Automated, High Accuracy Classification of Parkinsonian Disorders A Pattern Recognition Approach.docVIP

Automated, High Accuracy Classification of Parkinsonian Disorders: A Pattern Recognition Approach Andre F. Marquand , Maurizio Filippone , John Ashburner , Mark Girolami , Janaina Mourao-Miranda , 1* 2 3 4 1,4 Gareth J. Barker , Steven C. R. Williams , P. Nigel Leigh , Camilla R. V. Blain 1 1 5 1 1 Department of Neuroimaging, Centre for Neuroimaging Sciences, Institute of Psychiatry, King’s College London, London, United Kingdom, 2 School of Computing Science, University of Glasgow, Glasgow, United Kingdom, 3 Wellcome Trust Centre for Neuroimaging, University College London, London, United Kingdom, 4 Centre for Computational Statistics and Machine Learning, University College London, London, United Kingdom, 5 Brighton and Sussex Medical School, Trafford Centre for Biomedical Research, University of Sussex, Falmer, East Sussex, United Kingdom Abstract Progressive supranuclear palsy (PSP), multiple system atrophy (MSA) and idiopathic Parkinson’s disease (IPD) can be clinically indistinguishable, especially in the early stages, despite distinct patterns of molecular pathology. Structural neuroimaging holds promise for providing objective biomarkers for discriminating these diseases at the single subject level but all studies to date have reported incomplete separation of disease groups. In this study, we employed multi-class pattern recognition to assess the value of anatomical patterns derived from a widely available structural neuroimaging sequence for automated classification of these disorders. To achieve this, 17 patients wit