Identifying endophenotypes of autism: a multivariate approach
MetadataShow full item record
AuthorSegovia Román, Fermín; Holt, Rosemary; Spencer, Michael; Górriz Sáez, Juan Manuel; Ramírez Pérez de Inestrosa, Javier; Puntonet, Carlos G.; Phillips, Christophe; Chura, Lindsay; Baron-Cohen, Simon; Suckling, John
Autism spectrum conditionMRISupport vector machineSearchlightEndophenotype
Segovia, F.; et al. Identifying endophenotypes of autism: a multivariate approach. Frontiers in Computational Neuroscience, 8: 60 (2014). [http://hdl.handle.net/10481/32371]
SponsorshipThis work was partly supported by the University of Granada under the Genil PYR2012-10 project (CEI BioTIC GENIL CEB09-0010) and the University of Liège. The study was also funded by a Clinical Scientist Fellowship from the UK Medical Research Council (MRC (G0701919)) to Michael Spencer and by the UK National Institute for Health Research Cambridge Biomedical Research Centre.
The existence of an endophenotype of autism spectrum condition (ASC) has been recently suggested by several commentators. It can be estimated by finding differences between controls and people with ASC that are also present when comparing controls and the unaffected siblings of ASC individuals. In this work, we used a multivariate methodology applied on magnetic resonance images to look for such differences. The proposed procedure consists of combining a searchlight approach and a support vector machine classifier to identify the differences between three groups of participants in pairwise comparisons: controls, people with ASC and their unaffected siblings. Then we compared those differences selecting spatially collocated as candidate endophenotypes of ASC.