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 DOI Creative Commons
Soon Cheon Hwang, Hayeon Lee, Jun Hyuk Lee

et al.

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

Long-term trends in the prevalence of cardiovascular-kidney-metabolic syndrome in South Korea, 2011–2021: a representative longitudinal serial study DOI Creative Commons

Yesol Yim,

Jae Eun Lee, Yejun Son

et al.

The Lancet Regional Health - Western Pacific, Journal Year: 2025, Volume and Issue: 55, P. 101474 - 101474

Published: Jan. 22, 2025

Language: Английский

Citations

1
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 DOI Creative Commons
Hayeon Lee, Soon Cheon Hwang, Seoyoung Park

et al.

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

Published: Jan. 18, 2025

Language: Английский

Citations

0
Predictive Factors of Wound Healing and Limb Salvage After Successful Below-the-Knee Endovascular Angioplasty in Patients with Diabetic Foot Ulcer: A Retrospective Study DOI Creative Commons

Chang Sik Shin,

Kwon Cheol Yoo

Medicina, Journal Year: 2025, Volume and Issue: 61(2), P. 277 - 277

Published: Feb. 6, 2025

Background and Objectives: The primary objective of this study was to determine the predictive factors limb salvage wound healing in patients presenting with diabetic foot ulcers (DFUs) following successful below-the-knee endovascular angioplasty. Materials Methods: Between January 2014 2019, we retrospectively analyzed rates 85 (88 limbs) who underwent infra-popliteal treatment (EVT) for DFUs. Numerous variables were explored, including age, sex, comorbidities, scores from three DFU grading systems (Wagner grade, University Texas (UT) grade stage, Wound, Ischemia, Infection (WIfI) stage). Univariate multivariate Cox proportional hazards analyses conducted associations between adverse events these variables. Results: During follow-up, 44 wounds healed completely, 47 amputations (major, 25; minor, 22) required, 17 limbs needed reintervention healing. Nine received died cardiovascular cerebrovascular diseases, pneumonia, other causes. At 1, 3, 6, 9, 12 months, total 4.6%, 16.9%, 27.5%, 34.5%, 64.5%, respectively. 6 1 year, 2 years, 5 amputation-free survival 77.6%, 72.4%, 63.3%, In analyses, UT stage associated increased non-healing, while Wagner major lower-extremity amputation rates. Importantly, only simultaneous risk factor predicting both salvage. Conclusions: Despite angioplasty, a significant proportion experienced non-healing amputation. may serve as predictor outcomes.

Language: Английский

Citations

0
National trends in type 2 diabetes mellitus stratified by central adiposity using waist-to-height ratio in South Korea, 2005–2022 DOI Creative Commons
Hyunjee Kim, Seoyoung Park, Jaeyu Park

et al.

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

Published: Oct. 16, 2024

Studies investigating the association between type 2 diabetes mellitus and central adiposity are lacking. Therefore, this study aimed to investigate trends in stratified by using waist-to-height ratio (WHtR). Trends were examined adiposity, WHtR, with data from Korea National Health Nutrition Examination Survey (2005-2022). Individuals aged 30 years over who participated survey selected. Type was identified based on serum glucose or HbA1c levels, use of medications, a prior diagnosis physician. Weighted β-coefficients odd ratios (ORs) 95% confidence intervals (CIs) calculated assess changes disease prevalence. A total 79,368 participants included database (female: 45,163 [56.9%]). 2005 2022, prevalence increased 3.3 5.8% healthy group, 11.2 17.1% 18.0 26.7% high group. Males, older population, lower education level, household income, smoking associated higher risk diabetes. In overweight obese individuals had susceptibility than underweight normal-weight individuals, ORs 5.85 (95% CI, 2.54-13.47) 8.24 (3.79-17.94), respectively. The has all groups past decade. This underscores need for tailored interventions address disparities improve management at-risk populations.

Language: Английский

Citations

2
Sex-Specific Trends in the Prevalence of Osteoarthritis and Rheumatoid Arthritis From 2005 to 2021 in South Korea: Nationwide Cross-Sectional Study DOI Creative Commons
Seoyoung Park, Yejun Son, Hyeri Lee

et al.

JMIR Public Health and Surveillance, Journal Year: 2024, Volume and Issue: 10, P. e57359 - e57359

Published: Nov. 1, 2024

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 sex-specific of osteoarthritis RA, including sociological impact COVID-19 pandemic.

Language: Английский

Citations

2
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 DOI Creative Commons
Soon Cheon Hwang, Hayeon Lee, Jun Hyuk Lee

et al.

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

Citations

2