Search

Your search keyword '"Cha, Myung‐Jin"' showing total 495 results
Start Over Author "Cha, Myung‐Jin"
495 results on '"Cha, Myung‐Jin"'

3. Deep learning based ECG segmentation for delineation of diverse arrhythmias

Author

Joung, Chankyu, Kim, Mijin, Paik, Taejin, Kong, Seong-Ho, Oh, Seung-Young, Jeon, Won Kyeong, Jeon, Jae-hu, Hong, Joong-Sik, Kim, Wan-Joong, Kook, Woong, Cha, Myung-Jin, and van Koert, Otto

Subjects
Computer Science - Machine Learning, Electrical Engineering and Systems Science - Signal Processing
Abstract

Accurate delineation of key waveforms in an ECG is a critical step in extracting relevant features to support the diagnosis and treatment of heart conditions. Although deep learning based methods using segmentation models to locate P, QRS, and T waves have shown promising results, their ability to handle arrhythmias has not been studied in any detail. In this paper we investigate the effect of arrhythmias on delineation quality and develop strategies to improve performance in such cases. We introduce a U-Net-like segmentation model for ECG delineation with a particular focus on diverse arrhythmias. This is followed by a post-processing algorithm which removes noise and automatically determines the boundaries of P, QRS, and T waves. Our model has been trained on a diverse dataset and evaluated against the LUDB and QTDB datasets to show strong performance, with F1-scores exceeding 99% for QRS and T waves, and over 97% for P waves in the LUDB dataset. Furthermore, we assess various models across a wide array of arrhythmias and observe that models with a strong performance on standard benchmarks may still perform poorly on arrhythmias that are underrepresented in these benchmarks, such as tachycardias. We propose solutions to address this discrepancy.

Published
2023
Full Text
View/download PDF

16. Association between body mass index and results of cryoballoon ablation in Korean patients with atrial fibrillation: an analysis from Korean Heart Rhythm Society Cryoablation registry

Author

Ahn, Hyun Jin, primary, Oh, Il-Young, additional, Choi, JeongMin, additional, Lee, Kyung-Yeon, additional, Ahn, Hyo-Jeong, additional, Kwon, Soonil, additional, Choi, Eue-Keun, additional, Oh, Seil, additional, Kim, Ju Youn, additional, Cha, Myung-Jin, additional, Kwon, Chang Hee, additional, Lee, Sung Ho, additional, Park, Junbeom, additional, Kim, Ki-Hun, additional, Yang, Pil-Sung, additional, Kim, Jun-Hyung, additional, Shim, Jaemin, additional, Lim, Hong Euy, additional, and Lee, So-Ryoung, additional

Published
2024
Full Text
View/download PDF

19. Long‐term clinical impact of early recurrence of atrial tachyarrhythmia after cryoballoon ablation in patients with atrial fibrillation.

Author

Park, Jinsun, Cha, Myung‐Jin, Kwon, Chang Hee, Cho, Min Soo, Nam, Gi‐Byoung, Oh, Il‐Young, Lee, So‐Ryoung, Kim, Ju Youn, Lee, Sung Ho, Park, Junbeom, Kim, Ki‐Hun, Yang, Pil‐Sung, Kim, Jun Hyung, Shim, Jaemin, and Lim, Hong Euy

Subjects
*RISK assessment, *HEART atrium, *RESEARCH funding, *CRYOSURGERY, *TREATMENT effectiveness, *REPORTING of diseases, *DESCRIPTIVE statistics, *MULTIVARIATE analysis, *ATRIAL fibrillation, *DISEASE relapse, *TACHYCARDIA, *CONFIDENCE intervals, *TIME, *PATIENT aftercare, *DISEASE risk factors
Abstract

Introduction: The impact of early recurrence of atrial tachyarrhythmia (ERAT) within the 90‐day blanking period on long‐term outcomes in atrial fibrillation (AF) patients undergoing cryoballoon ablation (CBA) is controversial. This study aimed to assess the relationship between ERAT and late recurrence of atrial tachyarrhythmia (LRAT) post‐CBA. Methods: Utilizing data from a multicenter registry in Korea (May 2018 to June 2022), we analyzed the presence and timing of ERAT (<30, 30–60, and 60–90 days) and its association with LRAT risk after CBA. LRAT was defined as any recurrence of AF, atrial flutter, or atrial tachycardia lasting more than 30 s beyond the 90 days. Results: Out of 2636 patients, 745 (28.2%) experienced ERAT post‐CBA. Over an average follow‐up period of 21.2 ± 10.3 months, LRAT was observed in 874 (33.1%) patients. Patients with ERAT had significantly lower 1‐year LRAT freedom compared to those without ERAT (42.6% vs. 85.5%, p <.001). Multivariate analysis identified ERAT as a potential predictor of LRAT, with a hazard ratio (HR) of 3.98 (95% confidence interval [CI], 3.47–4.57). Significant associations were noted across all examined time frames (HR, 3.84; 95% CI, 3.32–4.45 in <30 days, HR, 5.53; 95% CI, 4.13–7.42 in 30–60 days, and HR, 4.29; 95% CI, 3.12–5.89 in 60–90 days). This finding was consistently observed across all types of AF. Conclusion: ERAT during the 90‐day blanking period strongly predicts LRAT in AF patients undergoing CBA, indicating a need to reconsider the clinical significance of this period. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

23. Stroke and Systemic Embolism and Other Adverse Outcomes of Heart Failure With Preserved and Reduced Ejection Fraction in Patients With Atrial Fibrillation (from the COmparison study of Drugs for symptom control and complication prEvention of Atrial Fibrillation [CODE-AF])

