A Deep Learning-Based Single-View Echocardiographic Analysis for Prediction of Left Ventricular Outflow Tract Obstruction After Transcatheter Aortic Valve Replacement
Authors:
Preprint
Abstract
Aims: Dynamic left ventricular outflow tract obstruction (LVOTO) is a hemodynamically significant complication following transcatheter aortic valve replacement (TAVR) that remains difficult to predict with conventional transthoracic echocardiography (TTE). We examined whether a deep learning (DL) model developed for LVOTO detection in hypertrophic cardiomyopathy (HCM) could predict post-TAVR LVOTO from pre-TAVR TTE in patients with severe aortic stenosis (AS). Methods and Results: In this retrospective study of 302 consecutive patients undergoing TAVR for severe AS, a pre-trained DL model was applied to pre-TAVR TTE to generate a patient-level DL index of LVOTO (DLi-LVOTO; range 0–100). Post-TAVR LVOTO was defined as a peak pressure gradient ≥30 mmHg on follow-up TTE. Logistic regression and receiver operating characteristic analyses assessed the association and discriminative performance of DLi-LVOTO. Pre-TAVR LVOTO was present in 32 patients (10.6%) and post-TAVR LVOTO in 35 (11.6%). Follow-up TTE was performed at a median of 47 days (IQR 37–63) after TAVR, with the majority of TTE (216 of 302, 71.5%) performed within 2 months. DLi-LVOTO was significantly higher in patients with LVOTO at both pre- and post-TAVR TTE (all p<0.001). In multivariable analysis, DLi-LVOTO remained independently associated with post-TAVR LVOTO even after adjusting for conventional TTE parameters and pre-TAVR LVOTO (adjusted OR 1.29, 95% CI 1.06–1.56 per 10-score increase, p=0.011), with an AUROC of 0.78 (95% CI 0.72–0.85). Among patients without pre-TAVR LVOTO, DLi-LVOTO retained independent predictive value (adjusted OR 1.56, 95% CI 1.19–2.06, p=0.001; AUROC 0.84, 95% CI 0.77–0.91). Conclusion: A DL model originally trained in HCM patients independently predicts post-TAVR LVOTO from pre-TAVR TTE, including in patients without pre-existing LVOTO, suggesting it captures hemodynamic features beyond conventional echocardiographic assessment.Keywords
Funding Information
- Institute of Information & Communications Technology Planning & Evaluation (grant number 2022000972)
This publication has 20 references indexed in Scilit:
- Single-View Echocardiographic Analysis for Left Ventricular Outflow Tract Obstruction Prediction in Hypertrophic Cardiomyopathy: A Deep Learning ApproachJournal of the American Society of Echocardiography, 2025
- Incidence, Predictors, and Prognostic Impact of Left Ventricular Outflow Tract Obstruction Following Transcatheter Aortic Valve ReplacementCJC Open, 2025
- Deep Learning–Based Detection and Severity Assessment of Bicuspid Aortic Valve StenosisJournal of the American Society of Echocardiography, 2025
- Mavacamten for Left Ventricular Outflow Tract Obstruction After Successful Transcatheter Aortic Valve ImplantationJACC: Case Reports, 2025
- Artificial intelligence-enhanced comprehensive assessment of the aortic valve stenosis continuum in echocardiographyEBioMedicine, 2025
- Obstruction in Hypertrophic Cardiomyopathy: Many FacesJournal of the American Society of Echocardiography, 2024
- Acute Hemodynamic Compromise After Transcatheter Aortic Valve Replacement Due to Dynamic Left Ventricle Obstruction: A Systematic ReviewThe American Journal of Cardiology, 2023
- Diagnosis and Evaluation of Hypertrophic CardiomyopathyJACC, 2022
- Recommendations for Cardiac Chamber Quantification by Echocardiography in Adults: An Update from the American Society of Echocardiography and the European Association of Cardiovascular ImagingJournal of the American Society of Echocardiography, 2015
- Suicide left ventricle following transcatheter aortic valve implantationCatheterization and Cardiovascular Interventions, 2010