Gaussian process classification of Alzheimer's disease and mild cognitive impairment from resting state fMRI
Edward Challis 1,2 , Barbara Spano 3 , Laura Serra 3 , Marco Bozzali 3 , Seb Oliver 1 , and Mara Cercignani 2
Physics and Astronomy, University of Sussex,
Brighton, Sussex, United Kingdom,
Imaging Sciences Centre, Brighton and Sussex Medical
School, Brighton, Sussex, United Kingdom,
Laboratory, IRCSS Santa Lucia, Rome, Italy
Statistical machine learning techniques are seeing
increased interest by the neuroimaging community.
Simultaneously clinicians and researchers are also
studying the functional connectivity patterns of brains
and how these relations might change in conditions like
Alzheimers disease or clinical depression. In this
study we investigate the performance of Gaussian process
classifiers to perform patient stratification from
functional connectivity patterns of brains at rest. The
majority of previous approaches to such problems have
focused on using support vector machines to perform
classification in this setting. Our results confirm that
Gaussian process classifiers form a promising direction
for future research.
This abstract and the presentation materials are available to members only;
a login is required.