Seoyoung Park
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Seoyoung Park has a total of 56 co-authors. Here are the top co-authors by number of shared publications:
- Dong Keon Yon
Department of Medicine Kyung Hee University College of Medicine Seoul South Korea
11 shared publications - Jaeyu Park
Center for Digital Health, Medical Science Research Institute Kyung Hee University Medical Center, Kyung Hee University College of Medicine Seoul South Korea
7 shared publications - Damiano Pizzol
Health Department, Eni Mozambique, Maputo, Mozambique
6 shared publications - Masoud Rahmati
Department of Physical Education and Sport Sciences, Faculty of Literature and Human Sciences, Lorestan University, Khorramabad, Iran
6 shared publications - Selin Woo
Center for Digital Health, Medical Science Research Institute Kyung Hee University Medical Center, Kyung Hee University College of Medicine Seoul South Korea
6 shared publications - Hayeon Lee
Center for Digital Health, Medical Science Research Institute, Kyung Hee University Medical Center, Kyung Hee University College of Medicine, Seoul, South Korea
5 shared publications
Latest Publications
- Open Access
- 23 September 2026
- Published by JMIR Publications Inc. in JMIR Medical Informatics
- Vol. 14, e82145
Multioutput Machine Learning Model for Predicting Postoperative Outcomes After Liposuction: Algorithm Development and Validation Study in a Multicenter Cohort
Background: Liposuction is widely performed to remove localized fat deposits and improve body contour, yet individualized prediction of postoperative outcomes remains challenging. Existing machine learning (ML) studies have largely focused on single-outcome prediction, with limited attention to the interdependence between postoperative body weight and circumferential size. Objective: This study aimed to develop and validate a chained multioutput ML framework to jointly predict postoperative body weight and circumferential size after liposuction using a large multicenter cohort from the 365mc network. Methods: We analyzed a multicenter cohort of 7804 individuals who underwent liposuction in 2024 at 20 obesity specialty clinics in the 365mc network across South Korea. Using 15 predictors, we compared 8 individual ML models, an automated ML approach, 2 ensemble approaches, and chained multioutput regression models for predicting postoperative body weight and circumferential size. Models were developed using 5-fold cross-validation and evaluated on an independent test set. Performance was assessed using the coefficient of determination ( R 2 ), root mean square error (RMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE), and feature importance was evaluated using Shapley additive explanation (SHAP) values. The selected model was integrated into a web-based clinical decision support system (CDSS). Results: A total of 7804 individuals who underwent liposuction were included; of these, 7612 (97.54%) were female. The chained extra trees regressor model with a weight-to-size prediction order achieved an R 2 of 0.98, an RMSE of 2.36, an MAE of 1.24, and a MAPE of 2.19. The SHAP analysis identified preoperative weight as the main predictor of postoperative body weight and preoperative size and liposuction-related factors as key predictors of postoperative circumferential size. The final model was integrated into a web-based CDSS (365mc AI platform). Conclusions: We developed and validated a chained multioutput regression model to predict postoperative body weight and circumferential size after liposuction. Integrated into a web-based CDSS, the model may support patient-specific preoperative counseling and surgical planning.
- 23 September 2026
- Published by JMIR Publications Inc. in JMIR Medical Informatics
- Vol. 14, e82145
Open AccessMultioutput Machine Learning Model for Predicting Postoperative Outcomes After Liposuction: Algorithm Development and Validation Study in a Multicenter Cohort
Background: Liposuction is widely performed to remove localized fat deposits and improve body contour, yet individualized prediction of postoperative outcomes remains challenging. Existing machine learning (ML) studies have largely focused on single-outcome prediction, with limited attention to the interdependence between postoperative body weight and circumferential size. Objective: This study aimed to develop and validate a chained multioutput ML framework to jointly predict postoperative body weight and circumferential size after liposuction using a large multicenter cohort from the 365mc network. Methods: We analyzed a multicenter cohort of 7804 individuals who underwent liposuction in 2024 at 20 obesity specialty clinics in the 365mc network across South Korea. Using 15 predictors, we compared 8 individual ML models, an automated ML approach, 2 ensemble approaches, and chained multioutput regression models for predicting postoperative body weight and circumferential size. Models were developed using 5-fold cross-validation and evaluated on an independent test set. Performance was assessed using the coefficient of determination ( R 2 ), root mean square error (RMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE), and feature importance was evaluated using Shapley additive explanation (SHAP) values. The selected model was integrated into a web-based clinical decision support system (CDSS). Results: A total of 7804 individuals who underwent liposuction were included; of these, 7612 (97.54%) were female. The chained extra trees regressor model with a weight-to-size prediction order achieved an R 2 of 0.98, an RMSE of 2.36, an MAE of 1.24, and a MAPE of 2.19. The SHAP analysis identified preoperative weight as the main predictor of postoperative body weight and preoperative size and liposuction-related factors as key predictors of postoperative circumferential size. The final model was integrated into a web-based CDSS (365mc AI platform). Conclusions: We developed and validated a chained multioutput regression model to predict postoperative body weight and circumferential size after liposuction. Integrated into a web-based CDSS, the model may support patient-specific preoperative counseling and surgical planning.
