premalignant/malignant FIHSs.
Results:
Twenty-eight patients with confirmed histopathological diagnoses were identified, including 15 men (54.0%) and 13 women (46.0%). The median age of all patients at the first imaging diagnosis was 65 ± 9.54 (range, 43–78) years. Of the 28 patients with FIHSs, 9 (32%) were diagnosed with cholangiocarcinoma and 7 (25%) were diagnosed with precursor lesions, which included six intraductal papillary neoplasms of the bile duct and one biliary intraepithelial neoplasm. Accordingly, 16 (57%) patients had malignant or precursor lesions, and 12 (43%) were diagnosed with non-precursor benign lesions. None of the clinical variables and imaging features used for analysis showed a statistically significant difference between the non-premalignant benign and premalignant/malignant FIHS groups (p > 0.05).
Conclusion
FIHSs visualized only as duct dilatation can harbor malignant or precursor lesions.
3.Smoking Cessation Treatment in Primary Care
Hye-ji AN ; Cheol-Min LEE ; Yoo-Bin SEO ; Eon-Sook LEE ; Yu-Jin PAEK
Korean Journal of Family Practice 2024;14(4):184-192
Smoking is a major health risk factor contributing to substantial morbidity and mortality worldwide. Although most smokers express a desire to quit— or they attempt to do so—, achieving smoking cessation solely through individual willpower is often challenging. Primary care plays a pivotal role in supporting smoking cessation efforts by increasing the likelihood of success. Even brief advice from a physician significantly increases the chance of quitting, and combining counseling with pharmacotherapy further improves cessation rates. Particular attention is required for smokers in special populations, such as those with cardiovascular diseases or mental health conditions, wherein tailored and proactive smoking cessation interventions are crucial. Digital health tools, including smartphone applications and text messaging interventions, have recently emerged as effective strategies to support personalized smoking cessation behaviors. Furthermore, institutional support, such as national programs, quitlines, and post-screening counseling for lung cancer, are critical resources that promote successful cessation. Primary care physicians are uniquely positioned to foster longterm smoking cessation success through sustained relationships with patients by leveraging these tools and resources to provide comprehensive and continuous care.
4.Smoking Cessation Treatment in Primary Care
Hye-ji AN ; Cheol-Min LEE ; Yoo-Bin SEO ; Eon-Sook LEE ; Yu-Jin PAEK
Korean Journal of Family Practice 2024;14(4):184-192
Smoking is a major health risk factor contributing to substantial morbidity and mortality worldwide. Although most smokers express a desire to quit— or they attempt to do so—, achieving smoking cessation solely through individual willpower is often challenging. Primary care plays a pivotal role in supporting smoking cessation efforts by increasing the likelihood of success. Even brief advice from a physician significantly increases the chance of quitting, and combining counseling with pharmacotherapy further improves cessation rates. Particular attention is required for smokers in special populations, such as those with cardiovascular diseases or mental health conditions, wherein tailored and proactive smoking cessation interventions are crucial. Digital health tools, including smartphone applications and text messaging interventions, have recently emerged as effective strategies to support personalized smoking cessation behaviors. Furthermore, institutional support, such as national programs, quitlines, and post-screening counseling for lung cancer, are critical resources that promote successful cessation. Primary care physicians are uniquely positioned to foster longterm smoking cessation success through sustained relationships with patients by leveraging these tools and resources to provide comprehensive and continuous care.
5.Smoking Cessation Treatment in Primary Care
Hye-ji AN ; Cheol-Min LEE ; Yoo-Bin SEO ; Eon-Sook LEE ; Yu-Jin PAEK
Korean Journal of Family Practice 2024;14(4):184-192
Smoking is a major health risk factor contributing to substantial morbidity and mortality worldwide. Although most smokers express a desire to quit— or they attempt to do so—, achieving smoking cessation solely through individual willpower is often challenging. Primary care plays a pivotal role in supporting smoking cessation efforts by increasing the likelihood of success. Even brief advice from a physician significantly increases the chance of quitting, and combining counseling with pharmacotherapy further improves cessation rates. Particular attention is required for smokers in special populations, such as those with cardiovascular diseases or mental health conditions, wherein tailored and proactive smoking cessation interventions are crucial. Digital health tools, including smartphone applications and text messaging interventions, have recently emerged as effective strategies to support personalized smoking cessation behaviors. Furthermore, institutional support, such as national programs, quitlines, and post-screening counseling for lung cancer, are critical resources that promote successful cessation. Primary care physicians are uniquely positioned to foster longterm smoking cessation success through sustained relationships with patients by leveraging these tools and resources to provide comprehensive and continuous care.
