MLMyeongcheol Lee

Myeongcheol Lee

*This is an algorithmically generated author record based on publicly available information.

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


Myeongcheol Lee has a total of 58 co-authors. Here are the top co-authors by number of shared publications:

  • Dong Keon Yon

    Center for Digital Health, Medical Science Research Institute, Kyung Hee University College of Medicine, Seoul, South Korea

    7 shared publications
  • Ai Koyanagi

    Research and Development Unit, Parc Sanitari Sant Joan de Déu, CIBERSAM, ISCIII, Dr. Antoni Pujadas, 42, Sant Boi de Llobregat 08830, Barcelona, Spain; ICREA, Pg. Lluis Companys 23, Barcelona 08010, Spain

    5 shared publications
  • Lee Smith

    Centre for Health, Performance and Wellbeing Anglia Ruskin University Cambridge UK

    5 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

    4 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

    4 shared publications
  • Sang Youl Rhee

    Department of Endocrinology and Metabolism Kyung Hee University College of Medicine Seoul Republic of Korea

    4 shared publications

Latest Publications

  • Open Access

    Physical Activity and Cardiovascular Risk in Type 2 Diabetes With Normal Body Mass Index and Abdominal Obesity: A Nationwide Cohort Study

    by Onyou Kim, Yong Hwan Park, Soo Yeon Kim, Myeongcheol Lee, Wonchang Hahn, Chang Hoon Kim, Danbee Kang, Ki Hong Choi

    Background: The prognostic implications of abdominal obesity and moderate‐to‐vigorous physical activity (MVPA) in patients with type 2 diabetes who have a normal body mass index remain unclear. Methods: This nationwide retrospective cohort study included 323 029 adults with newly diagnosed type 2 diabetes and a normal body mass index (2 ) between January 1, 2010, and December 31, 2023, from the Korean National Health Insurance Service database. Abdominal obesity was defined using sex‐specific waist circumference thresholds (≥90 cm for men, ≥80 cm for women). MVPA was assessed through standardized self‐reported questionnaires administered during routine health screenings. The primary outcome was major adverse cardiovascular and cerebrovascular events, defined as a composite of all‐cause death, myocardial infarction, ischemic stroke, or hospitalization for heart failure. Results: Among the study population, 34 033 (10.5%) had abdominal obesity. During a median follow‐up of 6.0 years (interquartile range, 2.6–9.0 years), abdominal obesity was associated with a higher risk of major adverse cardiovascular and cerebrovascular events (adjusted hazard ratio [HR], 1.13 [95% CI, 1.09–1.17]). Among patients with abdominal obesity, regular MVPA after diagnosis (27.1%) was associated with a significantly lower risk of major adverse cardiovascular and cerebrovascular events (adjusted HR 0.74 [95% CI, 0.68–0.80]), all‐cause mortality (adjusted HR 0.72 [95% CI, 0.65–0.80]), ischemic stroke (adjusted HR 0.77 [95% CI, 0.66–0.89]), and hospitalization for heart failure (adjusted HR 0.75 [95% CI, 0.60–0.93]). The cardiovascular protective effects of MVPA were consistent regardless of statin or antidiabetic medication use. Conclusions: In patients with type 2 diabetes and a normal body mass index, abdominal obesity was independently associated with a higher risk of major adverse cardiovascular and cerebrovascular events. Regular engagement in MVPA showed consistent cardiovascular benefits in this population, irrespective of pharmacotherapy. Registration: URL: https://www.clinicaltrials.gov ; Unique identifier: NCT07071545.

  • Becoming Physically Active and Risks of Mortality and Liver‐Related Events in Adults With Chronic Hepatitis B: A Nationwide Cohort Study

    by Byeong Geun Song, Myeongcheol Lee, Juhee Cho, Geum‐Youn Gwak, Danbee Kang, Dong Hyun Sinn