- 19 September 2026
- Published by Elsevier in Ophthalmology Retina
Global Burden of Age-Related Macular Degeneration, with Forecast up to 2050
- 19 September 2026
- Published by Elsevier in Ophthalmology Retina
Global Burden of Age-Related Macular Degeneration, with Forecast up to 2050
- Open Access
- 30 June 2026
- Published by The Editorial Office of Gut and Liver in Gut and Liver
- Vol. 20 (4) , 681-693
Global, Regional, and National Burden of Liver Cancer from 1990 to 2021 and Projections to 2050: A Global Burden of Disease Study 2021
This study assessed the burden of liver cancer (LC) and its major risk factors from 1990 to 2021, with projections to 2050. The global and regional LC burden from 1990 to 2021 was extracted from the Global Burden of Disease Study 2021, and stratified by age, sex, Sociodemographic Index (SDI), region, and etiological category. Trends for the age-standardized mortality rate (ASMR) and age-standardized disability-adjusted life year rate (ASDR) were evaluated using estimated annual percentage changes. Attributable risk factors, including alcohol use, drug use, a high body mass index, tobacco use, and high fasting plasma glucose levels, were examined. Projections of the LC burden to 2050 were modeled under baseline and hypothetical risk elimination scenarios. The global ASMR of LC remained stable, from 5.86 per 100,000 population (95% uncertainty interval [UI], 5.38 to 6.46) in 1990 to 5.65 (95% UI, 5.13 to 6.30) in 2021. Regions with an initially high ASMR showed increases until the early 2000s, then decreased. The LC burden increased sharply with age and was consistently higher in males, particularly in high-SDI regions. Mortality varied by etiology, with hepatitis B virus as the leading cause, followed by hepatitis C virus and alcohol use. Major risk factors were alcohol and tobacco use among males and drug and alcohol use among females. By 2050, the ASMR and ASDR of LC are projected to reach 6.23 per 100,000 population (95% UI, 4.94 to 8.09) and 158.91 (95% UI, 125.34 to 210.28), respectively, but could decrease to 5.32 (95% UI, 4.21 to 6.95) and 135.33 (95% UI, 106.74 to 179.05) under improved metabolic and behavioral risk scenarios. Despite public health interventions, LC is estimated to maintain a significant global burden.
- 30 June 2026
- Published by The Editorial Office of Gut and Liver in Gut and Liver
- Vol. 20 (4) , 681-693
Open AccessGlobal, Regional, and National Burden of Liver Cancer from 1990 to 2021 and Projections to 2050: A Global Burden of Disease Study 2021
This study assessed the burden of liver cancer (LC) and its major risk factors from 1990 to 2021, with projections to 2050. The global and regional LC burden from 1990 to 2021 was extracted from the Global Burden of Disease Study 2021, and stratified by age, sex, Sociodemographic Index (SDI), region, and etiological category. Trends for the age-standardized mortality rate (ASMR) and age-standardized disability-adjusted life year rate (ASDR) were evaluated using estimated annual percentage changes. Attributable risk factors, including alcohol use, drug use, a high body mass index, tobacco use, and high fasting plasma glucose levels, were examined. Projections of the LC burden to 2050 were modeled under baseline and hypothetical risk elimination scenarios. The global ASMR of LC remained stable, from 5.86 per 100,000 population (95% uncertainty interval [UI], 5.38 to 6.46) in 1990 to 5.65 (95% UI, 5.13 to 6.30) in 2021. Regions with an initially high ASMR showed increases until the early 2000s, then decreased. The LC burden increased sharply with age and was consistently higher in males, particularly in high-SDI regions. Mortality varied by etiology, with hepatitis B virus as the leading cause, followed by hepatitis C virus and alcohol use. Major risk factors were alcohol and tobacco use among males and drug and alcohol use among females. By 2050, the ASMR and ASDR of LC are projected to reach 6.23 per 100,000 population (95% UI, 4.94 to 8.09) and 158.91 (95% UI, 125.34 to 210.28), respectively, but could decrease to 5.32 (95% UI, 4.21 to 6.95) and 135.33 (95% UI, 106.74 to 179.05) under improved metabolic and behavioral risk scenarios. Despite public health interventions, LC is estimated to maintain a significant global burden.
