This study proposes a retrospective analysis that systematically integrates multidimensional biomechanical and anatomical data to construct an early and accurate predictive model for adverse aortic remodeling following thoracic endovascular aortic repair (TEVAR) in patients with Type B aortic dissection (TBAD). Postoperative follow-up CTA images will be analyzed using vascular deformation mapping (VDM) technology, which enables quantitative assessment of regional aortic deformation and strain evolution through high-precision three-dimensional registration, thereby overcoming the limitations of conventional diameter-based measurements. Concurrently, patient-specific computational fluid dynamics (CFD) models will be reconstructed from preoperative CTA data to simulate the hemodynamic environment within the dissected aorta, extracting key parameters including wall shear stress, flow velocity, and pressure distribution to quantify the mechanical forces driving vascular remodeling. Furthermore, the anatomical characteristics of entry tears-including their number, spatial distribution, and size-will be systematically characterized. By integrating these three dimensions of indicators and employing multivariable regression and machine learning algorithms, independent risk factors significantly associated with adverse events such as false lumen aneurysmal expansion, aortic rupture, and recurrent dissection will be identified, ultimately establishing a comprehensive predictive model that combines sensitivity, objectivity, and clinical feasibility. The development of this model is expected to provide clinicians with quantitative decision support for early identification of high-risk patients, formulation of individualized surveillance strategies, and implementation of timely interventions, thereby substantially improving the long-term prognosis and quality of life for TBAD patients following TEVAR.