Yeon-Jik Choi
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
Yeon-Jik Choi has a total of 50 co-authors. Here are the top co-authors by number of shared publications:
- Hun-Jun Park
Department of biomedicine and health sciences, The Catholic University of Korea, Seoul 06591, Republic of Korea
2 shared publications - Junghoon Lee
Division of Cardiology, Department of Internal Medicine, Eunpyeong St. Mary’s Hospital, College of Medicine, The Catholic University of Korea, Seoul 06591, Republic of Korea
2 shared publications - Kiwon Ban
Department of Biomedical Sciences, City University of Hong Kong, Kowloon, China
2 shared publications - Myeong-Ki Hong
Division of Cardiology, Severance Cardiovascular Hospital, Yonsei University College of Medicine, Seoul, Korea
2 shared publications - Osung Kwon
Division of Cardiology, Department of Internal Medicine, Eunpyeong St. Mary’s Hospital, College of Medicine, The Catholic University of Korea, Seoul, Korea
2 shared publications - Suk Min Seo
Division of Cardiology, Department of Internal Medicine, Eunpyeong St. Mary’s Hospital, The Catholic University, Seoul, Korea
2 shared publications
Latest Publications
- Open Access
- 1 January 2027
- Published by XMLink in Korean Circulation Journal
- Vol. 57
Outcomes of Second Valve Implantation as a Bail-Out Strategy for Acute Valve Migration During Transcatheter Aortic Valve Implantation: A Retrospective Multi-Center Study
Kim SO, et al. Korean Circ J. 2027 ;57:e72. https://doi.org/10.4070/kcj.2026.0218
- 1 January 2027
- Published by XMLink in Korean Circulation Journal
- Vol. 57
Open AccessOutcomes of Second Valve Implantation as a Bail-Out Strategy for Acute Valve Migration During Transcatheter Aortic Valve Implantation: A Retrospective Multi-Center Study
Kim SO, et al. Korean Circ J. 2027 ;57:e72. https://doi.org/10.4070/kcj.2026.0218
- Open Access
- 16 November 2026
- Published by MDPI AG in Diagnostics
- Vol. 16 (22) , 3812
Diagnostic Performance of 96-Channel Magnetocardiography for Angiographically Significant Coronary Stenosis in Patients with Chest Pain and Clinically Suspected Angina: A Two-Center Post Hoc Analysis
Background/Objectives: We evaluated the diagnostic performance of 96-channel magnetocardiography (MCG) for angiographically significant coronary stenosis in patients with chest pain and clinically suspected angina. Methods: This two-center post hoc analysis included 137 participants with paired resting (Rest) and post-exercise recovery recordings. The anatomical reference required visually assessed stenosis ≥70% in a vessel with a reference diameter ≥ 2.5 mm. A predefined Total Score ≥ 2 indicated a positive MCG test. Results: The cohort included 37 reference-positive and 100 reference-negative participants. Rest and post-exercise AUCs were 0.710 (95% CI 0.612–0.801) and 0.815 (0.730–0.889), respectively. The direct paired AUC difference was 0.106 (95% CI 0.004–0.207; paired DeLong p = 0.041). A separate exploratory fitted-model comparison yielded an AUC difference of 0.097 (95% CI 0.031–0.214). At Total Score ≥ 2, Rest sensitivity and specificity were 64.9% and 74.0%. Post-exercise sensitivity, specificity, positive predictive value, and negative predictive value were 83.8% (95% CI 68.9–92.3), 77.0% (67.8–84.2), 57.4% (44.2–69.7), and 92.8% (85.1–96.6), respectively. Post-exercise MCG produced six false-negative and 23 false-positive results. Paired sensitivity and specificity differences were not statistically significant. Conclusions: In this selected cohort, post-exercise MCG showed higher discrimination than Rest MCG for the study-defined anatomical target. The findings support further evaluation as an adjunctive electrophysiological test; they do not establish physiological ischemia detection or justify deferring indicated anatomical assessment.