- Open Access
- 25 January 2026
- Published by Korean Neuropsychiatric Association in Psychiatry Investigation
- Vol. 23 (1) , 48-62
National Trends in the Prevalence of Suicide Attempts Among Adolescents by Self-Perceived Weight, 2005–2023: A Nationwide Representative Study in South Korea
ObjectiveSuicide is a leading cause of death among adolescents, and despite the need to distinguish between suicidal consideration and suicide attempts, research focused on suicide attempts remains insufficient. Therefore, this study aims to investigate the influence of self-perceived weight on suicide attempts.MethodsThis study utilized data from the Korea Youth Risk Behavior Web-based Survey for its analysis from 2005 to 2023, including a total of 1,156,728 participants. This study utilized various analytical methods to examine the influence of self-perceived weight on suicide attempts. We estimated weighted prevalence and used linear regression to assess temporal trend β coefficients and their differences (βdiff) with 95% confidence intervals (CIs), and survey-weighted logistic regression to estimate weighted odds ratios (wORs) and 95% CIs for the association between self-perceived weight and suicide attempts.ResultsA comparison of suicide attempts based on self-perceived weight suggested that individuals who perceived themselves as overweight (weighted prevalence, 3.97% [95% CI, 3.89 to 4.04]) had the highest rate of suicide attempts, followed by those who perceived themselves as underweight (3.36% [95% CI, 3.28 to 3.44]), while those who perceived themselves as having a normal weight (3.20% [95% CI, 3.14 to 3.27]) had the lowest rate. Additionally, females (underweight: 4.47% [95% CI, 4.32 to 4.62]; normal weight: 3.91% [95% CI, 3.81 to 4.01]; overweight: 5.23% [5.11 to 5.35]) experienced more suicide attempts than males (underweight: 2.73% [95% CI, 2.65 to 2.82]; normal weight: 2.43% [95% CI, 2.35 to 2.51]; overweight: 2.60% [95% CI, 2.52 to 2.69]).ConclusionFindings from the present study suggest that self-perceived weight was associated with suicide attempts and interaction analyses indicated a potential sex-based difference in the impact of body image distortion. Therefore, this study suggests the introduction of programs and campaigns aimed at correcting distorted self-perceived weight.
- 25 January 2026
- Published by Korean Neuropsychiatric Association in Psychiatry Investigation
- Vol. 23 (1) , 48-62
Open AccessNational Trends in the Prevalence of Suicide Attempts Among Adolescents by Self-Perceived Weight, 2005–2023: A Nationwide Representative Study in South Korea
ObjectiveSuicide is a leading cause of death among adolescents, and despite the need to distinguish between suicidal consideration and suicide attempts, research focused on suicide attempts remains insufficient. Therefore, this study aims to investigate the influence of self-perceived weight on suicide attempts.MethodsThis study utilized data from the Korea Youth Risk Behavior Web-based Survey for its analysis from 2005 to 2023, including a total of 1,156,728 participants. This study utilized various analytical methods to examine the influence of self-perceived weight on suicide attempts. We estimated weighted prevalence and used linear regression to assess temporal trend β coefficients and their differences (βdiff) with 95% confidence intervals (CIs), and survey-weighted logistic regression to estimate weighted odds ratios (wORs) and 95% CIs for the association between self-perceived weight and suicide attempts.ResultsA comparison of suicide attempts based on self-perceived weight suggested that individuals who perceived themselves as overweight (weighted prevalence, 3.97% [95% CI, 3.89 to 4.04]) had the highest rate of suicide attempts, followed by those who perceived themselves as underweight (3.36% [95% CI, 3.28 to 3.44]), while those who perceived themselves as having a normal weight (3.20% [95% CI, 3.14 to 3.27]) had the lowest rate. Additionally, females (underweight: 4.47% [95% CI, 4.32 to 4.62]; normal weight: 3.91% [95% CI, 3.81 to 4.01]; overweight: 5.23% [5.11 to 5.35]) experienced more suicide attempts than males (underweight: 2.73% [95% CI, 2.65 to 2.82]; normal weight: 2.43% [95% CI, 2.35 to 2.51]; overweight: 2.60% [95% CI, 2.52 to 2.69]).ConclusionFindings from the present study suggest that self-perceived weight was associated with suicide attempts and interaction analyses indicated a potential sex-based difference in the impact of body image distortion. Therefore, this study suggests the introduction of programs and campaigns aimed at correcting distorted self-perceived weight.
