Spontaneous vertebral artery dissecting aneurysms (SVADAs) are rare, non-traumatic arterial dissections characterized by intramural hematoma and/or aneurysmal dilatation, typically associated with hypertension and loss of structural integrity of the vessel wall [1], [2], [3]. The hemodynamic mechanisms driving their formation, growth, and rupture are poorly understood, the most common cause of SVADAs being idiopathic [4]. Using computational fluid dynamics (CFD), our study aimed to investigate the pathophysiological roles of the kinematic pressure and wall shear stress (WSS) distributions prior to and following SVADA formation. However, running CFD is computationally intensive and may require significant resources to numerically solve the Navier-Stokes equations [5]. In this work, we also demonstrate how neural networks can provide an accurate alternative to costly CFD. This methodology may make patient specific CFD more tenable for neurosurgical practice.