- 16 November 2026
- Published by MDPI AG in Diagnostics
- Vol. 16 (22) , 3812
Open AccessDiagnostic Performance of 96-Channel Magnetocardiography for Angiographically Significant Coronary Stenosis in Patients with Chest Pain and Clinically Suspected Angina: A Two-Center Post Hoc Analysis
Background/Objectives: We evaluated the diagnostic performance of 96-channel magnetocardiography (MCG) for angiographically significant coronary stenosis in patients with chest pain and clinically suspected angina. Methods: This two-center post hoc analysis included 137 participants with paired resting (Rest) and post-exercise recovery recordings. The anatomical reference required visually assessed stenosis ≥70% in a vessel with a reference diameter ≥ 2.5 mm. A predefined Total Score ≥ 2 indicated a positive MCG test. Results: The cohort included 37 reference-positive and 100 reference-negative participants. Rest and post-exercise AUCs were 0.710 (95% CI 0.612–0.801) and 0.815 (0.730–0.889), respectively. The direct paired AUC difference was 0.106 (95% CI 0.004–0.207; paired DeLong p = 0.041). A separate exploratory fitted-model comparison yielded an AUC difference of 0.097 (95% CI 0.031–0.214). At Total Score ≥ 2, Rest sensitivity and specificity were 64.9% and 74.0%. Post-exercise sensitivity, specificity, positive predictive value, and negative predictive value were 83.8% (95% CI 68.9–92.3), 77.0% (67.8–84.2), 57.4% (44.2–69.7), and 92.8% (85.1–96.6), respectively. Post-exercise MCG produced six false-negative and 23 false-positive results. Paired sensitivity and specificity differences were not statistically significant. Conclusions: In this selected cohort, post-exercise MCG showed higher discrimination than Rest MCG for the study-defined anatomical target. The findings support further evaluation as an adjunctive electrophysiological test; they do not establish physiological ischemia detection or justify deferring indicated anatomical assessment.
- Open Access
- 7 May 2026
- Published by MDPI AG in Diagnostics
- Vol. 16 (10) , 1422
A Transformer-Based Machine Learning Framework for Risk Stratification of Left Bundle Branch Block After Transcatheter Aortic Valve Replacement
Background/Objectives: Left bundle branch block (LBBB) remains a common complication after transcatheter aortic valve replacement (TAVR) and is associated with adverse clinical outcomes. However, accurate prediction of LBBB remains challenging due to the complex interactions among the anatomical, procedural, and clinical factors. This study aimed to develop a machine learning (ML)-based framework to predict LBBB and identify relevant contributing features. Methods: In this multicenter retrospective study, we analyzed 242 patients undergoing TAVR across three institutions. A machine learning framework incorporating transformer-based feature selection and conventional classifiers was developed. Model performance was evaluated using accuracy, precision, recall, F1-score, and area under the receiver operating characteristic curve (AUC). Internal validation was performed using bootstrap resampling. Results: The gradient boosting model using ML-derived features demonstrated the most balanced performance, achieving an accuracy of 78.05% and an F1-score of 50.46%, with modest discrimination (AUC 0.61). The ML-based approach identified clinically relevant features, including coronary height, left ventricular outflow tract/annulus ratio, and prosthetic valve size, as well as additional variables not emphasized in conventional analyses. Conclusions: ML-based feature selection can capture complex feature interactions beyond traditional statistical approaches and provide clinically meaningful insights into risk stratification for LBBB after TAVR. Although predictive performance was modest, this approach highlights the potential of ML for improved risk stratification and individualized procedural planning. Further large-scale external validation is warranted.