- Open Access
- 1 January 2026
- Published by XMLink in Journal of Korean Medical Science
- Vol. 41 (35)
Global, Regional, and National Burden of Aortic Aneurysm, 1990–2021, and Projections to 2050
Jung M, et al. J Korean Med Sci. 2026 Sep;41:e237. https://doi.org/10.3346/jkms.2026.41.e237
- 1 January 2026
- Published by XMLink in Journal of Korean Medical Science
- Vol. 41 (35)
Open AccessGlobal, Regional, and National Burden of Aortic Aneurysm, 1990–2021, and Projections to 2050
Jung M, et al. J Korean Med Sci. 2026 Sep;41:e237. https://doi.org/10.3346/jkms.2026.41.e237
- Top Cited Papers
- 8 July 2025
- Published by Wolters Kluwer Health in Circulation
- Vol. 152 (1) , 11-23
Burden of Cardiovascular Outcomes After SARS-CoV-2 Infection in South Korea and Japan: A Binational Population-Based Cohort Study
BACKGROUND: Despite the significant global impact of the COVID-19 pandemic, limited studies have investigated the long-term cardiovascular sequelae of SARS-CoV-2 infection, particularly among Asian populations. This large-scale, population-based binational cohort study with long-term follow-up aimed to investigate the association between SARS-CoV-2 infection and the risk of cardiovascular events. METHODS: We used binational, large-scale, and population-based cohorts, including a Korean nationwide cohort (K-CONV-N [Korea Disease Control and Prevention Agency-COVID-19-National Health Insurance Service cohort]; discovery cohort; n=18 989 129) and a Japanese nationwide cohort (Japan Medical Data Center; validation cohort; n=12 218 680). Individuals aged 20 years or older were included from January 1, 2020, to December 31, 2022. We assessed the long-term risk of incident cardiovascular outcomes after SARS-CoV-2 infection. The primary outcome was the risk of cardiovascular diseases based on International Classification of Diseases, Tenth Revision code diagnosis. After propensity score–based overlap weighting, Cox proportional hazard models were used to estimate adjusted hazard ratios for cardiovascular outcomes. We assessed the time attenuation effect of cardiovascular outcomes after SARS-CoV-2 infection. Multiple subgroup analyses were conducted by 16 cardiovascular outcomes, COVID-19 severity, vaccination, and SARS-CoV-2 strain. RESULTS: In the overlap-weighted discovery cohort, 7 960 357 individuals were included (mean age, 48.52 years [SD, 9.33]; men, 4 283 878 [53.82%]). SARS-CoV-2 infection was associated with a long-term increased risk of overall cardiovascular outcomes (adjusted hazard ratio, 1.62 [95% CI, 1.60–1.64]), particularly ischemic heart disease (1.81 [95% CI, 1.77–1.84]), heart failure (1.79 [95% CI, 1.73–1.85]), cerebrovascular disorders (1.65 [95% CI, 1.60–1.69]), major adverse cardiovascular events (1.65 [95% CI, 1.60–1.70]), inflammatory heart diseases (1.53 [95% CI, 1.31–1.80]), dysrhythmia (1.44 [95% CI, 1.42–1.46]), and thrombotic disorders (1.42 [95% CI, 1.35–1.48]). The increased risk persisted up to 18 months, with the highest association observed for 1 to 6 months after infection. The risk of cardiovascular diseases was pronounced with COVID-19 severity; however, it decreased with the administration of complete vaccination and subsequent booster doses. A similar risk of cardiovascular outcomes existed across every SARS-CoV-2 era (pre-delta, delta, and omicron). Similar patterns were observed in the validation cohort. The absolute risk of cardiovascular disease events after SARS-CoV-2 infection remained remarkably low (2.12% versus 1.31% in the noninfected population), particularly stroke (0.24% versus 0.13%) and ischemic heart disease (0.73% versus 0.39%). CONCLUSIONS: This binational study observed associations between SARS-CoV-2 infection and cardiovascular events during extended follow-up across viral eras. Complete vaccination was linked to lower cardiovascular events. However, the absolute risk of cardiovascular disease events after SARS-CoV-2 infection remained remarkably low, particularly for stroke and ischemic heart disease. Although these findings suggest ongoing vigilance and preventive measures remain crucial, they should be interpreted within the context of these low absolute risks when considering long-term cardiovascular complications.
