Association between behavioral and sociodemographic factors and high subjective health among adolescents: a nationwide representative study in South Korea

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: Jan. 7, 2025

The need to understand subjective health has increased during the COVID-19 pandemic, given its substantial impact on lifestyle habits and perceptions. Thus, this study aimed investigate trends association of with demographic behavioral factors, primarily focusing change when pandemic emerged. This used data from Korea Youth Risk Behavior Web-based Survey, comprising 1,190,468 adolescents aged 12–18 years (female, 48.49%). We investigated factors 2006 2023. A weighted linear regression joinpoint were conducted evaluate trend in adolescent health, while logistic was assess associated factors. stratification analysis performed for subgroups determine variations across different groups. prevalence reporting high throughout before pandemic; however, exhibited a decreasing pandemic. Regarding female sex (ratio odds ratio [ROR], 0.85 [95% CI, 0.83–0.87]), low-income households (ROR, 0.67 0.64–0.69]), low academic achievement 0.83 0.81–0.85]) less likelihood health. Healthier breakfast consumption, 1.13 1.10–1.16]; sufficient fruit intake, 1.12 1.09–1.15]; physical activity, 2.02 1.95–2.09]) higher disparities To address observed decline among targeted interventions at promoting healthy behaviors particularly vulnerable demographics are crucial.

Language: Английский

---

Machine learning-based prediction of substance use in adolescents in 3 independent worldwide cohorts: Algorithm development and validation study (Preprint)

Journal of Medical Internet Research, Journal Year: 2025, Volume and Issue: 27, P. e62805 - e62805

Published: Jan. 16, 2025

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

Language: Английский

---

Trends in adolescent violence victimization pre-, intra-, and post-COVID–19 pandemic in South Korea, 2012–2023: a nationwide cross-sectional study

Psychiatry Research, Journal Year: 2025, Volume and Issue: 348, P. 116429 - 116429

Published: March 6, 2025

Language: Английский

---

Development of an explainable machine learning model for predicting depression in adolescent girls with non-suicidal self-injury: A cross-sectional multicenter study

Journal of Affective Disorders, Journal Year: 2025, Volume and Issue: unknown

Published: March 1, 2025

Language: Английский

---

Prediction model for type 2 diabetes mellitus and its association with mortality using machine learning in three independent cohorts from South Korea, Japan, and the UK: a model development and validation study

EClinicalMedicine, Journal Year: 2025, Volume and Issue: 80, P. 103069 - 103069

Published: Jan. 18, 2025

Language: Английский

---

Innovative Machine Learning Paradigms for Predicting Emergency Department Visits in T2DM Patients: A Comprehensive Analysis Across South Korea's Quintet Cohorts (Preprint)

Published: April 28, 2025

Background: Visiting emergency departments (ED) among patients with Type 2 Diabetes Mellitus (T2DM) is associated adverse outcomes, including increased risks of hospitalization and mortality. Utilizing real-world clinical data, prescription information, to predict the likelihood ED visits could benefit primary care. This study aimed apply machine learning (ML) methods based on electronic medical records (EMR) T2DM. Methods: We analyzed data from five independent EHR-based cohorts: Data institutions were combined randomly divided into a training set (n=176,576) for model test (n=44,144) evaluation. The outcome was occurrence first visits. Various models evaluated through hyperparameter tuning within set, area under receiver operating characteristic (AUROC) curve calculated set. Results: Among 64,436 screened, xxx met inclusion criteria, 11,549 (17.92%) having at least visit in while 220,720 49,770 (22.55%) one CatBoost exhibited superior performance, achieving mean AUROC 78 % (95% CI, 94.4-94.9) an 87 top 20 strong predictive variables, diastolic blood pressure (DBP) most significant variable identified. Conclusions: In this study, we developed assessing risk validated using other hospitals, demonstrating its applicability settings identifying heightened requiring

Language: Английский

---

Machine Learning–Based Prediction for Incident Hypertension Based on Regular Health Checkup Data: Derivation and Validation in 2 Independent Nationwide Cohorts in South Korea and Japan