6.Clinical and Imaging Features of a Focal Intrahepatic Biliary Stricture Visualized Only as Duct Dilatation
Byoung Je KIM ; Min Seong KIM ; Mi Jeong KIM ; Jae Hyuck YI ; Jin Hyuk PAEK ; Hye Won LEE ; Chan Hee PARK ; Gisu LEE ; Koo Jeong KANG
Journal of the Korean Society of Radiology 2024;85(6):1157-1168
Purpose:
We assessed the proportion of patients with a focal intrahepatic stricture (FIHS) that was a precursor lesion or malignancy and visualized only as a duct dilatation.
Materials and Methods:
This retrospective study assessed patients who underwent surgery or biopsy for an FIHS on CT or MRI between January 2010 and March 2022. The number and proportion of non-precursor benign lesions, precursors, and malignancies were calculated.Clinical variables and imaging features were compared between non-premalignant benign and premalignant/malignant FIHSs.
Results:
Twenty-eight patients with confirmed histopathological diagnoses were identified, including 15 men (54.0%) and 13 women (46.0%). The median age of all patients at the first imaging diagnosis was 65 ± 9.54 (range, 43–78) years. Of the 28 patients with FIHSs, 9 (32%) were diagnosed with cholangiocarcinoma and 7 (25%) were diagnosed with precursor lesions, which included six intraductal papillary neoplasms of the bile duct and one biliary intraepithelial neoplasm. Accordingly, 16 (57%) patients had malignant or precursor lesions, and 12 (43%) were diagnosed with non-precursor benign lesions. None of the clinical variables and imaging features used for analysis showed a statistically significant difference between the non-premalignant benign and premalignant/malignant FIHS groups (p > 0.05).
Conclusion
FIHSs visualized only as duct dilatation can harbor malignant or precursor lesions.
7.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.
8.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.
9.Clinical and Imaging Features of a Focal Intrahepatic Biliary Stricture Visualized Only as Duct Dilatation
Byoung Je KIM ; Min Seong KIM ; Mi Jeong KIM ; Jae Hyuck YI ; Jin Hyuk PAEK ; Hye Won LEE ; Chan Hee PARK ; Gisu LEE ; Koo Jeong KANG
Journal of the Korean Society of Radiology 2024;85(6):1157-1168
Purpose:
We assessed the proportion of patients with a focal intrahepatic stricture (FIHS) that was a precursor lesion or malignancy and visualized only as a duct dilatation.
Materials and Methods:
This retrospective study assessed patients who underwent surgery or biopsy for an FIHS on CT or MRI between January 2010 and March 2022. The number and proportion of non-precursor benign lesions, precursors, and malignancies were calculated.Clinical variables and imaging features were compared between non-premalignant benign and premalignant/malignant FIHSs.
Results:
Twenty-eight patients with confirmed histopathological diagnoses were identified, including 15 men (54.0%) and 13 women (46.0%). The median age of all patients at the first imaging diagnosis was 65 ± 9.54 (range, 43–78) years. Of the 28 patients with FIHSs, 9 (32%) were diagnosed with cholangiocarcinoma and 7 (25%) were diagnosed with precursor lesions, which included six intraductal papillary neoplasms of the bile duct and one biliary intraepithelial neoplasm. Accordingly, 16 (57%) patients had malignant or precursor lesions, and 12 (43%) were diagnosed with non-precursor benign lesions. None of the clinical variables and imaging features used for analysis showed a statistically significant difference between the non-premalignant benign and premalignant/malignant FIHS groups (p > 0.05).
Conclusion
FIHSs visualized only as duct dilatation can harbor malignant or precursor lesions.
10.Smoking Cessation Treatment in Primary Care
Hye-ji AN ; Cheol-Min LEE ; Yoo-Bin SEO ; Eon-Sook LEE ; Yu-Jin PAEK
Korean Journal of Family Practice 2024;14(4):184-192
Smoking is a major health risk factor contributing to substantial morbidity and mortality worldwide. Although most smokers express a desire to quit— or they attempt to do so—, achieving smoking cessation solely through individual willpower is often challenging. Primary care plays a pivotal role in supporting smoking cessation efforts by increasing the likelihood of success. Even brief advice from a physician significantly increases the chance of quitting, and combining counseling with pharmacotherapy further improves cessation rates. Particular attention is required for smokers in special populations, such as those with cardiovascular diseases or mental health conditions, wherein tailored and proactive smoking cessation interventions are crucial. Digital health tools, including smartphone applications and text messaging interventions, have recently emerged as effective strategies to support personalized smoking cessation behaviors. Furthermore, institutional support, such as national programs, quitlines, and post-screening counseling for lung cancer, are critical resources that promote successful cessation. Primary care physicians are uniquely positioned to foster longterm smoking cessation success through sustained relationships with patients by leveraging these tools and resources to provide comprehensive and continuous care.

Result Analysis
Print
Save
E-mail