Online Learning for Classification of Alzheimer Disease based on Cortical Thickness and Hippocampal Shape Analysis

• DOI: 10.4258/hir.2014.20.1.61
• Publication Date: 2014-03-05T01:17:02Z
• Authors: Ga-Young Lee; Jeonghun Kim; Ju Han Kim; Kiwoong Kim; Joon-Kyung Seong
• Keywords: Supervised Learning

Mobile healthcare applications are becoming a growing trend. Also, the prevalence of dementia in modern society is showing steady Among degenerative brain diseases that cause dementia, Alzheimer disease (AD) most common. The purpose this study was to identify AD patients using magnetic resonance imaging mobile environment.We propose an incremental classification for systems. Our method based on learning diagnosis and prediction cortical thickness data hippocampus shape. We constructed classifier principal component analysis linear discriminant analysis. performed initial subject classification. Initial group part our server. smartphone agent implements shows various results.With use alone, discrimination accuracy 87.33% (sensitivity 96.49% specificity 64.33%). When hippocampal shape were analyzed together, achieved 87.52% 96.79% 63.24%).In paper, we presented online by employing both data. implemented devices discriminated normal group.