Using support vector machines with multiple indices of diffusion for automated classification of mild cognitive impairment

• Published in: PloS one Vol. 7; no. 2; p. e32441
• Main Authors: O'Dwyer, Laurence, Lamberton, Franck, Bokde, Arun L W, Ewers, Michael, Faluyi, Yetunde O, Tanner, Colby, Mazoyer, Bernard, O'Neill, Desmond, Bartley, Máiréad, Collins, D Rónán, Coughlan, Tara, Prvulovic, David, Hampel, Harald
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 23.02.2012; Public Library of Science (PLoS)
• Subjects: Activities of daily living; Aged; Aging; Algorithms; Alzheimer Disease - diagnosis; Alzheimer Disease - pathology; Alzheimer's disease; Alzheimers disease; Anisotropy; Artificial intelligence; Automation; Biology; Brain research; Classification; Cognition Disorders - diagnosis; Cognition Disorders - pathology; Cognitive ability; Cognitive Dysfunction - diagnosis; Cognitive Dysfunction - pathology; Cognitive science; Data mining; Dementia; Diagnosis, Computer-Assisted - methods; Diffusion; Diffusion Tensor Imaging - methods; Female; Gerontology; Hospitals; Humans; Impairment; Learning algorithms; Machine learning; Magnetic resonance imaging; Magnetic Resonance Imaging - methods; Male; Medical imaging; Medicine; Middle Aged; Neurodegenerative diseases; Neuropathology; Neuroscience; Neurosciences; NMR; Nuclear magnetic resonance; Older people; Principal components analysis; Psychiatry; Psychosomatic medicine; Psychotherapy; Sensitivity and Specificity; Signal Processing, Computer-Assisted; Studies; Substantia alba; Support Vector Machine; Support vector machines; Volumetric analysis; San Francisco California; United Kingdom > UK; United States > US; Ireland; California; France; Germany
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0032441

Few studies have looked at the potential of using diffusion tensor imaging (DTI) in conjunction with machine learning algorithms in order to automate the classification of healthy older subjects and subjects with mild cognitive impairment (MCI). Here we apply DTI to 40 healthy older subjects and 33 MCI subjects in order to derive values for multiple indices of diffusion within the white matter voxels of each subject. DTI measures were then used together with support vector machines (SVMs) to classify control and MCI subjects. Greater than 90% sensitivity and specificity was achieved using this method, demonstrating the potential of a joint DTI and SVM pipeline for fast, objective classification of healthy older and MCI subjects. Such tools may be useful for large scale drug trials in Alzheimer's disease where the early identification of subjects with MCI is critical.