A narrative review of artificial intelligence applications in type B aortic dissection

Artificial intelligence (AI) has emerged as a transformative tool in the management of aortic dissection, particularly type B aortic dissection (TBAD), in which diagnosis, risk stratification, and procedural decision-making remain complex and time sensitive. This narrative review aims to synthesize current evidence and highlight evolving applications of AI, including machine learning, deep learning, and computational modeling, across the continuum of TBAD care. AI-driven computer vision models have demonstrated high accuracy in automated detection, classification, and segmentation of aortic dissections, significantly accelerating diagnostic workflows. Furthermore, predictive algorithms show promise in forecasting aortic remodeling, false lumen progression, and long-term aneurysmal degeneration. Further integration of AI with computational fluid dynamics has enabled the rapid simulation of patient-specific hemodynamics, offering insights into disease progression and treatment planning with markedly reduced processing time. Emerging work in multinomics, powered by machine learning, may also enhance precision medicine approaches by improving early detection and monitoring of post-thoracic endovascular aortic repair remodeling. Early studies suggest potential roles for reinforcement learning and continuous physiologic data modeling in mitigating spinal cord ischemia risk and supporting personalized clinical decisions. Our review underscores ethical considerations related to data privacy, equitable model development, and multi-institutional standardization. Collectively, these advancements highlight the expanding role of AI in augmenting clinical expertise and shaping future personalized approaches to TBAD care.