Artificial intelligence to predict complications after abdominal aortic endoprosthesis
Implantation of an Endovascular Prosthesis for the Treatment of Abdominal Aortic Aneurysms: Use of a Machine Learning Model From CT Images to Predict Complications
This project will try an AI tool to predict endoleaks and other complications from CT and angiography images in people treated with an abdominal aortic endoprosthesis.
Quick facts
| Study type | Observational |
|---|---|
| Enrollment | 300 (estimated) |
| Ages | 18 Years and up |
| Sex | All |
| Sponsor | Groupe Hospitalier de la Rochelle Ré Aunis Academic / other |
| Locations | 1 site (La Rochelle) |
| Trial ID | NCT06884397 on ClinicalTrials.gov |
What this trial studies
This observational effort uses routine CT and angiography images from patients who received an abdominal aortic endoprosthesis to train and test a machine‑learning algorithm to predict post‑procedure complications such as endoleak. Patients treated and followed at Groupe Hospitalier de la Rochelle Ré Aunis who meet inclusion criteria will provide the imaging and outcome data, with exclusions for intraoperative embolization of the inferior mesenteric artery or aneurysm sac. The algorithm will be developed on retrospective image sets and validated on separate patient scans by comparing predictions to documented clinical outcomes. The aim is to automate image analysis to improve detection and risk stratification during long‑term follow‑up.
Who should consider this trial
Good fit: Adults treated for an infrarenal abdominal aortic aneurysm with an endovascular endoprosthesis who have follow‑up CT or angiography imaging and did not undergo intraoperative embolization of the inferior mesenteric artery or aneurysm sac are the ideal candidates.
Not a fit: Patients who had open surgical repair instead of an endovascular prosthesis, those without suitable imaging or follow‑up, or those who underwent intraoperative embolization are unlikely to benefit from this AI approach.
Why it matters
Potential benefit: If successful, the tool could identify patients at higher risk of endoleak earlier, allowing targeted follow‑up and quicker treatment to reduce complications.
How similar studies have performed: Previous small studies using machine learning on CT images have shown promising results for detecting or predicting endoleak, but large prospective validation remains limited.
Eligibility criteria
Show full inclusion / exclusion criteria
Inclusion Criteria: * Treated for an abdominal aortic aneurysm through endovascular prosthesis implantation Exclusion Criteria: * Underwent intraoperative embolization of the inferior mesenteric artery or aneurysmal sac * Refuse the use of their data
Where this trial is running
La Rochelle
- Groupe Hospitalier de la Rochelle Ré Aunis — La Rochelle, France (Recruiting)
Study contacts
- Study coordinator: Caroline Allix-Béguec, Ph.D.
- Email: caroline.allix-beguec@ght-atlantique17.fr
- Phone: +33516494246
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.