    Physical activity (PA) confers several health benefits; however, whether increasing PA among physically inactive adults with chronic hepatitis B (CHB) is associated with lower risks of adverse clinical outcomes remains unclear. We used the nationwide Korean National Health Insurance database. We included 318,131 adults with CHB who were physically inactive at the initial health screening (Exam 1) and completed a subsequent screening within 4 years (Exam 2). Among them, 58,703 initiated moderate‐to‐vigorous PA (MVPA), defined as vigorous activity ≥ 20 min/day on ≥ 3 days/week or moderate activity ≥ 30 min/day on ≥ 5 days/week. The primary outcome was all‐cause mortality, and the secondary outcomes were liver‐related events (hepatic decompensation, liver transplantation, hepatocellular carcinoma [HCC]) and HCC. Multivariable Cox and Fine–Grey competing‐risk models were adjusted for demographic, clinical, and behavioural factors. During a median 7.9‐year follow‐up (IQR, 5.2–9.5), 7609 deaths occurred. MVPA initiation was associated with lower all‐cause mortality (hazard ratio [HR], 0.89; 95% CI, 0.84–0.94), a lower risk of liver‐related events (subdistribution HR [subHR], 0.94; 95% CI, 0.92–0.97), and, more modestly, of HCC (subHR, 0.95; 95% CI, 0.91–0.99) compared with those remaining inactive. The association was more pronounced in older adults, women, never smokers, non‐drinkers, and untreated participants (all p for interaction ≤ 0.03). Initiating MVPA among physically inactive adults with CHB was associated with lower risks of mortality and liver‐related outcomes. These findings provide large‐scale epidemiological evidence supporting further evaluation of PA promotion in physically inactive patients with CHB.

  • Open Access

    Risk-based hepatocellular carcinoma surveillance thresholds using a prediction score in Asian patients with chronic hepatitis B: a nationwide cohort study

    by Won Sohn, Myeongcheol Lee, Danbee Kang, Ju Yeon Cho, Jung Hee Kim, Soo Jin Park, Yong-Han Paik

    Background/Aims: This study aimed to quantify hepatocellular carcinoma (HCC) incidence according to a validated prediction score and to define score-based cut-offs corresponding to surveillance-relevant incidence thresholds in Asian patients with chronic hepatitis B (CHB) receiving antiviral therapy.Methods: We conducted a nationwide population-based cohort study using the Korean National Health Insurance Service database. Adults with CHB initiating nucleos(t)ide analogue therapy between 2012 and 2023 were included; those with viral coinfections, prior malignancy, or decompensated cirrhosis were excluded. HCC risk was stratified using the HCC-RESCUE score. Incident HCC was the primary outcome. Annual HCC incidence rates and adjusted hazard ratios were estimated using multivariable Cox proportional hazards models.Results: Among 199,143 treated patients (median follow-up, 7.3 years), 15,233 developed HCC. Adjusted annual HCC incidence increased progressively across risk strata: 0.31% (95% confidence interval [CI], 0.24-0.40) in the low-risk group, 1.09% (95% CI, 0.84-1.41) in the intermediate-risk group, and 1.85% (95% CI, 1.44-2.40) in the high-risk group. Compared with the low-risk group, adjusted hazard ratios for HCC were 3.48 (95% CI, 3.35-3.61) and 5.90 (95% CI, 5.62-6.19) in the intermediate- and high-risk groups, respectively (all P<0.001). HCC-RESCUE scores corresponding to annual HCC incidence thresholds of 0.2%, 1.5%, and 3.0% were 47, 66, and 90.Conclusions: In a large antiviral-treated Asian CHB population, prediction score–based stratification revealed a graded spectrum of residual HCC risk and identified incidence-aligned thresholds relevant to surveillance. These findings support incidence-informed refinement of HCC surveillance strategies that complement traditional cirrhosis-based criteria in the antiviral treatment era.

  • Open Access

    Development and Validation of a Machine Learning Algorithm for Predicting Diabetes Retinopathy in Patients With Type 2 Diabetes: Algorithm Development Study

    by Sunyoung Kim, Jaeyu Park, Yejun Son, Hojae Lee, Selin Woo, Myeongcheol Lee, Hayeon Lee, Hyunji Sang, Dong Keon Yon, Sang Youl Rhee

