MINING DATA FROM CFD SIMULATIONS FOR ANEURYSM AND CAROTID BIFURCATION MODELS
 
N.Janković, M.Radović, D.Petrović, N.Zdravković and N.Filipović (UDC: 53(497.11)"1972/2012")
Abstract:
Arterial geometry variability is present both within and across individuals. To analyze the influence of geometric parameters, blood density, dynamic viscosity and blood velocity on wall shear stress (WSS) distribution in the human carotid artery bifurcation and aneurysm, the computer simulations were run to generate the data pertaining to this phenomenon. In our work we evaluate two prediction models for modeling these relationships: neural network model and k-nearest neighbor model. The results revealed that both models have high prediction ability for this prediction task. The achieved results represent progress in assessment of stroke risk for a given patient data in real time.