{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"submitter":["Pettersson-Yeo W"],"funding":["Wellcome Trust"],"pagination":["189"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC4097812"],"repository":["biostudies-literature"],"omics_type":["Unknown"],"volume":["8"],"pubmed_abstract":["In the pursuit of clinical utility, neuroimaging researchers of psychiatric and neurological illness are increasingly using analyses, such as support vector machine, that allow inference at the single-subject level. Recent studies employing single-modality data, however, suggest that classification accuracies must be improved for such utility to be realized. One possible solution is to integrate different data types to provide a single combined output classification; either by generating a single decision function based on an integrated kernel matrix, or, by creating an ensemble of multiple single modality classifiers and integrating their predictions. Here, we describe four integrative approaches: (1) an un-weighted sum of kernels, (2) multi-kernel learning, (3) prediction averaging, and "],"journal":["Frontiers in neuroscience"],"pubmed_title":["An empirical comparison of different approaches for combining multimodal neuroimaging data with support vector machine."],"pmcid":["PMC4097812"],"funding_grant_id":["WT088641/Z/09/Z","WT085390/Z/08/Z"],"pubmed_authors":["McGuire P","Pettersson-Yeo W","Mechelli A","Catani M","Marquand AF","Benetti S","Allen P","Joules R","Williams SC"],"additional_accession":[]},"is_claimable":false,"name":"An empirical comparison of different approaches for combining multimodal neuroimaging data with support vector machine.","description":"In the pursuit of clinical utility, neuroimaging researchers of psychiatric and neurological illness are increasingly using analyses, such as support vector machine, that allow inference at the single-subject level. Recent studies employing single-modality data, however, suggest that classification accuracies must be improved for such utility to be realized. One possible solution is to integrate different data types to provide a single combined output classification; either by generating a single decision function based on an integrated kernel matrix, or, by creating an ensemble of multiple single modality classifiers and integrating their predictions. Here, we describe four integrative approaches: (1) an un-weighted sum of kernels, (2) multi-kernel learning, (3) prediction averaging, and ","dates":{"release":"2014-01-01T00:00:00Z","publication":"2014","modification":"2025-04-22T00:59:50.653Z","creation":"2019-03-27T01:32:04Z"},"accession":"S-EPMC4097812","cross_references":{"pubmed":["25076868"],"doi":["10.3389/fnins.2014.00189"]}}