Pre-implant echocardiography plus EHR for post-LVAD risk stratification for survival: Single-center exploratory study.

Biomarkers of systemic disease burden and outcomes after transcatheter tricuspid edge-to-edge repair

Risk stratification after transcatheter tricuspid edge-to-edge repair (T-TEER) remains challenging, particularly in patients with advanced right-sided heart failure and systemic disease burden. Biomarkers reflecting inflammation, stress response and multiorgan dysfunction may provide additional prognostic information in this setting. This prospective single-centre cohort study included 84 consecutive patients undergoing T-TEER for severe tricuspid regurgitation using the TriClip or PASCAL system. Baseline concentrations of growth differentiation factor-15 (GDF-15), soluble urokinase plasminogen activator receptor (suPAR), and NT-proBNP were measured prior to intervention. The primary endpoint was all-cause mortality at 12 months. Secondary endpoints included cardiovascular rehospitalisation and a combined cardiovascular endpoint. Prognostic performance was assessed using receiver operating characteristic and tertile-based Kaplan-Meier analyses. Owing to the limited number of events, all analyses were considered exploratory. During 12-month follow-up, all-cause mortality occurred in 10 patients (11.9%), while cardiovascular rehospitalisation was observed in 29 patients (34.5%). GDF-15 demonstrated good discriminative performance for all-cause mortality (AUC 0.823, 95% CI 0.714–0.932, p = 0.001), whereas suPAR showed moderate prognostic discrimination (AUC 0.742, 95% CI 0.605–0.878, p = 0.013). In contrast, NT-proBNP showed no significant discrimination for all-cause mortality (AUC 0.535, 95% CI 0.362–0.709, p = 0.720). Higher tertiles of both GDF-15 and suPAR were associated with reduced overall and rehospitalisation-free survival. Baseline GDF-15 and suPAR were associated with adverse outcomes after T-TEER and demonstrated greater prognostic discrimination than NT-proBNP in this exploratory cohort. These exploratory findings support further investigation of systemic stress and inflammation biomarkers for risk stratification in patients with severe tricuspid regurgitation.

China-calibration-ready echocardiographic feature modeling for LVEF-derived dysfunction classification: a surrogate-label proof-of-concept

The primary contribution of this study is a transparent, calibration-ready analytical scaffold that can be reused and extended in future prospective Chinese anthracycline cohorts that incorporate true right ventricular outcome measures.

A fully automated machine learning assisted pipeline to predict disease progression for early-stage hypertrophic cardiomyopathy from echocardiography

A fully automated ML model identifies area-derived LACI at end-diastole at end-diastole as a robust feature associated with disease progression, providing improved risk stratification for pre-symptomatic HCM.

Validation of a deep learning-based workflow for the interpretation of the echocardiogram in a cardiooncology population

Echocardiography is the cornerstone for risk stratification, diagnosis, and monitoring of cancer therapy–related cardiac dysfunction (CTRCD)(1). Artificial intelligence (AI)–guided echocardiography has shown high accuracy and reliability in diverse cardiac populations and may reduce variability while improving workflow efficiency(2, 3). However, this technology has not yet been validated in a dedicated cohort of patients with cancer. To evaluate the accuracy and reliability of AI-guided echocardiography in assessing left ventricular ejection fraction (LVEF) and additional parameters, compared with conventional echocardiography, in a cardio-oncology population. This study included patients identified retrospectively from a cardio-oncology registry. Studies, that had already been analysed manually by expert sonographers and reported using AGFA PACS system, were uploaded to the US2.ai platform for automated analysis. The primary outcome was the level of agreement (LoA) between AI-guided and standard echocardiography for LVEF. Secondary outcomes included LoA for additional echocardiographic parameters and LoA between AI- LVEF and 3D LVEF. The performance of the deep learning (DL) algorithm in identifying LVEF <50% was evaluated using the area under the receiver operating characteristic curve (ROC-AUC). Subgroup analyses were performed in predefined populations clinically relevant in cardio-oncology. A total of 282 patients were included. Mean age was 60 ± 16 years, and 61% were women. Breast cancer was the most frequent malignancy (30.5%), followed by haematological malignancies (16.7%) and gastrointestinal tumours (10.6%). Manual median 2D LVEF was 60% (IQR: 55-64) and AI-derived LVEF was 59.2% (IQR: 53-64) showing good agreement and correlation (bias: −0.138, SD: 5.38, 95% LoA: −10.7 to 10.4, ICC: 0.791, 95% CI: 0.742–0.831, Spearman ρ: 0.718,), Table 1. Comparison between 3D echocardiography LVEF and AI-derived 2D LVEF showed similar agreement with narrower limits (bias: −0.13, 95% LoA: −9.51 to 9.26). The DL algorithm accurately identified LVEF <50% (ROC-AUC: 0.918, 95% CI: 0.875–0.961), Figure 1. Subgroup analyses demonstrated consistent agreement in patients with breast cancer, body mass index >30, prior radiotherapy and pericardial effusion. In a large real-world cardio-oncology cohort, AI-guided echocardiography demonstrated strong agreement with conventional echocardiography for LVEF assessment and high accuracy for detecting clinically relevant LV dysfunction. Performance was consistent across key subgroups, supporting the feasibility, reliability, and potential clinical value of integrating DL-based analysis into routine cardio-oncology echocardiographic workflows.Agreement between manual and AI-echo  AUC-ROC curve for LVEF<50%

Adverse Graft Remodeling Reflects Dynamic Allograft Stress and Predicts Adverse Outcomes After Heart Transplantation

Real-World Evaluation of a Nationally Mandated Risk Stratification Tool for Destination Therapy LVAD in Japan.

BACKGROUND Patient selection for destination therapy (DT) with durable left ventricular assist devices (LVADs) remains a major challenge in Asian advanced heart failure practice. In Japan, the J-MACS score is mandatorily calculated before DT implantation and directly influences eligibility decisions; however, its real-world prognostic performance in DT recipients remains unclear. OBJECTIVES To externally validate the predictability of the J-MACS score on mortality in a nationwide Japanese DT cohort. METHODS We conducted a nationwide registry-based analysis of patients undergoing HeartMate 3 implantation as DT between May 2021 and October 2025. The primary endpoint was 2-year all-cause mortality. Prognostic performance of the J-MACS score-based on age, prior cardiac surgery, serum creatinine, and central venous pressure-to-pulmonary artery wedge pressure ratio-was evaluated using multivariable Cox models and restricted mean survival time. RESULTS In total, 210 patients (median age, 60 years; 159 [76%] male) were followed for a median of 514 days (IQR: 257-730 days) after LVAD implantation. The J-MACS score independently predicted mortality (adjusted hazard ratio: 1.17, 95% CI: 1.02-1.36, P = 0.037). The 2-year cumulative mortality rates were 5.8% (95% CI: 2.0%-16.1%) in the low-risk group, 12.7% (95% CI 6.3%-24.6%) in the intermediate-risk group, and 28.6% (95% CI 14.6%-51.2%) in the high-risk group (P = 0.003 for comparison). The high-risk group had approximately 4 months shorter survival. CONCLUSIONS This nationwide real-world study provides the first validation of a nationally mandated DT eligibility algorithm. The J-MACS score may support risk-based clinical decision-making in Japanese DT practice.