Sang Jun Lee
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Sang Jun Lee has a total of 23 co-authors. Here are the top co-authors by number of shared publications:
- Sung Gyun Ahn
Wonju Severance Christian Hospital, Yonsei University Wonju College of Medicine, Wonju, South Korea
2 shared publications - Young Jun Park
Division of Cardiology, Department of Internal Medicine, Korea University Anam Hospital, Korea University College of Medicine , Seoul 02841
2 shared publications - Dae Ryong Kang
Department of Precision Medicine & Biostatistics, Yonsei University Wonju College of Medicine, Wonju, Republic of Korea
1 shared publication - Dong-Hyuk Cho
Division of Cardiology, Department of Internal Medicine, Korea University Anam Hospital, Korea University College of Medicine, Seoul, Korea
1 shared publication - Hyun Jin Ahn
Department of Internal Medicine and Cardiovascular Center, Seoul National University Hospital , 101 Daehak-ro, Jongno-gu, Seoul 03080
1 shared publication - Jang Young Kim
Division of Cardiology, Department of Internal Medicine, Wonju College of Medicine, Yonsei University, Wonju, Korea
1 shared publication
Latest Publications
- Open Access
- 24 April 2026
- Published by JMIR Publications Inc. in JMIR Medical Informatics
- Vol. 14 (1) , e83127
Deep Learning Model Using Transfer Learning for Detecting Left Ventricular Systolic Dysfunction: Retrospective Algorithm Development and Validation Study
Background: Artificial intelligence–augmented electrocardiogram (AI-ECG) models for detecting left ventricular systolic dysfunction (LVSD) often exhibit degraded performance in patients with comorbidities. Objective: This study aimed to introduce and validate a recalibration method using longitudinal patient data to enhance prediction accuracy and simulate its clinical utility for ongoing monitoring. Methods: We conducted a multicenter, retrospective cohort study using data from 2 hospitals in Korea. A dataset of paired transthoracic echocardiograms (TTEs) and electrocardiograms (ECGs) matched within a 2-week interval was constructed, separating pairs into baseline (first for each patient) and follow-up assessments. In addition to conventional supervised learning, we developed a patient-wise recalibration strategy that incorporated historical left ventricular ejection fraction measurements and prior AI-ECG outputs to adjust for future predictions, thus empirically mitigating confounding effects. Pretraining was also implemented to enhance the model’s performance. Results: The recalibrated 12-lead DeepECG LVSD model achieved an area under the receiver operating curve of 0.956 (95% CI 0.946‐0.965) for internal validation and 0.940 (95% CI 0.936‐0.945) for external validation of follow-up TTE-ECG pairs. The uncalibrated 12-lead DeepECG LVSD model also showed modest performance, with an area under the receiver operating curve of 0.953 (95% CI 0.941‐0.965) in the internal validation and 0.947 (95% CI 0.943‐0.951) in the external validation when tested on baseline TTE-ECG pairs. Recalibration yielded statistically significant improvements in the 12-lead DeepECG LVSD models ( P <.001), with enhanced and more balanced performance across all clinical subgroups. Conclusions: Patient-wise recalibration improved accuracy and consistency across various comorbidities by mitigating performance degradation and bias. This broadens the application of AI-ECG for LVSD detection from low-risk screening to high-risk longitudinal monitoring.
- 24 April 2026
- Published by JMIR Publications Inc. in JMIR Medical Informatics
- Vol. 14 (1) , e83127
Open AccessDeep Learning Model Using Transfer Learning for Detecting Left Ventricular Systolic Dysfunction: Retrospective Algorithm Development and Validation Study
Background: Artificial intelligence–augmented electrocardiogram (AI-ECG) models for detecting left ventricular systolic dysfunction (LVSD) often exhibit degraded performance in patients with comorbidities. Objective: This study aimed to introduce and validate a recalibration method using longitudinal patient data to enhance prediction accuracy and simulate its clinical utility for ongoing monitoring. Methods: We conducted a multicenter, retrospective cohort study using data from 2 hospitals in Korea. A dataset of paired transthoracic echocardiograms (TTEs) and electrocardiograms (ECGs) matched within a 2-week interval was constructed, separating pairs into baseline (first for each patient) and follow-up assessments. In addition to conventional supervised learning, we developed a patient-wise recalibration strategy that incorporated historical left ventricular ejection fraction measurements and prior AI-ECG outputs to adjust for future predictions, thus empirically mitigating confounding effects. Pretraining was also implemented to enhance the model’s performance. Results: The recalibrated 12-lead DeepECG LVSD model achieved an area under the receiver operating curve of 0.956 (95% CI 0.946‐0.965) for internal validation and 0.940 (95% CI 0.936‐0.945) for external validation of follow-up TTE-ECG pairs. The uncalibrated 12-lead DeepECG LVSD model also showed modest performance, with an area under the receiver operating curve of 0.953 (95% CI 0.941‐0.965) in the internal validation and 0.947 (95% CI 0.943‐0.951) in the external validation when tested on baseline TTE-ECG pairs. Recalibration yielded statistically significant improvements in the 12-lead DeepECG LVSD models ( P <.001), with enhanced and more balanced performance across all clinical subgroups. Conclusions: Patient-wise recalibration improved accuracy and consistency across various comorbidities by mitigating performance degradation and bias. This broadens the application of AI-ECG for LVSD detection from low-risk screening to high-risk longitudinal monitoring.
