Citations

Abstract Background Right ventricular (RV) systolic function is an independent predictor of outcome, but a robust automated method of quantitation is lacking. Purpose To develop and validate a deep learning model for quantifying RV systolic function from 2D echo clips and assess its prognostic value in various loading states and left-heart disease. Methods A deep learning convolutional neural network (CNN) was developed to quantitate RV systolic function using all available apical 4 chamber (A4C) views from 13,039 patients (61,187 A4C video clips) in a US institution. Videos were converted to frames of 256x256 grayscale pixels, with graphics, including the ECG, removed. The model used the S3D architecture, a 3D-CNN with many of the spatial and temporal convolutions separated. RV free wall longitudinal strain (RVFWLS) was used to define RV function: normal (≤-25%); mild (-20% to –24%); moderate (-15% to –19%) and severe RV dysfunction (0% to –14%). The AI-estimate was the average of multiple 32-frame segments for each clip identified as an A4C, including both standard and RV-focused variations. The model was validated in four distinct clinical cohorts from independent data sources: 1) 1365 patients referred to an external diagnostic echocardiography lab in a different US state; 2) 569 patients recruited prospectively with known or suspected pulmonary hypertension (PH); 3) 416 patients with moderate or greater tricuspid valve regurgitation (TR); 4) 872 patients imaged at an Eastern European University with left-sided cardiac diseases (valvular disease, cardiomyopathies, etc.), athletes, or healthy volunteers. Results Model output was strongly correlated with the presence of RV dysfunction by manual measurement [AUC 0.907 (95% CI: 0.888-0.926)] in the internal validation set. Results were similar in an external validation US cohort [N=1365; AUC 0.919 (95% CI: 0.899-0.939)]. When the model was applied to 569 patients with known or suspected PH, presence and severity of the AI measures of RV dysfunction were strongly associated with functional class, 6 min walk distance, NT-proBNP levels and right heart failure (p<0.001). The presence and severity of RV dysfunction (as categorized by the AI model) was strongly associated with all-cause mortality in patients with PH (Figure 1A) and in patients with significant TR (Figure 1B). The European cohort was a geographically and institutionally distinct cohort with a low prevalence of >mild TR (10.8%) or PH (6.4%). In this cohort the AI model predicted a reduced RVEF (< 45%) with an AUC of 0.864 (95% CI: 0.831-0.898) and associated with both all-cause mortality (Figure 2A) and a composite endpoint of heart failure hospitalization or death (Figure 2B). Conclusions A fully automated, AI-based assessment of RV systolic function, using 2D apical 4 chamber echo views alone, is highly feasible and can accurately categorize disease severity and predict outcome across a wide spectrum of cardiovascular conditions.Figure 1 Figure 2

Background Artificial intelligence (AI)–enabled electrocardiography has emerged as a tool for detecting cardiac dysfunction. The prognostic relevance of AI‐enabled electrocardiography–derived diastolic dysfunction (DD) in patients undergoing transcatheter aortic valve replacement had not been assessed. Methods We analyzed 3197 patients undergoing transcatheter aortic valve replacement for severe aortic stenosis between 2010 and 2023 with baseline 12‐lead ECGs processed by a validated AI model to classify diastolic function (grades 0–3). Multivariable Cox models and nested model comparisons assessed associations with all‐cause mortality, including a prespecified analysis in patients with indeterminate echocardiographic grading. Trajectories were defined by change in AI‐enabled electrocardiography DD grade (<2 versus ≥2) from baseline to 30‐day or 1‐year follow‐up. Results At baseline, 21% had grade 3, 57% had grade 2, 8% had grade 1, and 14% had grade 0 AI‐enabled electrocardiography DD. Higher grades were associated with adverse cardiac remodeling and comorbidities. Over a median follow‐up of 3.4 years, grade 3 AI‐enabled electrocardiography DD independently predicted mortality (hazard ratio [HR], 1.80 [95% CI, 1.47–2.20]; P <0.001). AI‐enabled electrocardiography DD improved prognostic discrimination beyond clinical and echocardiographic measures (ΔHarrell concordance statistic, 0.016; Δ χ 2 =57; P <0.001). Among 1259 patients with indeterminate echocardiographic grading, AI‐enabled electrocardiography added prognostic value (ΔHarrell concordance statistic, 0.02; Δ χ 2 =13; P =0.006). Worsening or persistently high‐risk trajectories were associated with increased mortality (HRs, 1.45–1.80; all P <0.05). Conclusions AI‐enabled electrocardiography–derived DD independently predicts mortality after transcatheter aortic valve replacement, adds value beyond echocardiographic grading, and enables dynamic risk stratification through longitudinal tracking.

