Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Yujin Choi has a total of 31 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Machine Learning–Based Prediction of Substance Use in Adolescents in Three Independent Worldwide Cohorts: Algorithm Development and Validation Study

    by Soeun Kim, Hyejun Kim, Seokjun Kim, Hojae Lee, Ahmed Hammoodi, Yujin Choi, Hyeon Jin Kim, Lee Smith, Min Seo Kim, Guillaume Fond, et al.

    Background: To address gaps in global understanding of cultural and social variations, this study used a high-performance machine learning (ML) model to predict adolescent substance use across three national datasets. Objective: This study aims to develop a generalizable predictive model for adolescent substance use using multinational datasets and ML. Methods: The study used the Korea Youth Risk Behavior Web-Based Survey (KYRBS) from South Korea (n=1,098,641) to train ML models. For external validation, we used the Youth Risk Behavior Survey (YRBS) from the United States (n=2,511,916) and Norwegian nationwide Ungdata surveys (Ungdata) from Norway (n=700,660). After developing various ML models, we evaluated the final model’s performance using multiple metrics. We also assessed feature importance using traditional methods and further analyzed variable contributions through SHapley Additive exPlanation values. Results: The study used nationwide adolescent datasets for ML model development and validation, analyzing data from 1,098,641 KYRBS adolescents, 2,511,916 YRBS participants, and 700,660 from Ungdata. The XGBoost model was the top performer on the KYRBS, achieving an area under receiver operating characteristic curve (AUROC) score of 80.61% (95% CI 79.63-81.59) and precision of 30.42 (95% CI 28.65-32.16) with detailed analysis on sensitivity of 31.30 (95% CI 29.47-33.20), specificity of 99.16 (95% CI 99.12-99.20), accuracy of 98.36 (95% CI 98.31-98.42), balanced accuracy of 65.23 (95% CI 64.31-66.17), F1-score of 30.85 (95% CI 29.25-32.51), and area under precision-recall curve of 32.14 (95% CI 30.34-33.95). The model achieved an AUROC score of 79.30% and a precision of 68.37% on the YRBS dataset, while in external validation using the Ungdata dataset, it recorded an AUROC score of 76.39% and a precision of 12.74%. Feature importance and SHapley Additive exPlanation value analyses identified smoking status, BMI, suicidal ideation, alcohol consumption, and feelings of sadness and despair as key contributors to the risk of substance use, with smoking status emerging as the most influential factor. Conclusions: Based on multinational datasets from South Korea, the United States, and Norway, this study shows the potential of ML models, particularly the XGBoost model, in predicting adolescent substance use. These findings provide a solid basis for future research exploring additional influencing factors or developing targeted intervention strategies.


  • Open Access

    Machine Learning–Based Prediction of Substance Use in Adolescents in Three Independent Worldwide Cohorts: Algorithm Development and Validation Study (Preprint)

    by Soeun Kim, Hyejun Kim, Seokjun Kim, Hojae Lee, Ahmed Hammoodi, Yujin Choi, Hyeon Jin Kim, Lee Smith, Min Seo Kim, Guillaume Fond, et al.

    BACKGROUND To address gaps in global understanding of cultural and social variations, this study used a high-performance machine learning (ML) model to predict adolescent substance use across three national datasets. OBJECTIVE This study aims to develop a generalizable predictive model for adolescent substance use using multinational datasets and ML. METHODS The study used the Korea Youth Risk Behavior Web-Based Survey (KYRBS) from South Korea (n=1,098,641) to train ML models. For external validation, we used the Youth Risk Behavior Survey (YRBS) from the United States (n=2,511,916) and Norwegian nationwide Ungdata surveys (Ungdata) from Norway (n=700,660). After developing various ML models, we evaluated the final model’s performance using multiple metrics. We also assessed feature importance using traditional methods and further analyzed variable contributions through SHapley Additive exPlanation values. RESULTS The study used nationwide adolescent datasets for ML model development and validation, analyzing data from 1,098,641 KYRBS adolescents, 2,511,916 YRBS participants, and 700,660 from Ungdata. The XGBoost model was the top performer on the KYRBS, achieving an area under receiver operating characteristic curve (AUROC) score of 80.61% (95% CI 79.63-81.59) and precision of 30.42 (95% CI 28.65-32.16) with detailed analysis on sensitivity of 31.30 (95% CI 29.47-33.20), specificity of 99.16 (95% CI 99.12-99.20), accuracy of 98.36 (95% CI 98.31-98.42), balanced accuracy of 65.23 (95% CI 64.31-66.17), F1-score of 30.85 (95% CI 29.25-32.51), and area under precision-recall curve of 32.14 (95% CI 30.34-33.95). The model achieved an AUROC score of 79.30% and a precision of 68.37% on the YRBS dataset, while in external validation using the Ungdata dataset, it recorded an AUROC score of 76.39% and a precision of 12.74%. Feature importance and SHapley Additive exPlanation value analyses identified smoking status, BMI, suicidal ideation, alcohol consumption, and feelings of sadness and despair as key contributors to the risk of substance use, with smoking status emerging as the most influential factor. CONCLUSIONS Based on multinational datasets from South Korea, the United States, and Norway, this study shows the potential of ML models, particularly the XGBoost model, in predicting adolescent substance use. These findings provide a solid basis for future research exploring additional influencing factors or developing targeted intervention strategies.

