Ensemble of random forests One vs. Rest classifiers for MCI and AD prediction using ANOVA cortical and subcortical feature selection and partial least squares

• Published in: Journal of neuroscience methods Vol. 302; pp. 47 - 57
• Main Authors: Ramírez, J., Górriz, J.M., Ortiz, A., Martínez-Murcia, F.J., Segovia, F., Salas-Gonzalez, D., Castillo-Barnes, D., Illán, I.A., Puntonet, C.G.
• Format: Journal Article
• Language: English
• Published: Netherlands Elsevier B.V 15.05.2018
• Subjects: Aged; Alzheimer Disease - classification; Alzheimer Disease - diagnostic imaging; Alzheimer Disease - pathology; Alzheimer's disease; Analysis of Variance; ANOVA feature selection; Bagging; Brain - diagnostic imaging; Brain - pathology; Cognitive Dysfunction - classification; Cognitive Dysfunction - diagnostic imaging; Cognitive Dysfunction - pathology; Computer-aided diagnosis; Databases, Factual; Decision Trees; Disease Progression; Female; Humans; Image Interpretation, Computer-Assisted - methods; Least-Squares Analysis; Machine Learning; Magnetic Resonance Imaging; Male; Mild cognitive impairment; One vs. Rest classification; Partial least squares; Pattern Recognition, Automated; Random forests; Magnetic resonance imaging; Mild cognitive impairment; One vs. Rest classification; Machine learning; ANOVA feature selection; Alzheimer's disease; Partial least squares; Computer-aided diagnosis; Random forests; Bagging

[Display omitted] •Mild cognitive impairment prediction method based on an ensemble of one vs. all multi-class classifier.•Revised ANOVA feature selection method of MRI cortical and subcortical features.•Feature dimension reduction via multi-class partial least squares. Alzheimer's disease (AD)...