Deep-Learning Models for the Echocardiographic Assessment of Diastolic Dysfunction.

The authors explored a deep neural network (DeepNN) model that integrates multidimensional echocardiographic data to identify distinct patient subgroups with heart failure with preserved ejection fraction (HFpEF). The clinical algorithms for phenotyping the severity of diastolic dysfunction in HFpEF remain imprecise. The authors developed a DeepNN model to predict high- and low-risk phenogroups in a derivation cohort (n = 1,242). Model performance was first validated in 2 external cohorts to identify elevated left ventricular filling pressure (n = 84) and assess its prognostic value (n = 219) in patients with varying degrees of systolic and diastolic dysfunction. In 3 National Heart, Lung, and Blood Institute-funded HFpEF trials, the clinical significance of the model was further validated by assessing the relationships of the phenogroups with adverse clinical outcomes (TOPCAT [Aldosterone Antagonist Therapy for Adults With Heart Failure and Preserved Systolic Function] trial, n = 518), cardiac biomarkers, and exercise parameters (NEAT-HFpEF [Nitrate's Effect on Activity Tolerance in Heart Failure With Preserved Ejection Fraction] and RELAX-HF [Evaluating the Effectiveness of Sildenafil at Improving Health Outcomes and Exercise Ability in People With Diastolic Heart Failure] pooled cohort, n = 346). The DeepNN model showed higher area under the receiver-operating characteristic curve than 2016 American Society of Echocardiography guideline grades for predicting elevated left ventricular filling pressure (0.88 vs. 0.67; p = 0.01). The high-risk (vs. low-risk) phenogroup showed higher rates of heart failure hospitalization and/or death, even after adjusting for global left ventricular and atrial longitudinal strain (hazard ratio [HR]: 3.96; 95% confidence interval [CI]: 1.24 to 12.67; p = 0.021). Similarly, in the TOPCAT cohort, the high-risk (vs. low-risk) phenogroup showed higher rates of heart failure hospitalization or cardiac death (HR: 1.92; 95% CI: 1.16 to 3.22; p = 0.01) and higher event-free survival with spironolactone therapy (HR: 0.65; 95% CI: 0.46 to 0.90; p = 0.01). In the pooled RELAX-HF/NEAT-HFpEF cohort, the high-risk (vs. low-risk) phenogroup had a higher burden of chronic myocardial injury (p < 0.001), neurohormonal activation (p < 0.001), and lower exercise capacity (p = 0.001). This publicly available DeepNN classifier can characterize the severity of diastolic dysfunction and identify a specific subgroup of patients with HFpEF who have elevated left ventricular filling pressures, biomarkers of myocardial injury and stress, and adverse events and those who are more likely to respond to spironolactone.

Pandey A ，Kagiyama N ，Yanamala N ，Segar MW ，Cho JS ，Tokodi M ，Sengupta PP ... -  《-》

Phenomapping of patients with heart failure with preserved ejection fraction using machine learning-based unsupervised cluster analysis.

To identify distinct phenotypic subgroups in a highly-dimensional, mixed-data cohort of individuals with heart failure (HF) with preserved ejection fraction (HFpEF) using unsupervised clustering analysis. The study included all Treatment of Preserved Cardiac Function Heart Failure with an Aldosterone Antagonist (TOPCAT) participants from the Americas (n = 1767). In the subset of participants with available echocardiographic data (derivation cohort, n = 654), we characterized three mutually exclusive phenogroups of HFpEF participants using penalized finite mixture model-based clustering analysis on 61 mixed-data phenotypic variables. Phenogroup 1 had higher burden of co-morbidities, natriuretic peptides, and abnormalities in left ventricular structure and function; phenogroup 2 had lower prevalence of cardiovascular and non-cardiac co-morbidities but higher burden of diastolic dysfunction; and phenogroup 3 had lower natriuretic peptide levels, intermediate co-morbidity burden, and the most favourable diastolic function profile. In adjusted Cox models, participants in phenogroup 1 (vs. phenogroup 3) had significantly higher risk for all adverse clinical events including the primary composite endpoint, all-cause mortality, and HF hospitalization. Phenogroup 2 (vs. phenogroup 3) was significantly associated with higher risk of HF hospitalization but a lower risk of atherosclerotic event (myocardial infarction, stroke, or cardiovascular death), and comparable risk of mortality. Similar patterns of association were also observed in the non-echocardiographic TOPCAT cohort (internal validation cohort, n = 1113) and an external cohort of patients with HFpEF [Phosphodiesterase-5 Inhibition to Improve Clinical Status and Exercise Capacity in Heart Failure with Preserved Ejection Fraction (RELAX) trial cohort, n = 198], with the highest risk of adverse outcome noted in phenogroup 1 participants. Machine learning-based cluster analysis can identify phenogroups of patients with HFpEF with distinct clinical characteristics and long-term outcomes.