    Background: Diabetic retinopathy (DR) is the leading cause of preventable blindness worldwide. Machine learning (ML) systems can enhance DR in community-based screening. However, predictive power models for usability and performance are still being determined. Objective: This study used data from 3 university hospitals in South Korea to conduct a simple and accurate assessment of ML-based risk prediction for the development of DR that can be universally applied to adults with type 2 diabetes mellitus (T2DM). Methods: DR was predicted using data from 2 independent electronic medical records: a discovery cohort (one hospital, n=14,694) and a validation cohort (2 hospitals, n=1856). The primary outcome was the presence of DR at 3 years. Different ML-based models were selected through hyperparameter tuning in the discovery cohort, and the area under the receiver operating characteristic (ROC) curve was analyzed in both cohorts. Results: Among 14,694 patients screened for inclusion, 348 (2.37%) were diagnosed with DR. For DR, the extreme gradient boosting (XGBoost) system had an accuracy of 75.13% (95% CI 74.10‐76.17), a sensitivity of 71.00% (95% CI 66.83‐75.17), and a specificity of 75.23% (95% CI 74.16‐76.31) in the original dataset. Among the validation datasets, XGBoost had an accuracy of 65.14%, a sensitivity of 64.96%, and a specificity of 65.15%. The most common feature in the XGBoost model is dyslipidemia, followed by cancer, hypertension, chronic kidney disease, neuropathy, and cardiovascular disease. Conclusions: This approach shows the potential to enhance patient outcomes by enabling timely interventions in patients with T2DM, improving our understanding of contributing factors, and reducing DR-related complications. The proposed prediction model is expected to be both competitive and cost-effective, particularly for primary care settings in South Korea.


  • Open Access

    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

    by Seung Ha Hwang, Hayeon Lee, Jun Hyuk Lee, Myeongcheol Lee, Ai Koyanagi, Lee Smith, Sang Youl Rhee, Dong Keon Yon, Jinseok Lee

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


  • Open Access

    Association Between Sociodemographic Factors and Vaccine Acceptance for Influenza and SARS-CoV-2 in South Korea: Nationwide Cross-Sectional Study

    by Seohyun Hong, Yejun Son, Myeongcheol Lee, Jun Hyuk Lee, Jaeyu Park, Hayeon Lee, Elena Dragioti, Guillaume Fond, Laurent Boyer, Guillermo Felipe López Sánchez, et al.

    Background: The imperative arises to study the impact of socioeconomic factors on the acceptance of SARS-CoV-2 and influenza vaccines amid changes in immunization policies during the COVID-19 pandemic. Objective: To enhance targeted public health strategies and improve age-specific policies based on identified risk factors, this study investigated the associations between sociodemographic factors and vaccination behaviors during the COVID-19 pandemic, with emphasis on age-specific vaccine cost policies. Methods: This study analyzed data from the Korean Community Health Survey 2019‐2022 with 507,964 participants to investigate the impact of age-specific policies on vaccination behaviors during the pandemic period. Cohorts aged 19‐64 years and 65 years or older were stratified based on age (years), sociodemographic factors, and health indicators. The cohorts were investigated to assess the influence of relevant risk factors on vaccine acceptance under the pandemic by using weighted odds ratio and ratio of odds ratio (ROR). Results: Among 507,964 participants, the acceptance of the SARS-CoV-2 vaccine (COVID-19 vaccine) was higher among individuals with factors possibly indicating higher socioeconomic status, such as higher education level (age 19‐64 years: ROR 1.34; 95% CI 1.27‐1.40 and age ≥65 years: ROR 1.19; 95% CI 1.01‐1.41) and higher income (age 19‐64 years: ROR 1.67; 95% CI 1.58‐1.76 and age ≥65 years: ROR 1.21; 95% CI 1.06‐1.38) for both age cohorts compared to influenza vaccine acceptance before the pandemic. In the context of influenza vaccination during the pandemic, the older cohort exhibited vaccine hesitancy associated with health care mobility factors such as lower general health status (ROR 0.89; 95% CI 0.81‐0.97). Conclusions: SARS-CoV-2 vaccination strategies should focus on reducing hesitancy among individuals with lower social participation. To improve influenza vaccine acceptance during the pandemic, strategies for the younger cohort should focus on individuals with lower social participation, while efforts for the older cohort should prioritize individuals with limited access to health care services.


  • Open Access

    Slow gut transit increases the risk of Alzheimer’s disease: An integrated study of the bi-national cohort in South Korea and Japan and Alzheimer’s disease model mice

    by Jiseung Kang, Myeongcheol Lee, Mincheol Park, Jibeom Lee, Sunjae Lee, Jaeyu Park, Ai Koyanagi, Lee Smith, Christa J. Nehs, Dong Keon Yon, et al.


  • Open Access

    Hand and Oral Hygiene Practices of South Korean Adolescents Before and During the COVID-19 Pandemic

    by Jiyeon Oh, Myeongcheol Lee, Hojae Lee, Hwi Yang, Jaeyu Park, Masoud Rahmati, Ai Koyanagi, Lee Smith, Guillaume Fond, Laurent Boyer, et al.