  • Top Cited Papers
    Open Access

    Acute and post-acute respiratory complications of SARS-CoV-2 infection: population-based cohort study in South Korea and Japan

    by Yujin Choi, Hyeon Jin Kim, Jaeyu Park, Myeongcheol Lee, Sunyoung Kim, Ai Koyanagi, Lee Smith, Min Seo Kim, Masoud Rahmati, Hayeon Lee, et al.

    Considering the significant burden of post-acute COVID-19 conditions among patients infected with SARS-CoV-2, we aimed to identify the risk of acute respiratory complications or post-acute respiratory sequelae. A binational population-based cohort study was conducted to analyze the risk of acute respiratory complications or post-acute respiratory sequelae after SARS-CoV-2 infection. We used a Korean nationwide claim-based cohort (K-COV-N; n = 2,312,748; main cohort) and a Japanese claim-based cohort (JMDC; n = 3,115,606; replication cohort) after multi-to-one propensity score matching. Among 2,312,748 Korean participants (mean age, 47.2 years [SD, 15.6]; 1,109,708 [48.0%] female), 17.1% (394,598/2,312,748) were infected with SARS-CoV-2. The risk of acute respiratory complications or post-acute respiratory sequelae is significantly increased in people with SARS-CoV-2 infection compared to the general population (acute respiratory complications: HR, 8.06 [95% CI, 6.92-9.38]; post-acute respiratory sequelae: 1.68 [1.62-1.75]), and the risk increased with increasing COVID-19 severity. We identified COVID-19 vaccination as an attenuating factor, showing a protective association against acute or post-acute respiratory conditions. Furthermore, while the excess post-acute risk diminished with time following SARS-CoV-2 infection, it persisted beyond 6 months post-infection. The replication cohort showed a similar pattern in the association. Our study comprehensively evaluates respiratory complications in post-COVID-19 conditions, considering attenuating factors such as vaccination status, post-infection duration, COVID-19 severity, and specific respiratory conditions.


  • Open Access

    Machine Learning–Based Prediction of Suicidal Thinking in Adolescents by Derivation and Validation in 3 Independent Worldwide Cohorts: Algorithm Development and Validation Study

    by Hyejun Kim, Yejun Son, Hojae Lee, Jiseung Kang, Ahmed Hammoodi, Yujin Choi, Hyeon Jin Kim, Hayeon Lee, Guillaume Fond, Laurent Boyer, et al.

    Background: Suicide is the second-leading cause of death among adolescents and is associated with clusters of suicides. Despite numerous studies on this preventable cause of death, the focus has primarily been on single nations and traditional statistical methods. Objective: This study aims to develop a predictive model for adolescent suicidal thinking using multinational data sets and machine learning (ML). Methods: We used data from the Korea Youth Risk Behavior Web-based Survey with 566,875 adolescents aged between 13 and 18 years and conducted external validation using the Youth Risk Behavior Survey with 103,874 adolescents and Norway’s University National General Survey with 19,574 adolescents. Several tree-based ML models were developed, and feature importance and Shapley additive explanations values were analyzed to identify risk factors for adolescent suicidal thinking. Results: When trained on the Korea Youth Risk Behavior Web-based Survey data from South Korea with a 95% CI, the XGBoost model reported an area under the receiver operating characteristic (AUROC) curve of 90.06% (95% CI 89.97-90.16), displaying superior performance compared to other models. For external validation using the Youth Risk Behavior Survey data from the United States and the University National General Survey from Norway, the XGBoost model achieved AUROCs of 83.09% and 81.27%, respectively. Across all data sets, XGBoost consistently outperformed the other models with the highest AUROC score, and was selected as the optimal model. In terms of predictors of suicidal thinking, feelings of sadness and despair were the most influential, accounting for 57.4% of the impact, followed by stress status at 19.8%. This was followed by age (5.7%), household income (4%), academic achievement (3.4%), sex (2.1%), and others, which contributed less than 2% each. Conclusions: This study used ML by integrating diverse data sets from 3 countries to address adolescent suicide. The findings highlight the important role of emotional health indicators in predicting suicidal thinking among adolescents. Specifically, sadness and despair were identified as the most significant predictors, followed by stressful conditions and age. These findings emphasize the critical need for early diagnosis and prevention of mental health issues during adolescence.


