Park, Hyung‐Bok

BACKGROUND: Accurate assessment of left ventricular outflow tract (LVOT) gradients is critical for hypertrophic cardiomyopathy management, yet Doppler-based measurements are technically demanding and require expertise. The objective of this work was to develop a multi-view deep learning model capable of classifying LVOT obstruction (>20 mm Hg) using routine 2-dimensional echocardiographic windows without reliance on Doppler imaging. METHODS: We trained and externally validated a cross-attention-based video-to-video fusion framework that integrated EchoPrime-derived video representations from 3 standard transthoracic echocardiographic views to classify LVOT gradients. RESULTS: Training was performed on a derivation cohort (N=1833) from a tertiary care system in the United States, with model performance evaluated on an internally held-out test set (N=275) and a Korean external validation cohort (N=46). Single-view baselines showed limited discrimination (external area under the receiver operating curves, 0.47–0.70). Conversely, the domain-specific foundational model (EchoPrime) achieved superior single-view performance (area under the receiver operating curves, 0.75–0.80 internal; 0.79–0.83 external), highlighting the importance of echo-specific pretraining and temporal modeling. The proposed multi-view fusion further enhanced predictive performance, with the late fusion model reaching an area under the receiver operating curve of 0.84 on the external cohort with significant population-shift. CONCLUSIONS: These results suggest LVOT physiology is encoded in routine 2-dimensional imaging and can be leveraged for clinically relevant gradient classification without Doppler input. The proposed artificial intelligence-guided strategy demonstrates substantial cost savings compared with the screen-all approach. By integrating complementary spatial-temporal information across multiple views, our approach generalizes robustly across populations and may enable real-time decision support, extend LVOT assessment to portable or resource-limited settings, and complement Doppler-based evaluation for longitudinal hypertrophic cardiomyopathy management.

Abstract Background Accurate assessment of left ventricular outflow tract (LVOT) gradients is critical for hypertrophic cardiomyopathy (HCM) management, yet Doppler-based measurements are technically demanding and require expertise. Objective To develop a multi-view deep learning model capable of classifying LVOT obstruction (> 20mmHg) using routine 2D echocardiographic windows without reliance on Doppler imaging. Methods We trained and externally validated a cross-attention-based video-to-video fusion framework that integrated EchoPrime-derived video representations from three standard transthoracic echocardiographic views to classify LVOT gradients. Results Training was performed on a derivation cohort (N = 1833) from a tertiary care system in the United States, with model performance evaluated on an internal held-out test set (N = 275) and a Korean external validation cohort (N = 46). Single-view baselines showed limited discrimination (external AUROCs 0.47–0.70). Conversely, domain-specific foundational model (EchoPrime) achieved superior single-view performance (AUROCs 0.75–0.80 internal; 0.79–0.83 external), highlighting the importance of echo-specific pretraining and temporal modeling. The proposed multi-view fusion further enhanced predictive performance, with the late fusion model reaching an AUROC of 0.84 on the external cohort with significant population-shift. Conclusions These results suggest LVOT physiology is encoded in routine 2D imaging and can be leveraged for clinically relevant gradient classification without Doppler input- proposed AI-guided strategy demonstrates substantial cost savings compared with the screen-all approach. By integrating complementary spatial-temporal information across multiple views, our approach generalizes robustly across populations and may enable real-time decision support, extend LVOT assessment to portable or resource-limited settings, and complement Doppler-based evaluation for longitudinal HCM management.

Abstract Aims The aim of this study was to assess the association between triglyceride (TG) levels and cardiovascular disease (CVD) mortality concerning low-density lipoprotein cholesterol (LDL-C) and age in the general population. Methods and results From the Korean National Health Insurance Service database, 15 672 028 participants aged 18–99 who underwent routine health examinations were followed up for CVD mortality. Hazard ratios for CVD mortality were calculated using Cox models after adjusting for various confounders. During a mean of 8.8 years of follow-up, 105 174 individuals died of CVD. There was a clear log-linear association between TG and overall CVD mortality down to 50 mg/dL. Each two-fold increase in TG was associated with 1.10-fold (overall CVD), 1.22-fold [ischaemic heart disease (IHD)], 1.24-fold [acute myocardial infarction (AMI)], and 1.10-fold (ischaemic stroke) higher CVD mortality. Haemorrhagic stroke and heart failure were not associated with TG levels. The impact of hypertriglyceridaemia (HTG) on CVD weakened but remained present in persons with LDL-C < 100 mg/dL, in whom each two-fold higher TG was associated with 1.05-fold (overall CVD), 1.12-fold (IHD), 1.15-fold (AMI), and 1.05-fold (ischaemic stroke) higher CVD mortality. The younger population (18–44 years) had stronger associations between TG levels and mortality from overall CVD, IHD, and AMI than the older population. Conclusion Hypertriglyceridaemia independently raises CVD mortality with lingering risks in young and older individuals with low LDL-C levels, suggesting the importance of management of HTG even with controlled LDL-C.

