Hybrid multivariate pattern analysis combined with extreme learning machine for Alzheimer’s dementia diagnosis using multi-measure rs-fMRI spatial patterns

• Published in: PloS one Vol. 14; no. 2; p. e0212582
• Main Authors: Nguyen, Duc Thanh, Ryu, Seungjun, Qureshi, Muhammad Naveed Iqbal, Choi, Min, Lee, Kun Ho, Lee, Boreom
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 22.02.2019; Public Library of Science (PLoS)
• Subjects: Advertising executives; Aged; Aged, 80 and over; Aging; Alzheimer Disease - diagnostic imaging; Alzheimer's disease; Artificial intelligence; Attention; Basis functions; Biological markers; Biology and Life Sciences; Biomarkers; Brain; Brain Mapping; Brain research; Classification; Cognitive ability; Cognitive disorders; Cognitive Dysfunction - diagnostic imaging; Computer and Information Sciences; Dementia; Dementia disorders; Diagnosis; Diagnostic imaging; Discrimination; Engineering; Female; Functional magnetic resonance imaging; Humans; Learning algorithms; Machine learning; Magnetic Resonance Imaging; Male; Medical diagnosis; Medical imaging; Medicine and Health Sciences; Memory; Methods; Multivariate analysis; Neural networks; Neuroimaging; Neurology; NMR; Nuclear magnetic resonance; Pattern analysis; Principal components analysis; Radial basis function; Republic of Korea; Research and Analysis Methods; Statistical analysis; Studies; Support Vector Machine; Support vector machines; Republic of Korea; Canada; Montreal Quebec Canada; South Korea
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0212582

Early diagnosis of Alzheimer's disease (AD) and Mild Cognitive Impairment (MCI) is essential for timely treatment. Machine learning and multivariate pattern analysis (MVPA) for the diagnosis of brain disorders are explicitly attracting attention in the neuroimaging community. In this paper, we propose a voxel-wise discriminative framework applied to multi-measure resting-state fMRI (rs-fMRI) that integrates hybrid MVPA and extreme learning machine (ELM) for the automated discrimination of AD and MCI from the cognitive normal (CN) state. We used two rs-fMRI cohorts: the public Alzheimer's disease Neuroimaging Initiative database (ADNI2) and an in-house Alzheimer's disease cohort from South Korea, both including individuals with AD, MCI, and normal controls. After extracting three-dimensional (3-D) patterns measuring regional coherence and functional connectivity during the resting state, we performed univariate statistical t-tests to generate a 3-D mask that retained only voxels showing significant changes. Given the initial univariate features, to enhance discriminative patterns, we implemented MVPA feature reduction using support vector machine-recursive feature elimination (SVM-RFE), and least absolute shrinkage and selection operator (LASSO), in combination with the univariate t-test. Classifications were performed by an ELM, and its efficiency was compared to linear and nonlinear (radial basis function) SVMs. The maximal accuracies achieved by the method in the ADNI2 cohort were 98.86% (p<0.001) and 98.57% (p<0.001) for AD and MCI vs. CN, respectively. In the in-house cohort, the same accuracies were 98.70% (p<0.001) and 94.16% (p<0.001). From a clinical perspective, combining extreme learning machine and hybrid MVPA applied on concatenations of multiple rs-fMRI biomarkers can potentially assist the clinicians in AD and MCI diagnosis.