Journal of Medical Internet Research, Journal Year: 2024, Volume and Issue: 26, P. e52794 - e52794

Published: Nov. 5, 2024

Background Worldwide, cardiovascular diseases are the primary cause of death, with hypertension as a key contributor. In 2019, led to 17.9 million deaths, predicted reach 23 by 2030. Objective This study presents new method predict using demographic data, 6 machine learning models for enhanced reliability and applicability. The goal is harness artificial intelligence early accurate diagnosis across diverse populations. Methods Data from 2 national cohort studies, National Health Insurance Service-National Sample Cohort (South Korea, n=244,814), conducted between 2002 2013 were used train test designed anticipate incident within 5 years health checkup involving those aged ≥20 years, Japanese Medical Center (Japan, n=1,296,649) extra validation. An ensemble was identify most salient features contributing presenting feature importance analysis confirm contribution each future. Results Adaptive Boosting logistic regression showed superior balanced accuracy (0.812, sensitivity 0.806, specificity 0.818, area under receiver operating characteristic curve 0.901). indicators age, diastolic blood pressure, BMI, systolic fasting glucose. dataset (extra validation set) corroborated these findings (balanced 0.741 0.824). model integrated into public web portal predicting onset based on data. Conclusions Comparative evaluation our against classical statistical distinct studies emphasized former’s stability, generalizability, reproducibility in onset.

Language: Английский

---

National trends in adolescents’ mental health by income level in South Korea, pre– and post–COVID–19, 2006–2022

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: Oct. 23, 2024

Despite the significant impact of COVID-19 pandemic on various factors related to adolescent mental health problems such as stress, sadness, suicidal ideation, and suicide attempts, research this topic has been insufficient date. This study is based Korean Youth Risk Behavior Web-based Survey from 2006 2022. We analyzed adolescents questionnaires with medical interviews, within five income groups compared them several risk factors. A total 1,138,804 participants were included in study, a mean age (SD) 15.01 (0.75) years. Of these, 587,256 male (51.57%). In 2022, recent period weighted prevalence stress highest group was 40.07% (95% CI, 38.67-41.48), sadness 28.15% (26.82-29.48), ideation 13.92% (12.87-14.97), attempts 3.42% (2.90-3.93) while lowest 62.77% (59.42-66.13), 46.83% (43.32-50.34), 31.70% (28.44-34.96), 10.45% (8.46-12.45). Lower showed higher proportion Overall had decreased until onset pandemic. However, increase found during Our an association between household level illness adolescents. Furthermore, exacerbated among low level, underscoring necessity for heightened public attention measures targeted at demographic.

Language: Английский

---

Comparison of national trends in physical activity among adolescents before and during the COVID-19 pandemic: a nationally representative serial study in South Korea

Heliyon, Journal Year: 2024, Volume and Issue: 10(21), P. e40004 - e40004

Published: Nov. 1, 2024

Language: Английский

---

Predictive model for abdominal liposuction volume in patients with obesity using machine learning in a longitudinal multi-center study in Korea

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: Nov. 30, 2024

Abstract This study aimed to develop and validate a machine learning (ML)-based model for predicting liposuction volumes in patients with obesity. used longitudinal cohort data from 2018 2023 five nationwide centers affiliated 365MC Liposuction Hospital, the largest hospitals Korea. Fifteen variables related patient profiles were integrated applied various ML algorithms, including random forest, support vector, XGBoost, decision tree, AdaBoost regressors. Performance evaluation employed mean absolute error (MAE), root square (RMSE), R-squared (R 2 ) score. Feature importance RMSE analyses performed compare influence of each feature on prediction performance. A total 9,856 included final analysis. The forest regressor best predicted volume (MAE, 0.197, RMSE, 0.249, R , 0.792). Body fat mass waist circumference most important features (feature 71.55 13.21, 0.201 0.221, respectively). Leveraging this model, web-based application was developed suggest ideal volumes. These findings could be clinical practice enhance decision-making tailor surgical interventions individual needs, thereby improving overall efficacy satisfaction.

Language: Английский

---