Hong-Mi Choi

Hong-Mi Choi

Auto-generated profile, based on publicly available information

Hong-Mi Choi

Department of Cardiology, Cardiovascular Center, Seoul National University Bundang Hospital, Seongnam, Korea

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2024 in Korean Circulation Journal
Verified
Journal Article
Open access
PDF file
YJYeonggul Jang
Yeonggul Jang
HCHyejung Choi
Hyejung Choi
YYYeonyee E. Yoon
Yeonyee E. Yoon
JJJaeik Jeon
Jaeik Jeon
HKHyejin Kim
Hyejin Kim
HCHyuk-Jae Chang
Hyuk-Jae Chang
Jang Y, et al. Korean Circ J. 2024 Aug;54:e103. https://doi.org/10.4070/kcj.2024.0060

1 May 2025 in Circulation: Cardiovascular Imaging
Verified
Journal Article
Closed access
IMInki Moon
Inki Moon
JLJina Lee
Jina Lee
SLSeung-Ah Lee
Seung-Ah Lee
DJDawun Jeong
Dawun Jeong
JJJaeik Jeon
Jaeik Jeon
HCHyuk-Jae Chang
Hyuk-Jae Chang
BACKGROUND: While echocardiography is pivotal for detecting left ventricular hypertrophy (LVH), it struggles with etiology differentiation. To enhance LVH assessment, we aimed to develop an artificial intelligence algorithm using echocardiography-based radiomics. This algorithm is designed to detect LVH and differentiate its common etiologies, such as hypertrophic cardiomyopathy (HCM), cardiac amyloidosis (CA), and hypertensive heart disease (HHD), based on echocardiographic images. METHODS: The developmental data sets from multiple medical centers included 867 subjects, with an independent external test set from a single tertiary medical center containing 619 subjects. Radiomic feature analysis was conducted on 4 echocardiographic views, extracting both conventional and harmonization-driven myocardial textures along with myocardial geographic features. Then, we developed classification models for each condition. Variable contributions were evaluated using Shapley Additive Explanations analysis. RESULTS: The radiomics-based LightGBM model, selected from internal validation, maintained strong performance in the external test set (area under the curve of 0.96 for HCM, 0.89 for CA, and 0.86 for HHD). Compared with the logistic regression model using conventional echocardiographic parameters (left ventricular ejection fraction, left ventricular mass index, left atrial volume index, and E/e′), the final model demonstrated superior sensitivity (0.89 versus 0.80 for HCM, 0.80 versus 0.80 for CA, and 0.75 versus 0.33 for HHD) and F1-score (0.87 versus 0.57 for HCM, 0.84 versus 0.72 for CA, and 0.82 versus 0.50 for HHD). Feature analysis highlighted that harmonization-driven textures played a key role in differentiating HCM, while conventional textures and myocardial thickness were influential in differentiating CA and HHD. CONCLUSIONS: This study confirms that artificial intelligence-enhanced echocardiography-based radiomics effectively differentiate the etiology of LVH, highlighting the potential of artificial intelligence-driven texture and geographic analysis in LVH evaluation.

4 April 2022 in International Journal of Heart Failure
Verified
Journal Article
Open access
PDF file
IHIn-Chang Hwang
In-Chang Hwang
HCHong-Mi Choi
Hong-Mi Choi
YYYeonyee E. Yoon
Yeonyee E. Yoon
JPJin Joo Park
Jin Joo Park
JPJun-Bean Park
Jun-Bean Park
GCGoo-Yeong Cho
Goo-Yeong Cho
Hwang IC, et al. Int J Heart Fail. 2022 Apr;4:e10. https://doi.org/10.36628/ijhf.2022.0007

1 January 2025 in Korean Circulation Journal
Verified
Journal Article
Open access
PDF file
JLJaehyun Lim
Jaehyun Lim
JCJae Yeong Cho
Jae Yeong Cho
SKSoongu Kwak
Soongu Kwak
CPChan-Soon Park
Chan-Soon Park
JPJiesuck Park
Jiesuck Park
HKHyung-Kwan Kim
Hyung-Kwan Kim
Lim J, et al. Korean Circ J. 2025 Mar;55:e72. https://doi.org/10.4070/kcj.2024.0443

25 October 2024 in Journal of the American Heart Association
Verified
Journal Article
Open access
CPChan Soon Park
Chan Soon Park
JPJiesuck Park
Jiesuck Park
NBNan Young Bae
Nan Young Bae
SKSoongu Kwak
Soongu Kwak
HCHong‐Mi Choi
Hong‐Mi Choi
HKHyung-Kwan Kim
Hyung-Kwan Kim
Background: Optimal medical treatment can lead to improvement in left ventricular ejection fraction (LVEF) in patients with heart failure with reduced EF (HFrEF). We investigated the characteristics, predictors, and outcomes of HFrEF according to the 1‐year LVEF following angiotensin receptor–neprilysin inhibitors therapy (ARNI). Methods and Results: Using the STRATS‐HF‐ARNI (Strain for Risk Assessment and Therapeutic Strategies in Patients With Heart Failure Treated With Angiotensin Receptor‐Neprilysin Inhibitor) registry, we identified 1074 patients with HFrEF who took ARNI and underwent baseline and 1‐year echocardiography. Patients were classified as HF with improved ejection fraction (HFimpEF) and persistent HFrEF (perHFrEF) (1‐year LVEF >40% and ≤40%). The primary and secondary outcomes were all‐cause and cardiac mortality from the 1‐year follow‐up. Among 1074 included patients, 498 (46.4%) had HFimpEF, and 576 (53.6%) had perHFrEF. Older age, male sex, and large LV end‐diastolic volumes were positive predictors of perHFrEF, whereas atrial fibrillation and high systolic blood pressure were identified as inverse predictors. Patients with HFimpEF showed lower all‐cause and cardiac mortality rates (both log‐rank P <0.001). In the multivariable analysis, perHFrEF (hazard ratio, 2.402 [95% CI, 1.251–4.610]; P =0.008) was an independent predictor of poor outcomes. The risk of all‐cause mortality decreased as the 1‐year LVEF increased up to 40%; however, no additional risk reduction was observed beyond 40%. Compared with patients taking renin‐angiotensin‐aldosterone system inhibitors in the STRATS‐AHF (Strain for Risk Assessment and Therapeutic Strategies in Patients With Acute Heart Failure) registry, those in the STRATS‐HF‐ARNI registry demonstrated better outcomes in both HFimpEF and perHFrEF. Conclusions: Patients with HFimpEF had better prognosis than those with perHFrEF, and ARNI treatment in HFrEF could be more beneficial than renin‐angiotensin‐aldosterone system inhibitors for both HFimpEF and perHFrEF. Registration: URL: https://www.who.int/clinical‐trials‐registry‐platform ; Unique identifier: KCT0008098.

1 January 2021 in Journal of Korean Medical Science
Verified
Journal Article
Open access
PDF file
WLWonjae Lee
Wonjae Lee
WCWonsuk Choi
Wonsuk Choi
SKSi-Hyuck Kang
Si-Hyuck Kang
IHIn-Chang Hwang
In-Chang Hwang
HCHong-Mi Choi
Hong-Mi Choi
GCGoo-Yeong Cho
Goo-Yeong Cho
Lee W, et al. J Korean Med Sci. 2021 Jan;36(6):e47. https://doi.org/10.3346/jkms.2021.36.e47