Deep-Learning Models for the Echocardiographic Assessment of Diastolic Dysfunction

Ambarish Pandey, Nobuyuki Kagiyama, Naveena Yanamala, Matthew W. Segar, Jung S. Cho, Márton Tokodi, Partho P. Sengupta

Research output: Contribution to journalArticlepeer-review

Abstract

Objectives: 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). Background: The clinical algorithms for phenotyping the severity of diastolic dysfunction in HFpEF remain imprecise. Methods: 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). Results: 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). Conclusions: 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.

Original languageEnglish (US)
JournalJACC: Cardiovascular Imaging
DOIs
StateAccepted/In press - 2021

Keywords

  • deep learning
  • diastolic dysfunction
  • echocardiography
  • heart failure with preserved ejection fraction

ASJC Scopus subject areas

  • Radiology Nuclear Medicine and imaging
  • Cardiology and Cardiovascular Medicine

Fingerprint

Dive into the research topics of 'Deep-Learning Models for the Echocardiographic Assessment of Diastolic Dysfunction'. Together they form a unique fingerprint.

Cite this