    Importance: Only a few studies have examined the long-term trends of hand and oral hygiene, especially among adolescents.Objective: To investigate the 15-year trends in frequency of handwashing and toothbrushing and examine the factors associated with hand and oral hygiene, particularly during the COVID-19 pandemic.Design, Setting, and Participants: This cross-sectional study, performed from January 1, 2008, to December 31, 2022, used general population–based data from 963 644 individuals in a national representative survey (Korea Youth Risk Behavior Web-based Survey [KYRBS]).Exposure: COVID-19 pandemic.Main Outcomes and Measures: Trends in hand and oral hygiene practices were measured by how frequently adolescents washed their hands and whether they fulfilled the recommended guidelines for toothbrushing. An interrupted time series analysis using linear and logistic regression models was performed to assess any associations with the COVID-19 pandemic. Hand and oral hygiene behaviors before and during the pandemic in each sociodemographic subgroup were also compared.Results: In the 963 644 adolescents (495 697 [51.4%] male; mean [range] age, 15.01 [12-18] years) who participated in the KYRBS from 2008 to 2022, a 73.3% (95% CI, 59.4%-97.4%; P < .001) immediate increase was seen in overall hand hygiene behavior at the onset of the COVID-19 pandemic compared with the prepandemic period, with a sustained decrease thereafter (β = −0.018; 95% CI, −0.022 to −0.015; P < .001). Meanwhile, no immediate increase was observed in terms of overall oral hygiene behavior (0.1%; 95% CI, −0.9% to 1.1%; P = .82); however, there was a sustained decrease during the pandemic (β = −0.018; 95% CI, −0.020 to −0.016; P < .001). Older age, female sex, nonsmoking status, alcohol use, low household economic level, and poor school performance were significantly associated with poor hand hygiene during the pandemic.Conclusions and Relevance: In this cross-sectional study of South Korean adolescents, an increase in the prevalence of hand hygiene was observed during the early pandemic; however, this prevalence decreased over time. Meanwhile, the decrease in the prevalence of oral hygiene was more pronounced during the pandemic. This study recommends stronger guidelines for adolescent health coaches, such as teachers or public health advisers, regarding hygiene behaviors, even after the COVID-19 pandemic ends.


  • Open Access

    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 (Preprint)

    by Seung Ha Hwang, Hayeon Lee, Jun Hyuk Lee, Myeongcheol Lee, Ai Koyanagi, Lee Smith, Sang Youl Rhee, Dong Keon Yon, Jinseok Lee

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

  • Open Access

    Machine learning-based prediction model for cardiovascular disease in patients with diabetes: Derivation and validation in two independent Korean cohorts (Preprint)

    by Hyunji Sang, Hojae Lee, Myeongcheol Lee, Jaeyu Park, Wonyoung Cho, Sunyoung Kim, Ho Geol Woo, Masoud Rahmati, Ai Koyanagi, Lee Smith, et al.

    BACKGROUND Various machine learning (ML) prediction models have recently been developed for cardiovascular disease (CVD) in type 2 diabetes mellitus (T2DM); however, the lack of multiple risk factors limits their predictive power. OBJECTIVE This study aimed to evaluate the validity and usefulness of an ML model for predicting the 3-year incidence of CVD in patients with T2DM. METHODS We used data from two independent cohorts, the discovery cohort (one hospital; n=12,809) and the validation cohort (two hospitals; n=2019), to predict CVD. The outcome of interest was the presence/absence of CVD at 3 years. We selected various ML-based models with hyperparameter tuning in the discovery cohort and performed an area under the receiver operating characteristic curve (AUROC) analysis in the validation cohort. RESULTS The study dataset included 12,809 (discovery) and 2,019 (validation) patients with T2DM recruited between 2008–2022. CVD was observed in 1,238 (10.2%) patients in the discovery cohort. The random forest (RF) model had a mean AUROC of 0.830 (95% confidence interval 0.816–0.845) in the discovery dataset. Applying this result to the extra-validation dataset revealed the best performance among the models, with an AUROC of 0.72 (accuracy of 65.4%, sensitivity of 66.0%, specificity of 65.4%, and balanced accuracy of 65.7%). Creatinine and glycated hemoglobin levels were the most influential factors in the RF model. CONCLUSIONS This study demonstrates the usefulness and feasibility of ML for assessing CVD incidence in patients with T2DM and suggests its potential for use in patient screening. Further international studies are required to validate our findings.