Introduction: The role of hypertriglyceridemia (HTG) in cardiovascular disease (CVD) remains controversial, especially in persons with well-controlled low-density lipoprotein cholesterol (LDL-C). Hypothesis: We aimed to evaluate the association between triglyceride (TG) levels and CVD mortality according to LDL-C and age in a general population. Methods: From the Korean National Health Insurance Service database, 15,672,028 participants aged 18-99 who underwent routine health examinations were followed up for CVD mortality. Hazard ratios (HRs) for CVD mortality were calculated using Cox models after adjusting for various confounders. Results: During a mean 8.8 years of follow-up, 105,174 individuals died from CVD. There was a clear log-linear association between TG and overall CVD mortality down to 50 mg/dL. Each two-fold increase in TG was associated with 1.10-fold (overall CVD), 1.22-fold (ischemic heart disease [IHD]), 1.24-fold (acute myocardial infarction [AMI]), and 1.10-fold (ischemic stroke) higher CVD mortality. Hemorrhagic stroke and heart failure were not associated with TG levels. The impact of HTG on CVD weakened but remained present in persons with LDL-C <100 mg/dL, in whom each two-fold higher TG was associated with 1.05-fold (overall CVD), 1.12-fold (IHD), 1.15-fold (AMI), and 1.05-fold (ischemic stroke) higher CVD mortality. The younger population (18 to 44 years) had stronger associations between TG levels and mortality from overall CVD, IHD, and AMI than the older population. Conclusions: HTG independently increases CVD mortality. There are residual risks of HTG in both young and older individuals with a low level of LDL-C. HTG management might be beneficial in individuals with well-controlled LDL-C.

Abstract Aims To investigate the impact of statins on plaque progression according to high-risk coronary atherosclerotic plaque (HRP) features and to identify predictive factors for rapid plaque progression in mild coronary artery disease (CAD) using serial coronary computed tomography angiography (CCTA). Methods and results We analyzed mild stenosis (25–49%) CAD, totaling 1432 lesions from 613 patients (mean age, 62.2 years, 63.9% male) and who underwent serial CCTA at a ≥2 year inter-scan interval using the Progression of AtheRosclerotic PlAque DetermIned by Computed TomoGraphic Angiography Imaging (NCT02803411) registry. The median inter-scan period was 3.5 ± 1.4 years; plaques were quantitatively assessed for annualized percent atheroma volume (PAV) and compositional plaque volume changes according to HRP features, and the rapid plaque progression was defined by the ≥90th percentile annual PAV. In mild stenotic lesions with ≥2 HRPs, statin therapy showed a 37% reduction in annual PAV (0.97 ± 2.02 vs. 1.55 ± 2.22, P = 0.038) with decreased necrotic core volume and increased dense calcium volume compared to non-statin recipient mild lesions. The key factors for rapid plaque progression were ≥2 HRPs [hazard ratio (HR), 1.89; 95% confidence interval (CI), 1.02–3.49; P = 0.042], current smoking (HR, 1.69; 95% CI 1.09–2.57; P = 0.017), and diabetes (HR, 1.55; 95% CI, 1.07–2.22; P = 0.020). Conclusion In mild CAD, statin treatment reduced plaque progression, particularly in lesions with a higher number of HRP features, which was also a strong predictor of rapid plaque progression. Therefore, aggressive statin therapy might be needed even in mild CAD with higher HRPs. Clinical trial registration ClinicalTrials.gov NCT02803411

Abstract Objectives: We aimed to compare the segmentation performance of the current prominent deep learning (DL) algorithms with ground-truth segmentations and to validate the reproducibility of the manually created 2D echocardiographic four cardiac chamber ground-truth annotation.Background: Recently emerged DL based fully-automated chamber segmentation and function assessment methods have shown great potential for future application in aiding image acquisition, quantification, and suggestion for diagnosis. However, the performance of current DL algorithms have not previously been compared with each other. In addition, the reproducibility of ground-truth annotations which are the basis of these algorithms have not yet been fully validated.Methods: We retrospectively enrolled 500 consecutive patients who underwent transthoracic echocardiogram (TTE) from December 2019 to December 2020. Simple U-net, Res-U-net, and Dense-U-net algorithms were compared for the segmentation performances and clinical indices such as left atrial volume (LAV), left ventricular end diastolic volume (LVEDV), LV end systolic volume (LVESV), LV mass, and ejection fraction (EF) were evaluated. The inter- and intra- observer variability analysis was performed by two expert sonographers for a randomly selected echocardiographic view in 100 patients (apical 2-chamber, apical 4-chamber, and parasternal short axis views).Results: The overall performance of all DL methods was excellent (average Dice similarity coefficient (DSC) 0.91 to 0.95 and average Intersection over union (IOU) 0.83 to 0.90), with the exception of LV wall area on PSAX view (average DSC of 0.83, IOU 0.72). In addition, there were no significant difference in clinical indices between ground truth and automated DL measurements. For inter- and intra observer variability analysis, the overall intra observer reproducibility was excellent: LAV (ICC = 0.995), LVEDV (ICC = 0.996), LVESV (ICC = 0.997), LV mass (ICC = 0.991) and EF (ICC = 0.984). The inter-observer reproducibility was slightly lower as compared to intraobserver agreement: LAV (ICC = 0.976), LVEDV (ICC = 0.982), LVESV (ICC =0.970), LV mass (ICC = 0.971), and EF (ICC = 0.899).Conclusions: The three current prominent DL-based fully automated methods are able to reliably perform four-chamber segmentation and quantification of clinical indices. Furthermore, we were able to validate the four cardiac chamber ground-truth annotation and demonstrate an overall excellent reproducibility, but still with some degree of inter-observer variability.