Random forest prediction of Alzheimer’s disease using pairwise selection from time series data

• Published in: PloS one Vol. 14; no. 2; p. e0211558
• Main Authors: Moore, P. J., Lyons, T. J., Gallacher, J.
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 14.02.2019; Public Library of Science (PLoS)
• Subjects: Age; Aged; Aged, 80 and over; Alzheimer Disease - diagnostic imaging; Alzheimer's disease; Alzheimers disease; Artificial intelligence; Benchmarking; Biology and Life Sciences; Biomarkers; Brain research; Classification; Cognition & reasoning; Cognitive ability; Computer and Information Sciences; Data points; Data processing; Dementia; Demographic variables; Demographics; Diagnosis; Diagnostic imaging; Disease Progression; Family medical history; Female; Health risks; Humans; Image Interpretation, Computer-Assisted; Machine Learning; Magnetic Resonance Imaging; Male; Management; Medical diagnosis; Medical imaging; Medical records; Medical research; Medicine and Health Sciences; Memory; Middle Aged; Neuroimaging; Neurology; Neurosciences; NMR; Nuclear magnetic resonance; Pattern Recognition, Automated; Physical Sciences; Research and Analysis Methods; Test procedures; Time dependence; Time series; United Kingdom > UK

Time-dependent data collected in studies of Alzheimer's disease usually has missing and irregularly sampled data points. For this reason time series methods which assume regular sampling cannot be applied directly to the data without a pre-processing step. In this paper we use a random forest t...