- 8 July 2025
- Published by Wolters Kluwer Health in Circulation
- Vol. 152 (1) , 11-23
Top Cited PapersBurden of Cardiovascular Outcomes After SARS-CoV-2 Infection in South Korea and Japan: A Binational Population-Based Cohort Study
BACKGROUND: Despite the significant global impact of the COVID-19 pandemic, limited studies have investigated the long-term cardiovascular sequelae of SARS-CoV-2 infection, particularly among Asian populations. This large-scale, population-based binational cohort study with long-term follow-up aimed to investigate the association between SARS-CoV-2 infection and the risk of cardiovascular events. METHODS: We used binational, large-scale, and population-based cohorts, including a Korean nationwide cohort (K-CONV-N [Korea Disease Control and Prevention Agency-COVID-19-National Health Insurance Service cohort]; discovery cohort; n=18 989 129) and a Japanese nationwide cohort (Japan Medical Data Center; validation cohort; n=12 218 680). Individuals aged 20 years or older were included from January 1, 2020, to December 31, 2022. We assessed the long-term risk of incident cardiovascular outcomes after SARS-CoV-2 infection. The primary outcome was the risk of cardiovascular diseases based on International Classification of Diseases, Tenth Revision code diagnosis. After propensity score–based overlap weighting, Cox proportional hazard models were used to estimate adjusted hazard ratios for cardiovascular outcomes. We assessed the time attenuation effect of cardiovascular outcomes after SARS-CoV-2 infection. Multiple subgroup analyses were conducted by 16 cardiovascular outcomes, COVID-19 severity, vaccination, and SARS-CoV-2 strain. RESULTS: In the overlap-weighted discovery cohort, 7 960 357 individuals were included (mean age, 48.52 years [SD, 9.33]; men, 4 283 878 [53.82%]). SARS-CoV-2 infection was associated with a long-term increased risk of overall cardiovascular outcomes (adjusted hazard ratio, 1.62 [95% CI, 1.60–1.64]), particularly ischemic heart disease (1.81 [95% CI, 1.77–1.84]), heart failure (1.79 [95% CI, 1.73–1.85]), cerebrovascular disorders (1.65 [95% CI, 1.60–1.69]), major adverse cardiovascular events (1.65 [95% CI, 1.60–1.70]), inflammatory heart diseases (1.53 [95% CI, 1.31–1.80]), dysrhythmia (1.44 [95% CI, 1.42–1.46]), and thrombotic disorders (1.42 [95% CI, 1.35–1.48]). The increased risk persisted up to 18 months, with the highest association observed for 1 to 6 months after infection. The risk of cardiovascular diseases was pronounced with COVID-19 severity; however, it decreased with the administration of complete vaccination and subsequent booster doses. A similar risk of cardiovascular outcomes existed across every SARS-CoV-2 era (pre-delta, delta, and omicron). Similar patterns were observed in the validation cohort. The absolute risk of cardiovascular disease events after SARS-CoV-2 infection remained remarkably low (2.12% versus 1.31% in the noninfected population), particularly stroke (0.24% versus 0.13%) and ischemic heart disease (0.73% versus 0.39%). CONCLUSIONS: This binational study observed associations between SARS-CoV-2 infection and cardiovascular events during extended follow-up across viral eras. Complete vaccination was linked to lower cardiovascular events. However, the absolute risk of cardiovascular disease events after SARS-CoV-2 infection remained remarkably low, particularly for stroke and ischemic heart disease. Although these findings suggest ongoing vigilance and preventive measures remain crucial, they should be interpreted within the context of these low absolute risks when considering long-term cardiovascular complications.