Segar MW ，Patel KV ，Ayers C ，Basit M ，Tang WHW ，Willett D ，Berry J ，Grodin JL ，Pandey A ... -  《-》

Clinical Phenogroups in Heart Failure With Preserved Ejection Fraction: Detailed Phenotypes, Prognosis, and Response to Spironolactone.

This study sought to assess if clinical phenogroups differ in comprehensive biomarker profiles, cardiac and arterial structure/function, and responses to spironolactone therapy. Previous studies identified distinct subgroups (phenogroups) of patients with heart failure with preserved ejection fraction (HFpEF). Among TOPCAT (Treatment of Preserved Cardiac Function Heart Failure with an Aldosterone Antagonist Trial) participants, we performed latent-class analysis to identify HFpEF phenogroups based on standard clinical features and assessed differences in multiple biomarkers measured from frozen plasma; cardiac and arterial structure/function measured with echocardiography and arterial tonometry; prognosis; and response to spironolactone. Three HFpEF phenogroups were identified. Phenogroup 1 (n = 1,214) exhibited younger age, higher prevalence of smoking, preserved functional class, and the least evidence of left ventricular (LV) hypertrophy and arterial stiffness. Phenogroup 2 (n = 1,329) was older, with normotrophic concentric LV remodeling, atrial fibrillation, left atrial enlargement, large-artery stiffening, and biomarkers of innate immunity and vascular calcification. Phenogroup 3 (n = 899) demonstrated more functional impairment, obesity, diabetes, chronic kidney disease, concentric LV hypertrophy, high renin, and biomarkers of tumor necrosis factor-alpha-mediated inflammation, liver fibrosis, and tissue remodeling. Compared with phenogroup 1, phenogroup 3 exhibited the highest risk of the primary endpoint of cardiovascular death, heart failure hospitalization, or aborted cardiac arrest (hazard ratio [HR]: 3.44; 95% confidence interval [CI]: 2.79 to 4.24); phenogroups 2 and 3 demonstrated similar all-cause mortality (phenotype 2 HR: 2.36; 95% CI: 1.89 to 2.95; phenotype 3 HR: 2.26, 95% CI: 1.77 to 2.87). Spironolactone randomized therapy was associated with a more pronounced reduction in the risk of the primary endpoint in phenogroup 3 (HR: 0.75; 95% CI: 0.59 to 0.95; p for interaction = 0.016). Results were similar after excluding participants from Eastern Europe. We identified important differences in circulating biomarkers, cardiac/arterial characteristics, prognosis, and response to spironolactone across clinical HFpEF phenogroups. These findings suggest distinct underlying mechanisms across clinically identifiable phenogroups of HFpEF that may benefit from different targeted interventions.

Cohen JB ，Schrauben SJ ，Zhao L ，Basso MD ，Cvijic ME ，Li Z ，Yarde M ，Wang Z ，Bhattacharya PT ，Chirinos DA ，Prenner S ，Zamani P ，Seiffert DA ，Car BD ，Gordon DA ，Margulies K ，Cappola T ，Chirinos JA ... -  《-》

Impaired systolic function by strain imaging in heart failure with preserved ejection fraction.

This study sought to determine the frequency and magnitude of impaired systolic deformation in heart failure with preserved ejection fraction (HFpEF). Although diastolic dysfunction is widely considered a key pathophysiologic mediator of HFpEF, the prevalence of concomitant systolic dysfunction has not been clearly defined. We assessed myocardial systolic and diastolic function in 219 HFpEF patients from a contemporary HFpEF clinical trial. Myocardial deformation was assessed using a vendor-independent 2-dimensional speckle-tracking software. The frequency and severity of impaired deformation was assessed in HFpEF, and compared to 50 normal controls free of cardiovascular disease and to 44 age- and sex-matched hypertensive patients with diastolic dysfunction (hypertensive heart disease) but no HF. Among HFpEF patients, clinical, echocardiographic, and biomarker correlates of left ventricular strain were determined. The HFpEF patients had preserved left ventricular ejection fraction and evidence of diastolic dysfunction. Compared to both normal controls and hypertensive heart disease patients, the HFpEF patients demonstrated significantly lower longitudinal strain (LS) (-20.0 ± 2.1 and -17.07 ± 2.04 vs. -14.6 ± 3.3, respectively, p < 0.0001 for both) and circumferential strain (CS) (-27.1 ± 3.1 and -30.1 ± 3.5 vs. -22.9 ± 5.9, respectively; p < 0.0001 for both). In HFpEF, both LS and CS were related to LVEF (LS, R = -0.46; p < 0.0001; CS, R = -0.51; p < 0.0001) but not to standard echocardiographic measures of diastolic function (E' or E/E'). Lower LS was modestly associated with higher NT-proBNP, even after adjustment for 10 baseline covariates including LVEF, measures of diastolic function, and LV filling pressure (multivariable adjusted p = 0.001). Strain imaging detects impaired systolic function despite preserved global LVEF in HFpEF that may contribute to the pathophysiology of the HFpEF syndrome. (LCZ696 Compared to Valsartan in Patients With Chronic Heart Failure and Preserved Left-ventricular Ejection Fraction; NCT00887588).

