Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Reported safety events from ultrasound enhancing agents: a critical reappraisal.

Echo research and practice·2026

Same author

Advancing Quality in the Evaluation, Surveillance, and Management of Aortic Stenosis: A Report From the AHA Target: AS Registry.

Circulation·2026

Same author

Redo-TAVR (TAV-in-TAV) Best Practices Part 1: Short-in-Short and Short-in-Tall - A Heart and Valve Collaboratory Document.

JACC. Cardiovascular interventions·2026

Same author

Redo-TAVR (TAV-in-TAV) Best Practices Part 2: Tall-in-Short and Tall-in-Tall - A Heart and Valve Collaboratory Document.

JACC. Cardiovascular interventions·2026

Same author

A novel computational method to predict hypoattenuated leaflet thickening post-transcatheter aortic valve replacement using preprocedural computed tomography scans.

JTCVS structural and endovascular·2026

Same author

Comparative Analysis of Leaflet Materials, Stent Materials, and Stent Cell Density for Bileaflet Transcatheter Mitral Valve Design.

Annals of biomedical engineering·2026

Search research articles

Related Experiment Video

Updated: May 9, 2025

A Simplified Stepwise Approach to Echo Guidance during Percutaneous Mitral Valve Repair

A Simplified Stepwise Approach to Echo Guidance during Percutaneous Mitral Valve Repair

Published on: October 16, 2021

Machine learning methods to predict transvalvular gradient waveform post-transcatheter aortic valve replacement using

Wenyuan Song¹, Taylor Sirset-Becker², Luis René Mata Quinonez³

¹School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, Ga; Department of Biomedical Engineering, Georgia Institute of Technology and Emory University, Atlanta, Ga.

The Journal of Thoracic and Cardiovascular Surgery

|May 4, 2025

Summary

A new machine learning model predicts transcatheter aortic valve replacement (TAVR) pressure gradients using preprocedural data. This AI-driven approach enhances accuracy, potentially improving patient outcomes and guiding clinical decisions.

Keywords:

deep machine learning generative active learning generative artificial intelligence predictive surgical planning pressure gradient transcatheter aortic valve implantation/replacement

More Related Videos

Noninvasive Determination of Vortex Formation Time Using Transesophageal Echocardiography During Cardiac Surgery

Noninvasive Determination of Vortex Formation Time Using Transesophageal Echocardiography During Cardiac Surgery

Published on: November 28, 2018

Four-Dimensional Computed Tomography-Guided Valve Sizing for Transcatheter Pulmonary Valve Replacement

Four-Dimensional Computed Tomography-Guided Valve Sizing for Transcatheter Pulmonary Valve Replacement

Published on: January 20, 2022

Related Experiment Videos

Last Updated: May 9, 2025

A Simplified Stepwise Approach to Echo Guidance during Percutaneous Mitral Valve Repair

A Simplified Stepwise Approach to Echo Guidance during Percutaneous Mitral Valve Repair

Published on: October 16, 2021

Noninvasive Determination of Vortex Formation Time Using Transesophageal Echocardiography During Cardiac Surgery

Noninvasive Determination of Vortex Formation Time Using Transesophageal Echocardiography During Cardiac Surgery

Published on: November 28, 2018

Four-Dimensional Computed Tomography-Guided Valve Sizing for Transcatheter Pulmonary Valve Replacement

Four-Dimensional Computed Tomography-Guided Valve Sizing for Transcatheter Pulmonary Valve Replacement

Published on: January 20, 2022

Area of Science:

Cardiovascular Medicine
Artificial Intelligence in Healthcare
Medical Imaging Analysis

Background:

Transcatheter aortic valve replacement (TAVR) effectiveness is assessed by post-procedural transvalvular pressure gradients.
Predicting these gradients pre-procedure can optimize TAVR outcomes and patient management.
Current methods for gradient prediction lack precision and advanced analytical capabilities.

Purpose of the Study:

To develop a novel machine learning (ML) method using generative artificial intelligence (AI) and smart data selection.
To predict the post-TAVR gradient waveform accurately using preprocedural Doppler echocardiogram data.
To enhance the predictive power of ML models for TAVR gradient waveforms.

Main Methods:

A deep ML model was trained on data from 110 TAVR patients.
The model utilized a generative active learning framework to predict post-TAVR gradients from pre-TAVR data.
Smart data selection strategies were incorporated to improve model performance.

Main Results:

The ML model achieved an average prediction accuracy of 84.85% (relative mean absolute error).
Generative AI improved accuracy by 3.11%; data selection enhanced it by 16.03% over baseline ML.
Bland-Altman analysis confirmed strong agreement between predicted and measured pressure gradients.

Conclusions:

A deep, generative, active ML model can predict post-TAVR time-varying pressure gradients from preprocedural Doppler echocardiograms.
This predictive capability may aid in preventing TAVR complications and guiding clinical decisions.
Further research is needed for other valve types to explore gradient changes.