- Open Access
- 1 January 2025
- Published by XMLink in Journal of Korean Medical Science
- Vol. 40 (25) , e133
Trends in Diet Quality by the Diagnosis of Chronic Diseases in Korea, 2013–2021: A Nationwide Representative Study
Lee H, et al. J Korean Med Sci. 2025 Mar;40(25):e133. https://doi.org/10.3346/jkms.2025.40.e133
- 1 January 2025
- Published by XMLink in Journal of Korean Medical Science
- Vol. 40 (25) , e133
Open AccessTrends in Diet Quality by the Diagnosis of Chronic Diseases in Korea, 2013–2021: A Nationwide Representative Study
Lee H, et al. J Korean Med Sci. 2025 Mar;40(25):e133. https://doi.org/10.3346/jkms.2025.40.e133
- Open Access
- 1 November 2024
- Published by JMIR Publications Inc. in JMIR Public Health and Surveillance
- Vol. 10 (1) , e57359
Sex-Specific Trends in the Prevalence of Osteoarthritis and Rheumatoid Arthritis From 2005 to 2021 in South Korea: Nationwide Cross-Sectional Study
Background: Osteoarthritis and rheumatoid arthritis (RA) are prevalent chronic joint disorders, with prevalence rates varying by sex. However, few studies have comprehensively documented the factors contributing to the sex-specific prevalence of osteoarthritis and RA, including sociological factors and the impact of the COVID-19 pandemic. Objective: This study aims to identify long-term trends in the sex-specific prevalence of osteoarthritis and RA from 2005 to 2021 while examining the factors that serve as vulnerabilities specific to each sex within the context of the COVID-19 pandemic. Methods: Data were collected from a nationally representative sample of 110,225 individuals through the Korea National Health and Nutrition Examination Survey from 2005 to 2021. The study included patients aged 19 years and older diagnosed with osteoarthritis or RA in South Korea. Data were analyzed using weighted trends to accurately represent the sample population, with a 95% CI. Weighted logistic and regression models were used to identify vulnerable groups at risk of osteoarthritis or RA during the pandemic to assess sex-specific trends. Results: In total, 110,225 individuals (n=48,410, 43.92% male participants) were analyzed from 2005 to 2021, with prevalence rates remaining stable over time and higher in female than in male participants. Notably, during the pandemic, female participants aged 60 years and older exhibited a prevalence of osteoarthritis that was 4.92 times greater than male participants and a prevalence of RA that was 6.44 times greater (osteoarthritis: prevalence ratio [PR] 69.78, 95% CI 41.66-116.88; RA: PR 17.27, 95% CI 8.75-34.07). In terms of osteoarthritis, male participants did not show a significant association with BMI (PR 1.40, 95% CI 1.21-1.61; P=.47), whereas female participants exhibited a significantly higher vulnerability within the obese group (PR 1.68, 95% CI 1.55-1.83; P<.001). Regarding RA, lower education levels were associated with increased vulnerability, with male participants showing a greater risk than female participants (male participants: PR 2.29, 95% CI 1.61-3.27 and female participants: PR 1.50, 95% CI 1.23-1.84). Conclusions: This study reveals that women in South Korea have a higher prevalence of osteoarthritis and RA than men. Understanding these sex-specific trends and identifying vulnerability factors can enhance preventive efforts and patient care.
- 1 November 2024
- Published by JMIR Publications Inc. in JMIR Public Health and Surveillance
- Vol. 10 (1) , e57359
Open AccessSex-Specific Trends in the Prevalence of Osteoarthritis and Rheumatoid Arthritis From 2005 to 2021 in South Korea: Nationwide Cross-Sectional Study
Background: Osteoarthritis and rheumatoid arthritis (RA) are prevalent chronic joint disorders, with prevalence rates varying by sex. However, few studies have comprehensively documented the factors contributing to the sex-specific prevalence of osteoarthritis and RA, including sociological factors and the impact of the COVID-19 pandemic. Objective: This study aims to identify long-term trends in the sex-specific prevalence of osteoarthritis and RA from 2005 to 2021 while examining the factors that serve as vulnerabilities specific to each sex within the context of the COVID-19 pandemic. Methods: Data were collected from a nationally representative sample of 110,225 individuals through the Korea National Health and Nutrition Examination Survey from 2005 to 2021. The study included patients aged 19 years and older diagnosed with osteoarthritis or RA in South Korea. Data were analyzed using weighted trends to accurately represent the sample population, with a 95% CI. Weighted logistic and regression models were used to identify vulnerable groups at risk of osteoarthritis or RA during the pandemic to assess sex-specific trends. Results: In total, 110,225 individuals (n=48,410, 43.92% male participants) were analyzed from 2005 to 2021, with prevalence rates remaining stable over time and higher in female than in male participants. Notably, during the pandemic, female participants aged 60 years and older exhibited a prevalence of osteoarthritis that was 4.92 times greater than male participants and a prevalence of RA that was 6.44 times greater (osteoarthritis: prevalence ratio [PR] 69.78, 95% CI 41.66-116.88; RA: PR 17.27, 95% CI 8.75-34.07). In terms of osteoarthritis, male participants did not show a significant association with BMI (PR 1.40, 95% CI 1.21-1.61; P=.47), whereas female participants exhibited a significantly higher vulnerability within the obese group (PR 1.68, 95% CI 1.55-1.83; P<.001). Regarding RA, lower education levels were associated with increased vulnerability, with male participants showing a greater risk than female participants (male participants: PR 2.29, 95% CI 1.61-3.27 and female participants: PR 1.50, 95% CI 1.23-1.84). Conclusions: This study reveals that women in South Korea have a higher prevalence of osteoarthritis and RA than men. Understanding these sex-specific trends and identifying vulnerability factors can enhance preventive efforts and patient care.