Kraigher-Krainer E ，Shah AM ，Gupta DK ，Santos A ，Claggett B ，Pieske B ，Zile MR ，Voors AA ，Lefkowitz MP ，Packer M ，McMurray JJ ，Solomon SD ，PARAMOUNT Investigators ... -  《-》

Echocardiographic Features of Patients With Heart Failure and Preserved Left Ventricular Ejection Fraction.

The PARAGON-HF (Prospective Comparison of ARNI With ARB Global Outcomes in HF With Preserved Ejection Fraction) trial tested the efficacy of sacubitril-valsartan in patients with heart failure with preserved ejection fraction (HFpEF). Existing data on cardiac structure and function in patients with HFpEF suggest significant heterogeneity. The aim of this study was to characterize cardiac structure and function, quantify their associations with clinical outcomes, and contextualize these findings with other HFpEF studies. Echocardiography was performed in 1,097 of 4,822 PARAGON-HF patients within 6 months of enrollment. Associations with incident first heart failure hospitalization or cardiovascular death were assessed using Cox proportional hazards models adjusted for age, sex, region of enrollment, randomized treatment, N-terminal pro-brain natriuretic peptide, and clinical risk factors. Average age was 74 ± 8 years, 53% of patients were women, median N-terminal pro-brain natriuretic peptide level was 918 pg/ml (interquartile range: 485 to 1,578 pg/ml), 94% had hypertension, and 35% had atrial fibrillation. The mean left ventricular (LV) ejection fraction was 58.6 ± 9.8%, prevalence of LV hypertrophy was 21%, prevalence of left atrial enlargement was 83%, prevalence of elevated E/e' ratio was 53%, and prevalence of pulmonary hypertension was 31%. Heart failure hospitalization or cardiovascular death occurred in 288 patients at 2.8-year median follow-up. In fully adjusted models, higher LV mass index (hazard ratio [HR]: 1.05 per 10 g/m2; 95% confidence interval [CI]: 1.00 to 1.10; p = 0.03), E/e' ratio (HR: 1.04 per unit; 95% CI: 1.02 to 1.06; p < 0.001), pulmonary artery systolic pressure (HR: 1.51 per 10 mm Hg; 95% CI: 1.29 to 1.76; p < 0.001), and right ventricular end-diastolic area (HR: 1.04 per cm2; 95% CI: 1.01 to 1.07; p = 0.003) were each associated with this composite, while LV ejection fraction and left atrial size were not (p > 0.05 for all). Appreciable differences were observed in cardiac structure compared with other HFpEF clinical trials, despite similar E/e' ratio, pulmonary artery systolic pressure, and event rates. Diastolic dysfunction, left atrial enlargement, and pulmonary hypertension were common in PARAGON-HF. LV hypertrophy, elevated left- and right-sided pressures, and right ventricular enlargement were independently predictive of incident heart failure hospitalization or cardiovascular death. Echocardiographic differences among HFpEF trials despite similar clinical event rates highlight the heterogeneity of this syndrome. (Efficacy and Safety of LCZ696 Compared to Valsartan, on Morbidity and Mortality in Heart Failure Patients With Preserved Ejection Fraction [PARAGON-HF]; NCT01920711).

Shah AM ，Cikes M ，Prasad N ，Li G ，Getchevski S ，Claggett B ，Rizkala A ，Lukashevich I ，O'Meara E ，Ryan JJ ，Shah SJ ，Mullens W ，Zile MR ，Lam CSP ，McMurray JJV ，Solomon SD ，PARAGON-HF Investigators ... -  《-》