Abstract Multiple patient-specific parameters such as wall thickness, wall strength, and constitutive proper- ties, are required for the computational assessment of abdominal aortic aneurysm (AAA) rupture risk. Unfor- tunately, many of these quantities are not easily acces- sible and could only be determined by invasive proce- dures, rendering a computational rupture risk assess- ment obsolete. This study investigates two different approaches to predict these quantities using regression models in combination with a multitude of non-invasively accessible, explanatory variables. We have gathered a large dataset comprising tensile tests performed with AAA specimens and supplementary patient informa- tion based on blood analysis, the patients medical his- tory, and geometric features of the AAAs. Using this unique database we harness the capability of state-of- the-art Bayesian regression techniques to infer probabilistic models for multiple quantities of interest. After a brief presentation of our experimental results, we show that we can effectively reduce the predictive uncertainty in the assessment of several patient-specific parameters, most importantly in thickness and failure strength of the AAA wall. Thereby, the more elabo- rate Bayesian regression approach based on Gaussian processes consistently outperforms standard linear re- gression. Moreover, we show that previously proposed models for the wall strength perform poorly with our dataset.     «

Abstract Multiple patient-specific parameters such as wall thickness, wall strength, and constitutive proper- ties, are required for the computational assessment of abdominal aortic aneurysm (AAA) rupture risk. Unfor- tunately, many of these quantities are not easily acces- sible and could only be determined by invasive proce- dures, rendering a computational rupture risk assess- ment obsolete. This study investigates two different approaches to predict these quantities using regression models...     »