Digital Twin and Machine Learning Models to Enhance Planning and Outcomes of Thoracic Endovascular Aortic Repair Procedures

What this Trial Is About

Researchers are collecting clinical and anonymized CT images from patients undergoing Thoracic Endovascular Aortic Repair TEVAR to create detailed digital models, or digital twins, that simulate the procedure and train machine learning algorithms. This observational study aims to improve planning and prediction of TEVAR outcomes by supporting models that help select the best medical devices and anticipate complications. The study involves gathering patient-specific clinical and imaging data related to TEVAR, including augmenting anatomical information using statistical shape modeling to expand training datasets. High-quality digital twins will be developed to represent individual cases virtually. Machine learning models will be trained on these data to forecast procedural results and potential post-operative risks, enhancing both preoperative planning and postoperative assessment. Participants will undergo data collection including clinical information and detailed CT scans. Researchers will use this information to perform patient-specific numerical simulations and evaluate the accuracy of these models in replicating TEVAR outcomes over one year. The study also tracks how well the machine learning models predict complications after the procedure. Participation duration and follow-up extend up to one year to assess these outcomes comprehensively.

Digital Twin and Ml-basEd MOdel of TEVAR Interventions