Abstract Valvular heart disease represents a significant global health burden, with an estimated prevalence of 2.5% in high-income countries and projected increases due to population ageing. Randomized controlled trials in valvular heart disease have undergone substantial evolution, shifting from mortality-focused endpoints toward comprehensive assessments integrating imaging parameters and patient-centered outcomes. Cardiovascular imaging modalities, including echocardiography, cardiac computed tomography, and cardiac magnetic resonance, have become pivotal in trial design, patient selection, and endpoint definition. Recent landmark trials in aortic stenosis, including EARLY-TAVR and EVOLVED, have challenged traditional symptom-based intervention thresholds by incorporating imaging biomarkers of subclinical myocardial dysfunction and cardiac damage staging. In aortic regurgitation, the paucity of randomized controlled trials evidence contrasts with emerging transcatheter technologies, highlighting critical knowledge gaps. Mitral regurgitation trials have demonstrated the importance of patient phenotyping, with divergent outcomes between COAPT and MITRA-FR emphasizing the role of imaging in optimal patient selection. The recent TRILUMINATE and TRISCEND trials have transformed tricuspid regurgitation management through transcatheter interventions, prioritizing quality-of-life improvements alongside traditional clinical endpoints. Future directions include standardization of imaging protocols across modalities, development of artificial intelligence-enhanced analysis, and integration of multiparametric biomarkers for personalized risk stratification. The paradigm shift toward imaging-guided, patient-centered trial design represents a fundamental reimagining of therapeutic success in valvular heart disease, moving beyond procedural outcomes toward comprehensive assessment of clinical benefit and improved patient care.

Background The natural history of asymptomatic moderate or severe aortic regurgitation (AR) remains uncertain, with conflicting reports about its progression and surgical timing. We aimed to quantify adverse outcomes under conservative management and evaluate the association of aortic valve replacement/repair (AVR) with mortality. Methods Systematic searches (inception–July 2025) identified cohort studies of asymptomatic moderate/severe AR. Random-effects models estimated pooled incidence rates of adverse events; fixed-effects models were used for hazard ratios (HRs) of AVR vs conservative management. Results Twenty-seven studies (4720 patients; mean age 49 years; mean follow-up 3.9 years) were included. Pooled incidence rates per 100 person-years were 1.75 (95% CI 1.27 to 2.41) for all-cause mortality, 1.29 for cardiac death, 0.29 for sudden death, 4.30 for new symptoms and 7.01 for AVR. Asymptomatic low left ventricular ejection fraction occurred in only 0.9 per 100 person-years. Mortality rates were more than double those of the general population across age groups—2.45 (1.90 to 3.18) per 100 person-years for cohorts with mean age ≥50 years versus 0.59 (0.29 to 1.21) for younger cohorts. Early AVR was associated with lower mortality (pooled HR 0.33; 95% CI 0.30 to 0.37). Conclusion Asymptomatic moderate/severe AR carries significant excess mortality irrespective of age, contradicting its historically benign reputation. Given the rarity of asymptomatic LV dysfunction, earlier intervention guided by more sensitive markers of LV damage may improve outcomes, although heterogeneity and study quality warrant cautious interpretation. PROSPERO registration number CRD42024522683.

