Digital Twin and Ml-basEd MOdel of TEVAR Interventions
Trial statusRecruiting
Trial phaseNot listed
Trial typeObservational
Biological sexAll
Age18+
SponsorFondazione IRCCS Ca' Granda, Ospedale Maggiore Policlinico
About this trial
The study aims to collect clinical data and pseudonymized CT images of patients undergoing TEVAR in order to create an anatomical digital twin capable of simulating procedural outcomes and training machine learning (ML) algorithms. This approach will support predictive models that may assist physicians in selecting the optimal medical device, improving pre-TEVAR planning, and predicting post-TEVAR complications.
Eligibility criteria
This trial does not accept healthy volunteersQualifiers
≥18 Years and older (Adult, Older Adult)
Female and male
Received TEVAR for: Chronic or acute dissection, Aneurysm, Penetrating aortic ulcer, aortic thrombus, intramural hematoma or traumatic injury
Disqualifiers
Younger than 18 years old
Received TEVAR in surgical graft that replaced native aorta
Poor CT image quality that leads to failure in generating a high-fidelity 3D FE model of patient anatomy (no preoperative multidetector contrast-enhanced CT-scan available, preoperative CTscan slice thickness greater than 1mm, preoperative CT-scan with artifacts, motion artifacts due to the presence of other implanted devices affecting the region of interest)
Trial population
patients undergoing TEVAR
Trial design
Design model
Cohort
Time perspective
Retrospective
Treatments tested in this trial
Not listed
Trial groups
No trial groups listed
Trial outcomes
Primary outcomes
1
Determine the accuracy of patient-specific numerical simulations in replicating TEVAR deployment outcomes
Accuracy of the simulations, expressed in terms of the match between simulated and post-operative device-vessel interaction (e.g., configuration, sealing quality, apposition), as assessed via comparison of post-operative CT image with the simulation results
Time frame
up to 1 yearSecondary outcomes
1
Assess the predictive performance of the ML model in forecasting clinical complications
Sensitivity, specificity, and AUC of the model in predicting complications using retrospective clinical follow-up data
Time frame
up to 1 yearSponsors and contacts
Click on the lead sponsor to view all of their trials.
Source ClinicalTrials.gov