Events and Meetings of Italian Statistical Society, Advances in Latent Variables - Methods, Models and Applications

Font Size: 
Studying hemodynamic forces via spatial regression models over non-planar domains
Bree Ettinger, Simona Perotto, Laura M. Sangalli

Last modified: 2013-06-16

Abstract


In this paper, we analyze hemodynamic forces exerted by blood-flow over the wall of an internal carotid artery affected by an aneurysm. The aim of this study is to enhance the still limited knowledge of aneurysmal pathology. To analyze such data, we use a recently proposed spatial regression model for data occurring over bi-dimensional Riemmanian manifolds. This model is a generalized additive model, able to account for the complexity of the non-planar domain and incorporate spacevarying covariate information. The estimators have the typical penalized regression form and are linear in the observed data values; classical inferential tools are available.

Full Text: PDF