Background: Tricuspid regurgitation (TR) is associated with significant morbidity, but individualized treatment and timing of intervention are yet to be defined. We previously proposed and validated artificial intelligence electrocardiography (AI-ECG) scores for various diseases. Whether incorporating AI-ECG information adds to risk stratification above and beyond classical clinical parameters is unknown. Objectives: To identify AI-ECG scores independently associated with all-cause mortality in chronic TR and to create a composite AI-ECG risk score. Methods: Patients with a first echocardiographic diagnosis of ≥moderate TR between 2005-2016 and an ECG within ±15 days were included. The Tricuspid Regurgitation Impact on Outcome (TRIO) score was calculated as previously described based on 8 simple parameters (age, sex, severe TR, heart failure, lung disease, heart rate, creatinine and AST). AI-ECG probabilities of low ejection fraction, aortic stenosis, amyloid, cirrhosis, atrial fibrillation and hypertrophic cardiomyopathy were estimated by existing algorithms; the first 4 were associated with all-cause mortality and a composite AI-ECG risk score was calculated (0-4; 1 point for each AI-ECG above specific threshold). Results: A total of 12,377 pts were included (age 72±13 yrs, 55% women). Over a median follow-up of 1.3 yrs (IQR 0.1 to 4.4), 7,121 pts (58%) died. Mortality risk increased significantly with higher composite AI-ECG risk score (Fig. 1A). On multivariable analysis (proportional hazards method), the composite AI-ECG risk score remained independently associated with death, even after adjusting for age, sex, high NT-proBNP levels (>2,500 pg/mL), right ventricular systolic pressure (RVSP), diuretic use and TRIO risk score category (Fig. 1B). Conclusions: Patients with ≥moderate TR show progressively worse survival with increasing composite AI-ECG risk score. Incorporating AI-derived information from a simple and inexpensive ECG may identify patients with the highest risk of mortality beyond clinical risk scores as TRIO or classical clinical, laboratory and echocardiographic parameters. Prospective validation of this approach needs to be tested in future trials.

Abstract Aims The pathophysiology of tricuspid regurgitation (TR) during exercise in heart failure with preserved ejection fraction (HFpEF) is not well understood. Methods and results We investigated dynamic changes in TR severity during exercise in patients with HFpEF and associated relationships with haemodynamics, cardiopulmonary reserve, and prognosis using invasive haemodynamic exercise testing with simultaneous echocardiography and expired gas analysis. Among 169 patients with HFpEF (91 no TR, 44 mild TR, 34 ≥ moderate TR), older age and atrial fibrillation were more common in patients with greater TR severity. Right heart remodelling and dysfunction were more frequently observed with greater TR severity, particularly in the right atrium, along with stepwise increases in right atrial (RA) pressure and interventricular septal flattening, and decreases in cardiac output (CO). During exercise, TR severity frequently worsened, and over half of the patients with moderate TR at rest displayed severe TR during exercise, accompanied by profound RA dilatation, reduced RA reservoir strain, increased septal flattening, and more severely impaired CO reserve. Abnormalities in tricuspid annular motion and ventricular interaction were amplified by exercise with greater TR, but exercise pulmonary vascular pressures did not differ across groups. Patients with ≥ moderate TR during exercise displayed higher event rates (hazard ratio 2.85, 95% confidence interval 1.18–6.85), but patients with mild TR had similar prognosis as those without TR in adjusted models. Conclusions Tricuspid regurgitation in HFpEF is related to advanced RA myopathy and often worsens during exercise leading to dynamic right-sided heart failure, exaggerated ventricular interaction, impaired CO reserve, and increased risk for adverse outcomes. These data emphasize the clinical importance of exercise evaluation and call for further study of novel treatments in those with significant resting and provocable TR.

Abstract Aims While intentional weight loss achieved through cardiometabolic medications has been associated with robust salutary effects in heart failure (HF) with preserved ejection fraction (HFpEF), the clinical significance of unintentional weight loss in this setting remains unclear. Methods and results This retrospective cohort study included 434 overweight or obese patients with invasively proven HFpEF (67 ± 11 years, 236 female), without weight-reducing therapies or known malignancy, who underwent invasive hemodynamic cardiopulmonary testing and long-term clinical follow-up. The annualized weight change from index to final evaluation for the tertiles was: −21.1 to −1.8 kg/year (tertile 1); −1.8 to 0 kg/year (tertile 2); and 0 to +17.0 kg/year (tertile 3). Patients in tertile 1 had subtle abnormalities in ventilatory control at baseline, but there were no other significant differences between groups across a vast array of haemodynamic and metabolic parameters, both at rest and during exercise. Baseline weight was directly correlated with right and left heart filling pressures (r = 0.23–0.34, p &lt; 0.001), but annualized weight change showed no correlation with any baseline haemodynamic measurements (all p &gt; 0.05). Over a median follow-up of 4.7 years (interquartile range 2.3–6.5), patients in tertile 1 had higher risk of all-cause death (hazard ratio [HR] 3.36, 95% confidence interval [CI] 1.77–6.39, p &lt; 0.001), all-cause death or HF hospitalization (HR 2.49, 95% CI 1.53–4.04, p &lt; 0.001) and cardiac death or HF hospitalization (HR 2.28, 95% CI 1.28–4.07, p = 0.005) compared with those in tertile 2 or 3. These findings were consistent after multivariable adjustment. Conclusions Unintentional weight loss is associated with worse prognosis in patients with HFpEF and overweight or obesity, even as haemodynamics, exercise capacity, and gas exchange are not different from patients with stable or increasing weight. These data underline important and fundamental differences between therapeutic and unintended weight loss in HFpEF.

