Farina, Juan Maria M

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.

AbstractBackgroundThe prognosis in patients with advanced cardiac amyloidosis (CA) remains poor.ObjectivesWe sought to describe survival post heart transplantation (HT) in amyloid compared with non‐amyloid recipients, highlight waitlist times within the new allocation system across three Organ Procurement and Transplantation Network (OPTN) regions, and describe multiorgan transplantation (MOT) in hereditary amyloidosis.MethodsThis is a retrospective review of end‐stage CA patients who underwent HT at Mayo Clinic from January 2007 to December 2020. Wait time was compared in the new versus old OPTN allocation era starting December 18, 2018 by Wilcoxon rank sum test. All‐cause mortality for those with and without CA was compared using Kaplan–Meier estimates with log rank analysis, censoring December 16, 2022.ResultsFifty‐five patients with CA underwent HT between 2007 and 2020, 8 light chain amyloidosis (AL) (14.5%), 28 hereditary transthyretin (ATTRv) (50.9%), 17 wildtype transthyretin (ATTRwt) (30.9%), and 2 hereditary apolipoprotein A1 (AApoA1) amyloidosis patients (3.6%). No significant difference in overall survival post‐transplant was seen in amyloid compared with non‐amyloid (p = 0.816). Median time to HT was shorter in the new system, 45 days (IQR 24, 78) versus 174 days (IQR 76.5, 483.5), p = 0.006. There was a decline in MOT in hereditary amyloidosis over time with the concomitant rise in disease‐targeted therapies.ConclusionsHT survival in CA patients was similar to non‐amyloid patients. The new allocation system benefits this cohort with shorter wait times. There is less MOT in hereditary amyloidosis with increased utilization of disease‐targeted therapy.