- Open Access
- 14 February 2024
- Published by JMIR Publications Inc. in JMIR Preprints
Sex-Specific Trends in the Prevalence of Osteoarthritis and Rheumatoid Arthritis From 2005 to 2021 in South Korea: Nationwide Cross-Sectional Study (Preprint)
BACKGROUND Osteoarthritis and rheumatoid arthritis (RA) are prevalent chronic joint disorders, with prevalence rates varying by sex. However, few studies have comprehensively documented the factors contributing to the sex-specific prevalence of osteoarthritis and RA, including sociological factors and the impact of the COVID-19 pandemic. OBJECTIVE This study aims to identify long-term trends in the sex-specific prevalence of osteoarthritis and RA from 2005 to 2021 while examining the factors that serve as vulnerabilities specific to each sex within the context of the COVID-19 pandemic. METHODS Data were collected from a nationally representative sample of 110,225 individuals through the Korea National Health and Nutrition Examination Survey from 2005 to 2021. The study included patients aged 19 years and older diagnosed with osteoarthritis or RA in South Korea. Data were analyzed using weighted trends to accurately represent the sample population, with a 95% CI. Weighted logistic and regression models were used to identify vulnerable groups at risk of osteoarthritis or RA during the pandemic to assess sex-specific trends. RESULTS In total, 110,225 individuals (n=48,410, 43.92% male participants) were analyzed from 2005 to 2021, with prevalence rates remaining stable over time and higher in female than in male participants. Notably, during the pandemic, female participants aged 60 years and older exhibited a prevalence of osteoarthritis that was 4.92 times greater than male participants and a prevalence of RA that was 6.44 times greater (osteoarthritis: prevalence ratio [PR] 69.78, 95% CI 41.66-116.88; RA: PR 17.27, 95% CI 8.75-34.07). In terms of osteoarthritis, male participants did not show a significant association with BMI (PR 1.40, 95% CI 1.21-1.61; P=.47), whereas female participants exhibited a significantly higher vulnerability within the obese group (PR 1.68, 95% CI 1.55-1.83; P<.001). Regarding RA, lower education levels were associated with increased vulnerability, with male participants showing a greater risk than female participants (male participants: PR 2.29, 95% CI 1.61-3.27 and female participants: PR 1.50, 95% CI 1.23-1.84). CONCLUSIONS This study reveals that women in South Korea have a higher prevalence of osteoarthritis and RA than men. Understanding these sex-specific trends and identifying vulnerability factors can enhance preventive efforts and patient care.
- 14 February 2024
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessSex-Specific Trends in the Prevalence of Osteoarthritis and Rheumatoid Arthritis From 2005 to 2021 in South Korea: Nationwide Cross-Sectional Study (Preprint)
BACKGROUND Osteoarthritis and rheumatoid arthritis (RA) are prevalent chronic joint disorders, with prevalence rates varying by sex. However, few studies have comprehensively documented the factors contributing to the sex-specific prevalence of osteoarthritis and RA, including sociological factors and the impact of the COVID-19 pandemic. OBJECTIVE This study aims to identify long-term trends in the sex-specific prevalence of osteoarthritis and RA from 2005 to 2021 while examining the factors that serve as vulnerabilities specific to each sex within the context of the COVID-19 pandemic. METHODS Data were collected from a nationally representative sample of 110,225 individuals through the Korea National Health and Nutrition Examination Survey from 2005 to 2021. The study included patients aged 19 years and older diagnosed with osteoarthritis or RA in South Korea. Data were analyzed using weighted trends to accurately represent the sample population, with a 95% CI. Weighted logistic and regression models were used to identify vulnerable groups at risk of osteoarthritis or RA during the pandemic to assess sex-specific trends. RESULTS In total, 110,225 individuals (n=48,410, 43.92% male participants) were analyzed from 2005 to 2021, with prevalence rates remaining stable over time and higher in female than in male participants. Notably, during the pandemic, female participants aged 60 years and older exhibited a prevalence of osteoarthritis that was 4.92 times greater than male participants and a prevalence of RA that was 6.44 times greater (osteoarthritis: prevalence ratio [PR] 69.78, 95% CI 41.66-116.88; RA: PR 17.27, 95% CI 8.75-34.07). In terms of osteoarthritis, male participants did not show a significant association with BMI (PR 1.40, 95% CI 1.21-1.61; P=.47), whereas female participants exhibited a significantly higher vulnerability within the obese group (PR 1.68, 95% CI 1.55-1.83; P<.001). Regarding RA, lower education levels were associated with increased vulnerability, with male participants showing a greater risk than female participants (male participants: PR 2.29, 95% CI 1.61-3.27 and female participants: PR 1.50, 95% CI 1.23-1.84). CONCLUSIONS This study reveals that women in South Korea have a higher prevalence of osteoarthritis and RA than men. Understanding these sex-specific trends and identifying vulnerability factors can enhance preventive efforts and patient care.
