Frank J. Veith and Rasit Dinc presented new expert insights on the role of advancing artificial intelligence (AI) technologies in contemporary vascular medicine during a featured session at the 52nd annual VEITH Symposium. Their discussion outlined how emerging computational platforms may influence clinical decision-making, procedural planning, and long-term outcomes across endovascular care.

Delivered at one of the field's leading global forums, the session highlighted the growing importance of AI-enabled imaging, simulation, and digital workflow tools within vascular surgery and interventional practice. The VEITH Symposium, held in academic partnership with the Cleveland Clinic, continues to serve as a platform for introducing new advancements and shaping international perspectives on the future of vascular innovation.

The five-day meeting, known for its concise, rapid-fire presentations, draws thousands of vascular surgeons, interventional cardiologists, radiologists, and allied specialists from around the world. This year's program underscored a marked expansion in sessions dedicated to AI, digital workflow integration, intravascular imaging, and computational modelling, reflecting their rising impact on clinical practice.

Dinc, whose work on AI-enhanced intravascular imaging and endovascular planning has earned international attention, outlined how machine-learning algorithms and three-dimensional virtual modelling are beginning to optimise precision in complex vascular procedures.

In his remarks, Dinc emphasised that AI should be viewed as a decision-support engine rather than a replacement for clinical expertise. By integrating patient-specific imaging with computational simulation, he noted, clinicians can virtually test procedural scenarios before entering the operating room.

"Digitally evaluating potential treatment pathways in advance can reduce complication rates and improve procedural predictability, particularly in high-risk cases," Rasit Dinc stated.

He explained that AI-driven simulation platforms hold significant value for the management of aortic aneurysms, peripheral artery disease, and complex vascular lesions, where anatomy and pathology vary widely across patients. Machine-learning systems trained on extensive clinical datasets can compare thousands of analogous cases and propose strategies associated with optimal outcomes.