Abstract Aims Oxygen consumption at peak exercise is widely used to assess functional impairment in heart failure with preserved ejection fraction (HFpEF), but few patients exercise to this intensity in daily living. Alternative metrics that quantify submaximal fitness may provide more patient-centred evaluations, but the pathophysiology of submaximal exercise intolerance in HFpEF is unexplored. Methods and results Patients with HFpEF underwent invasive haemodynamic cardiopulmonary exercise testing with blood lactate measurement during exercise to volitional fatigue. Lactate threshold (LT) was defined as the exercise workload at which arterial lactate exceeded &gt;2.0 mmol/L, taken as a measure of submaximal fitness. Of patients with HFpEF (n = 286), 194 (68%) reached LT at a workload of 40 W or less (LT ≤40 W), while 92 (32%) reached a workload exceeding 40 W at LT (LT &gt;40 W). As compared to LT &gt;40 W, patients with LT ≤40 W were more likely to be female, anaemic, and had greater pulmonary vascular disease (all p &lt; 0.01). During 20 W exercise, participants with LT ≤40 W had higher pulmonary artery pressure, biventricular filling pressures, minute ventilation and respiratory drive, higher perceived dyspnoea and fatigue ratings, greater arterial–venous oxygen content difference, despite similar cardiac output and oxygen delivery. At peak exercise, most of these differences were no longer apparent. Findings were replicated using non-invasively-measured workload at ventilatory threshold. Conclusions Two-thirds of patients with HFpEF reach LT at workloads typical of activities of daily living. Patients with HFpEF and impaired submaximal fitness are more likely to be female, have greater pulmonary vascular disease and anaemia severity, and display greater haemodynamic, symptomatic, and ventilatory control abnormalities during low-level exercise, which are not apparent at maximal exertion. These findings have therapeutic implications and suggest a potentially important role for wider evaluation of submaximal fitness in addition to peak aerobic capacity.

Abstract Aims Tricuspid valve regurgitation (TR) is common and associated with increased mortality. The interaction between the pulmonary artery (PA) circulation and the right ventricle (RV) and association with outcomes is incompletely understood. The effective PA elastance (PA Ea) is a composite measure of RV afterload that refers to the pulmonary vascular load that the RV must overcome to eject blood. Whether PA Ea discriminates mortality risk in unselected patients with significant TR is unknown. Methods and results In consecutive patients with ≥moderate TR, we compared all-cause mortality at 5 years based on the PA Ea (defined as the RV systolic pressure/stroke volume as measured by transthoracic echocardiography). In a total of 12 682 patients, the median PA Ea was 0.7 mm Hg/mL (interquartile range 0.5, 0.9). Increasing levels of PA Ea were associated with heart failure, liver and kidney disease, and clinical markers of risk such as the Tricuspid Regurgitation Impact on Outcomes score. Increasing levels of PA Ea were associated with larger RVs, worse RV systolic function, higher N-terminal pro-brain natriuretic peptide levels, and greater degrees of right heart failure. After adjusting for age and sex, PA Ea was associated with higher risk of death (hazard ratio 1.55 per 0.5 mm Hg/mL change of PA Ea; 95% confidence intervals 1.51–1.60; P &lt; 0.0001). In multivariable modelling incorporating available clinical variables, PA Ea was independently predictive of outcome compared with other indexes of RV–PA coupling. Conclusion In patients with significant TR, higher PA Ea is progressively associated with RV dysfunction, right heart failure, and worse survival. Incorporating PA Ea into the routine echo assessment may help stratify risk.