- Open Access
- 14 February 2024
- Published by JMIR Publications Inc. in Journal of Medical Internet Research
- Vol. 26 (1) , e51473
Machine Learning–Based Prediction of Suicidality in Adolescents With Allergic Rhinitis: Derivation and Validation in 2 Independent Nationwide Cohorts
Background: Given the additional risk of suicide-related behaviors in adolescents with allergic rhinitis (AR), it is important to use the growing field of machine learning (ML) to evaluate this risk. Objective: This study aims to evaluate the validity and usefulness of an ML model for predicting suicide risk in patients with AR. Methods: We used data from 2 independent survey studies, Korea Youth Risk Behavior Web-based Survey (KYRBS; n=299,468) for the original data set and Korea National Health and Nutrition Examination Survey (KNHANES; n=833) for the external validation data set, to predict suicide risks of AR in adolescents aged 13 to 18 years, with 3.45% (10,341/299,468) and 1.4% (12/833) of the patients attempting suicide in the KYRBS and KNHANES studies, respectively. The outcome of interest was the suicide attempt risks. We selected various ML-based models with hyperparameter tuning in the discovery and performed an area under the receiver operating characteristic curve (AUROC) analysis in the train, test, and external validation data. Results: The study data set included 299,468 (KYRBS; original data set) and 833 (KNHANES; external validation data set) patients with AR recruited between 2005 and 2022. The best-performing ML model was the random forest model with a mean AUROC of 84.12% (95% CI 83.98%-84.27%) in the original data set. Applying this result to the external validation data set revealed the best performance among the models, with an AUROC of 89.87% (sensitivity 83.33%, specificity 82.58%, accuracy 82.59%, and balanced accuracy 82.96%). While looking at feature importance, the 5 most important features in predicting suicide attempts in adolescent patients with AR are depression, stress status, academic achievement, age, and alcohol consumption. Conclusions: This study emphasizes the potential of ML models in predicting suicide risks in patients with AR, encouraging further application of these models in other conditions to enhance adolescent health and decrease suicide rates.
- 14 February 2024
- Published by JMIR Publications Inc. in Journal of Medical Internet Research
- Vol. 26 (1) , e51473
Open AccessMachine Learning–Based Prediction of Suicidality in Adolescents With Allergic Rhinitis: Derivation and Validation in 2 Independent Nationwide Cohorts
Background: Given the additional risk of suicide-related behaviors in adolescents with allergic rhinitis (AR), it is important to use the growing field of machine learning (ML) to evaluate this risk. Objective: This study aims to evaluate the validity and usefulness of an ML model for predicting suicide risk in patients with AR. Methods: We used data from 2 independent survey studies, Korea Youth Risk Behavior Web-based Survey (KYRBS; n=299,468) for the original data set and Korea National Health and Nutrition Examination Survey (KNHANES; n=833) for the external validation data set, to predict suicide risks of AR in adolescents aged 13 to 18 years, with 3.45% (10,341/299,468) and 1.4% (12/833) of the patients attempting suicide in the KYRBS and KNHANES studies, respectively. The outcome of interest was the suicide attempt risks. We selected various ML-based models with hyperparameter tuning in the discovery and performed an area under the receiver operating characteristic curve (AUROC) analysis in the train, test, and external validation data. Results: The study data set included 299,468 (KYRBS; original data set) and 833 (KNHANES; external validation data set) patients with AR recruited between 2005 and 2022. The best-performing ML model was the random forest model with a mean AUROC of 84.12% (95% CI 83.98%-84.27%) in the original data set. Applying this result to the external validation data set revealed the best performance among the models, with an AUROC of 89.87% (sensitivity 83.33%, specificity 82.58%, accuracy 82.59%, and balanced accuracy 82.96%). While looking at feature importance, the 5 most important features in predicting suicide attempts in adolescent patients with AR are depression, stress status, academic achievement, age, and alcohol consumption. Conclusions: This study emphasizes the potential of ML models in predicting suicide risks in patients with AR, encouraging further application of these models in other conditions to enhance adolescent health and decrease suicide rates.