Using AI to improve planning for transcatheter heart valve procedures
Enhanced Valves Interventions and Safe AI Generated End Results
This project uses AI to analyze CT and echo images to see if it can better predict outcomes for people who had transcatheter aortic, mitral, or tricuspid valve procedures.
Quick facts
| Study type | Observational |
|---|---|
| Enrollment | 21000 (estimated) |
| Ages | 18 Years and up |
| Sex | All |
| Sponsor | Montreal Heart Institute Academic / other |
| Locations | 15 sites (New York, New York and 14 other locations) |
| Trial ID | NCT07213531 on ClinicalTrials.gov |
What this trial studies
This is a non-interventional, retrospective, multicenter project that applies deep learning (including convolutional neural networks) to multi-slice cardiac CT and vendor-specific transesophageal echocardiography to automate segmentation and measurements. The AI framework combines these imaging-derived measurements with pre-procedural clinical data to predict procedural success for TAVI, TMVI, TTVI, and M-TEER. The work aims to standardize measurements, reduce inter-observer variability, and support patient selection and procedural planning. Data are collected from specialized centers worldwide and processed centrally for validation of the predictive models.
Who should consider this trial
Good fit: Adults who underwent TAVI, TMVI, TTVI, or M-TEER with the specified device generations and who have high-quality pre-procedural ECG-gated CT or vendor-specific TEE image datasets available are ideal candidates for inclusion.
Not a fit: Patients without high-quality pre-procedural CT or TEE images, those treated with unsupported/older device generations, or with incomplete clinical data are unlikely to benefit from the AI predictions.
Why it matters
Potential benefit: If successful, this could help doctors choose the best patients and plan transcatheter valve procedures more accurately, potentially reducing complications and improving outcomes.
How similar studies have performed: Previous smaller studies have shown promising results for AI-based cardiac image segmentation and outcome prediction, but broad multicenter validation across multiple valve types is still limited.
Eligibility criteria
Show full inclusion / exclusion criteria
Inclusion Criteria: Patients who have reached the age of legal majority under local laws. * For TAVI group: All patients who have had TAVI with a third generation transcatheter heart valve (THV), with an available pre-procedural optimal quality CT scan as defined by an ECG- gating CT with: 1. five to ten image volumes at cardiac phases from 5% to 95% R-R 2. 0.625 mm slice thickness 3. 0.625 mm spacing between slices 4. 0.88 mm in-plane pixel spacing * For TMVI group: Patients who have had a TMVI with a dedicated device and screen failures, with an available optimal quality CT scan. * For TTVI group: Patients who have had a TTVI with a dedicated device and screen failures, with an available optimal quality CT scan. * For M-TEER: All patient who have had a M-TEER with 1) G4 or newer iteration of MitraClip or 2) G2 or newer iteration of Pascal, with available pre-procedural TEE videos images from one of two vendors: Phillips or GE, with clear identifiable views of the Mitral valve, frame per second equal or higher than 40 frames per second, acceptable 3D reconstructions. * For T-TEER: All patient who have had a T-TEER with G4 or newer iteration of TriClip or 2) G2 or newer iteration of Pascal, with available pre-procedural TEE videos images from one of two vendors: Phillips or GE, with clear identifiable views of the Tricuspid valve, frame per second equal or higher than 40 frames per second, acceptable transgastric image with acceptable 3D reconstructions. Exclusion Criteria: * For TAVI group: Valve-in-valve procedures * For TMVI group: Valve-in-valve and valve-in-ring procedures * For TTVI: Valve-in-valve and valve-in-ring procedures * For M-TEER: G3 or older MitraClip, G1 Pascal * For T-TEER: G3 Triclip, G1 Pascal
Where this trial is running
New York, New York and 14 other locations
- Montefiore Medical Center New York — New York, New York, United States (Recruiting)
- Montreal Heart Institute, 5000 Rue Bélanger, Montréal — Montreal, Quebec, Canada (Recruiting)
- St Michael's Hospital Toronto — Toronto, Canada (Recruiting)
- St Paul's Hospital Vancouver — Vancouver, Canada (Recruiting)
- Centre Hospitalier Universitaire (CHU) de Bordeaux, 12 rue Dubernat 33404 Talence cedex — Bourdeaux, France (Recruiting)
- CHU Lille — Lille, France (Recruiting)
- CHU Marseille — Marseille, France (Recruiting)
- Centre Cardiologique du Nord Paris — Paris, France (Recruiting)
- Institut Cardiovasculaire Paris-Sud Paris — Paris, France (Recruiting)
- Centre Hospitalier Universitaire Rennes — Rennes, France (Recruiting)
- Clinque Pasteur Toulouse - France — Toulouse, France (Recruiting)
- University Medical Center Hamburg-Eppendorf — Hamburg, Germany (Recruiting)
- Heart Valve Center Mainz — Mainz, Germany (Recruiting)
- Istituto Clinico Città di Brescia — Brescia, Italy (Recruiting)
- San Raffaele Heart Valve Center Milan — Milan, Italy (Recruiting)
Study contacts
- Principal investigator: Thomas Modine, MD, PhD — University Hospital Bordeaux, France
- Study coordinator: Thomas Modine, MD, PhD
- Email: thomasmodine@gmail.com
- Phone: +33(0)5 25 377541
How to participate
- Review the eligibility criteria above with your treating physician.
- Visit the official trial page on ClinicalTrials.gov for the most current contact information and recruitment status.
- Contact the listed study coordinator or principal investigator to request pre-screening. Pre-screening is free and never obligates you to enroll.