Author

Chung, Seyong, Kim, Tae-Hoon, Uhm, Jae-Sun, Cha, Myung-Jin, Lee, Jung-Myung, Park, Junbeom, Park, Jin-Kyu, Kang, Ki-Woon, Kim, Jun, Park, Hyung Wook, Choi, Eue-Keun, Kim, Jin-Bae, Kim, Chang-Soo, Lee, Young Soo, Shim, Jaemin, and Joung, Boyoung

Published
2020
Full Text
View/download PDF

35. Deep learning based ECG segmentation for delineation of diverse arrhythmias.

Author

Joung, Chankyu, Kim, Mijin, Paik, Taejin, Kong, Seong-Ho, Oh, Seung-Young, Jeon, Won Kyeong, Jeon, Jae-hu, Hong, Joong-Sik, Kim, Wan-Joong, Kook, Woong, Cha, Myung-Jin, and van Koert, Otto

Subjects
DEEP learning, ARRHYTHMIA, ELECTROCARDIOGRAPHY, PERFORMANCE standards
Abstract

Accurate delineation of key waveforms in an ECG is a critical step in extracting relevant features to support the diagnosis and treatment of heart conditions. Although deep learning based methods using segmentation models to locate P, QRS, and T waves have shown promising results, their ability to handle arrhythmias has not been studied in any detail. In this paper we investigate the effect of arrhythmias on delineation quality and develop strategies to improve performance in such cases. We introduce a U-Net-like segmentation model for ECG delineation with a particular focus on diverse arrhythmias. This is followed by a post-processing algorithm which removes noise and automatically determines the boundaries of P, QRS, and T waves. Our model has been trained on a diverse dataset and evaluated against the LUDB and QTDB datasets to show strong performance, with F1-scores exceeding 99% for QRS and T waves, and over 97% for P waves in the LUDB dataset. Furthermore, we assess various models across a wide array of arrhythmias and observe that models with a strong performance on standard benchmarks may still perform poorly on arrhythmias that are underrepresented in these benchmarks, such as tachycardias. We propose solutions to address this discrepancy. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

36. Association between body mass index and results of cryoballoon ablation in Korean patients with atrial fibrillation: an analysis from the Korean Heart Rhythm Society Cryoablation registry.

Author

Ahn, Hyun Jin, Oh, Il-Young, Choi, JungMin, Lee, Kyung-Yeon, Ahn, Hyo-Jeong, Kwon, Soonil, Choi, Eue-Keun, Oh, Seil, Kim, Ju Youn, Cha, Myung-Jin, Kwon, Chang Hee, Lee, Sung Ho, Park, Junbeom, Kim, Ki-Hun, Yang, Pil-Sung, Kim, Jun-Hyung, Shim, Jaemin, Lim, Hong Euy, and Lee, So-Ryoung

Abstract

Aims Pulmonary vein isolation using cryoablation is effective and safe in patients with atrial fibrillation (AF). Although both obesity and underweight are associated with a higher risk for incident AF, there is limited data on the efficacy and safety following cryoablation according to body mass index (BMI) especially in Asians. Methods and results Using the Korean Heart Rhythm Society Cryoablation registry, a multicentre registry of 12 tertiary hospitals, we analysed AF recurrence and procedure-related complications after cryoablation by BMI (kg/m2) groups (BMI < 18.5, underweight, UW; 18.5–23, normal, NW; 23–25, overweight, OW; 25–30, obese Ⅰ, OⅠ; ≥30, obese Ⅱ, OⅡ). A total of 2648 patients were included (median age 62.0 years; 76.7% men; 55.6% non-paroxysmal AF). Patients were categorized by BMI groups: 0.9% UW, 18.7% NW, 24.8% OW, 46.1% OI, and 9.4% OII. Underweight patients were the oldest and had least percentage of non-paroxysmal AF (33.3%). During a median follow-up of 1.7 years, atrial arrhythmia recurred in 874 (33.0%) patients (incidence rate, 18.9 per 100 person-years). After multivariable adjustment, the risk of AF recurrence was higher in UW group compared with NW group (adjusted hazard ratio, 95% confidence interval; 2.55, 1.18–5.50, P = 0.02). Procedure-related complications occurred in 123 (4.7%) patients, and the risk was higher for UW patients (odds ratio, 95% confidence interval; 2.90, 0.94–8.99, P = 0.07), mainly due to transient phrenic nerve palsy. Conclusion Underweight patients showed a higher risk of AF recurrence after cryoablation compared with NW patients. Also, careful attention is needed on the occurrence of phrenic nerve palsy in UW patients. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

37. Association of typical atrial flutter and cavotricuspid isthmus ablation on clinical recurrence after cryoballoon ablation for atrial fibrillation

Author

Jeong, Joo Hee, primary, Lee, Hyoung Seok, additional, Choi, Yun Young, additional, Kim, Yun Gi, additional, Choi, Jong-Il, additional, Kim, Young-Hoon, additional, Lim, Hong Euy, additional, Oh, Il-Young, additional, Cha, Myung-Jin, additional, Lee, So-Ryoung, additional, Kim, Ju Youn, additional, Kwon, Chang Hee, additional, Lee, Sung Ho, additional, Park, Junbeom, additional, Kim, Ki-Hun, additional, Yang, Pil-Sung, additional, Kim, Jun-Hyung, additional, and Shim, Jaemin, additional

Published
2023
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results