- 7 May 2026
- Published by MDPI AG in Diagnostics
- Vol. 16 (10) , 1422
Open AccessA Transformer-Based Machine Learning Framework for Risk Stratification of Left Bundle Branch Block After Transcatheter Aortic Valve Replacement
Background/Objectives: Left bundle branch block (LBBB) remains a common complication after transcatheter aortic valve replacement (TAVR) and is associated with adverse clinical outcomes. However, accurate prediction of LBBB remains challenging due to the complex interactions among the anatomical, procedural, and clinical factors. This study aimed to develop a machine learning (ML)-based framework to predict LBBB and identify relevant contributing features. Methods: In this multicenter retrospective study, we analyzed 242 patients undergoing TAVR across three institutions. A machine learning framework incorporating transformer-based feature selection and conventional classifiers was developed. Model performance was evaluated using accuracy, precision, recall, F1-score, and area under the receiver operating characteristic curve (AUC). Internal validation was performed using bootstrap resampling. Results: The gradient boosting model using ML-derived features demonstrated the most balanced performance, achieving an accuracy of 78.05% and an F1-score of 50.46%, with modest discrimination (AUC 0.61). The ML-based approach identified clinically relevant features, including coronary height, left ventricular outflow tract/annulus ratio, and prosthetic valve size, as well as additional variables not emphasized in conventional analyses. Conclusions: ML-based feature selection can capture complex feature interactions beyond traditional statistical approaches and provide clinically meaningful insights into risk stratification for LBBB after TAVR. Although predictive performance was modest, this approach highlights the potential of ML for improved risk stratification and individualized procedural planning. Further large-scale external validation is warranted.
- Open Access
- 1 January 2023
- Published by XMLink in Korean Circulation Journal
- Vol. 53 (8) , 499-518
The Gut-Heart Axis: Updated Review for The Roles of Microbiome in Cardiovascular Health
Bui TV, et al. Korean Circ J. 2023 Jun;53:e51. https://doi.org/10.4070/kcj.2023.0048
- 1 January 2023
- Published by XMLink in Korean Circulation Journal
- Vol. 53 (8) , 499-518
Open AccessThe Gut-Heart Axis: Updated Review for The Roles of Microbiome in Cardiovascular Health
Bui TV, et al. Korean Circ J. 2023 Jun;53:e51. https://doi.org/10.4070/kcj.2023.0048
- Open Access
- 1 January 2023
- Published by XMLink in Korean Circulation Journal
- Vol. 53 (6) , 367-386
Are There Hopeful Therapeutic Strategies to Regenerate the Infarcted Hearts?
Korean Circulation Journal 대한심장학회지 순환기 Oh GC, et al. Korean Circ J. 2023 May;53:e44. https://doi.org/10.4070/kcj.2023.0098
- 1 January 2023
- Published by XMLink in Korean Circulation Journal
- Vol. 53 (6) , 367-386
Open AccessAre There Hopeful Therapeutic Strategies to Regenerate the Infarcted Hearts?
Korean Circulation Journal 대한심장학회지 순환기 Oh GC, et al. Korean Circ J. 2023 May;53:e44. https://doi.org/10.4070/kcj.2023.0098
- Open Access
- 1 January 2018
- Published by Korean Society of Lipidology and Atherosclerosis in Journal of Lipid and Atherosclerosis
- Vol. 7 (1) , 62-67
Contrast-free (Zero-contrast) TAVR for Severe Aortic Stenosis in Patient with Chronic Kidney Disease
Choi YJ, et al. J Lipid Atheroscler. 2018 Jun;7(1):62-67. https://doi.org/10.12997/jla.2018.7.1.62
- 1 January 2018
- Published by Korean Society of Lipidology and Atherosclerosis in Journal of Lipid and Atherosclerosis
- Vol. 7 (1) , 62-67
Open AccessContrast-free (Zero-contrast) TAVR for Severe Aortic Stenosis in Patient with Chronic Kidney Disease
Choi YJ, et al. J Lipid Atheroscler. 2018 Jun;7(1):62-67. https://doi.org/10.12997/jla.2018.7.1.62