  • Open Access

    Machine Learning–Based Prediction of Suicidal Thinking in Adolescents by Derivation and Validation in 3 Independent Worldwide Cohorts: Algorithm Development and Validation Study (Preprint)

    by Hyejun Kim, Yejun Son, Hojae Lee, Jiseung Kang, Ahmed Hammoodi, Yujin Choi, Hyeon Jin Kim, Hayeon Lee, Guillaume Fond, Laurent Boyer, et al.

    BACKGROUND Suicide is the second-leading cause of death among adolescents and is associated with clusters of suicides. Despite numerous studies on this preventable cause of death, the focus has primarily been on single nations and traditional statistical methods. OBJECTIVE This study aims to develop a predictive model for adolescent suicidal thinking using multinational data sets and machine learning (ML). METHODS We used data from the Korea Youth Risk Behavior Web-based Survey with 566,875 adolescents aged between 13 and 18 years and conducted external validation using the Youth Risk Behavior Survey with 103,874 adolescents and Norway’s University National General Survey with 19,574 adolescents. Several tree-based ML models were developed, and feature importance and Shapley additive explanations values were analyzed to identify risk factors for adolescent suicidal thinking. RESULTS When trained on the Korea Youth Risk Behavior Web-based Survey data from South Korea with a 95% CI, the XGBoost model reported an area under the receiver operating characteristic (AUROC) curve of 90.06% (95% CI 89.97-90.16), displaying superior performance compared to other models. For external validation using the Youth Risk Behavior Survey data from the United States and the University National General Survey from Norway, the XGBoost model achieved AUROCs of 83.09% and 81.27%, respectively. Across all data sets, XGBoost consistently outperformed the other models with the highest AUROC score, and was selected as the optimal model. In terms of predictors of suicidal thinking, feelings of sadness and despair were the most influential, accounting for 57.4% of the impact, followed by stress status at 19.8%. This was followed by age (5.7%), household income (4%), academic achievement (3.4%), sex (2.1%), and others, which contributed less than 2% each. CONCLUSIONS This study used ML by integrating diverse data sets from 3 countries to address adolescent suicide. The findings highlight the important role of emotional health indicators in predicting suicidal thinking among adolescents. Specifically, sadness and despair were identified as the most significant predictors, followed by stressful conditions and age. These findings emphasize the critical need for early diagnosis and prevention of mental health issues during adolescence.

  • Maternal SARS-CoV-2 infection during pregnancy and subsequent risk of atopic dermatitis in offspring: a nationwide birth cohort study in South Korea

    by Minji Kim, Yujin Choi, Myeongcheol Lee, Jiseung Kang, So Min Kang, Dong-Geol Lee, Dong Keon Yon

    Although previous studies suggest an association between SARS-CoV-2 infection and atopic dermatitis (AD) in adults, insufficient attention has been given to the impact of SARS-CoV-2 infection on pregnant woman and their offspring. Evidence on prenatal SARS-CoV-2 infection and subsequent risk of AD is lacking; therefore, we aimed to investigate the risk of AD in infants born to women who were infected with SARS-CoV-2 during pregnancy.


  • Open Access

    National Trends in Rotavirus Enteritis among Infants in South Korea, 2010–2021: A Nationwide Cohort

    by Hyun Jee Lee, Yujin Choi, Jaeyu Park, Yong-Sung Choi, Dong Keon Yon, Do Hyun Kim

    Rotavirus causes a gastrointestinal tract infection that primarily affects young children. Due to the COVID-19 pandemic, individuals infected with the virus were subjected to quarantine measures, with strong emphases on personal hygiene and social distancing. The present study aimed to evaluate the characteristics of rotaviruses and compare the prevalence of rotavirus infection before and during the COVID-19 pandemic. This nationwide representative study was conducted using data acquired from the National Health Insurance Service between 2010 and 2021. We analyzed the data of patients younger than 12 months old who were diagnosed with rotavirus enteritis between January 2010 and December 2021. During the study period, a total of 34,487 infants younger than 12 months were diagnosed with rotavirus enteritis in South Korea. During the two-year COVID-19 pandemic (2020–2021), the rate of decline was significant (5843 cases in 2010 and 1125 in 2019), and by 2021, the total number of patients was almost negligible, as there are only 18 cases in 2021. A significant increase in the ratio of low birth weight (LBW) infants of inpatient department was observed from 2010 to 2021 (4.86% in 2010; 7.77% in 2019; and 23.08% in 2021), indicating that LBW infants are more vulnerable than infants born with normal weight. Average medical expenses related to rotavirus infections also declined significantly from 3,789,443,998 per year (pre-pandemic) to 808,353,795 per year (pandemic). Overall, personal hygiene and social distancing may play important roles in reducing rotavirus infections. However, further studies are needed to determine whether this decreasing trend persists after quarantine and whether the social life of individuals resumes.