- 18 December 2020
- Published by Oxford University Press (OUP) in European Journal of Preventive Cardiology
- Vol. 28 (18) , 2021-2029
Differential association of metabolic syndrome and low-density lipoprotein cholesterol with incident cardiovascular disease according to sex among Koreans: a national population-based study
To investigate sex differences in the association of metabolic syndrome (MetS) and/or low-density lipoprotein cholesterol (LDL-C) with the incidence of cardiovascular and cerebrovascular disease (CCVD). A total of 4 702 458 individuals, aged between 40 and 70, without a previous diagnosis of CCVD, underwent at least two health screenings between 2009 and 2011. Of them, 4 193 878 individuals (48.6% women) fulfilled the study requirements. The main outcome measured was the incidence of CCVD. By the end of 2017, 68 921 CCVD events occurred. Men in high LDL-C only, MetS only, and both MetS and high LDL-C groups had higher risks of CCVD. Women in MetS only and both MetS and high LDL-C groups, but not those in high LDL-C only group, had higher risks of CCVD than those in the reference group. The effect of the interaction between the presence of MetS and high LDL-C levels on the primary outcome was found among women (P for interaction 0.016) but not among men (P for interaction 0.897). A combination of MetS and LDL-C > 3.4 mmol/L increased the risk of CCVD as compared to MetS or LDL-C > 3.4 mmol/L alone in both men and women. Metabolic syndrome confers an increased risk of CCVD irrespective of sexes; LDL-C > 3.4 mmol/L alone has a greater influence on CCVD occurrence in men than in women. Metabolic syndrome and high LDL-C beget a synergistically detrimental impact on the incidence of CCVD in both men and women. Treatment of dyslipidaemia and metabolic syndrome should be tailored according to patient characteristics.
- 18 December 2020
- Published by Oxford University Press (OUP) in European Journal of Preventive Cardiology
- Vol. 28 (18) , 2021-2029
Differential association of metabolic syndrome and low-density lipoprotein cholesterol with incident cardiovascular disease according to sex among Koreans: a national population-based study
To investigate sex differences in the association of metabolic syndrome (MetS) and/or low-density lipoprotein cholesterol (LDL-C) with the incidence of cardiovascular and cerebrovascular disease (CCVD). A total of 4 702 458 individuals, aged between 40 and 70, without a previous diagnosis of CCVD, underwent at least two health screenings between 2009 and 2011. Of them, 4 193 878 individuals (48.6% women) fulfilled the study requirements. The main outcome measured was the incidence of CCVD. By the end of 2017, 68 921 CCVD events occurred. Men in high LDL-C only, MetS only, and both MetS and high LDL-C groups had higher risks of CCVD. Women in MetS only and both MetS and high LDL-C groups, but not those in high LDL-C only group, had higher risks of CCVD than those in the reference group. The effect of the interaction between the presence of MetS and high LDL-C levels on the primary outcome was found among women (P for interaction 0.016) but not among men (P for interaction 0.897). A combination of MetS and LDL-C > 3.4 mmol/L increased the risk of CCVD as compared to MetS or LDL-C > 3.4 mmol/L alone in both men and women. Metabolic syndrome confers an increased risk of CCVD irrespective of sexes; LDL-C > 3.4 mmol/L alone has a greater influence on CCVD occurrence in men than in women. Metabolic syndrome and high LDL-C beget a synergistically detrimental impact on the incidence of CCVD in both men and women. Treatment of dyslipidaemia and metabolic syndrome should be tailored according to patient characteristics.
- Open Access
- 1 January 2019
- Published by XMLink in Korean Circulation Journal
- Vol. 49 (11) , 1033-1034
Dose Coronary Angiography Suffice for Assessment of Intermediate Coronary Stenosis?
- 1 January 2019
- Published by XMLink in Korean Circulation Journal
- Vol. 49 (11) , 1033-1034
Open AccessDose Coronary Angiography Suffice for Assessment of Intermediate Coronary Stenosis?