A supervised method to assist the diagnosis and classification of the status of Alzheimer's disease using data from an fMRI experiment

Evanthia E Tripoliti; Dimitrios I Fotiadis; Maria Argyropoulou

doi:10.1109/IEMBS.2008.4650191

A supervised method to assist the diagnosis and classification of the status of Alzheimer's disease using data from an fMRI experiment

Annu Int Conf IEEE Eng Med Biol Soc. 2008:2008:4419-22. doi: 10.1109/IEMBS.2008.4650191.

Authors

Evanthia E Tripoliti¹, Dimitrios I Fotiadis, Maria Argyropoulou

Affiliation

¹ Unit of Medical Technology and Intelligent Information Systems, Dept. of Computer Science, University of Ioannina and Biomedical Research Institute - FORTH, GR 451 10, Greece.

PMID: 19163694
DOI: 10.1109/IEMBS.2008.4650191

Abstract

The aim of this work is the development of a method to assist the diagnosis and classification of the status of Alzheimer's Disease (AD) using information that can be extracted from fMRI. The method consists of five stages: a) preprocessing of fMRI data to remove non-task related variability, b) modeling BOLD response depending on stimulus, c) feature extraction from fMRI data, d) feature selection and e) classification using the Random Forests (RF) algorithm. The proposed method is evaluated using data from 41 subjects (14 young adults, 14 non demented older adults and 13 demented older adults.

MeSH terms

Adolescent
Adult
Aged
Aged, 80 and over
Algorithms
Alzheimer Disease / classification*
Alzheimer Disease / diagnosis*
Dementia / classification
Dementia / diagnosis
Diagnosis, Computer-Assisted / methods*
Female
Humans
Linear Models
Magnetic Resonance Imaging / methods*
Male
Normal Distribution
Signal Processing, Computer-Assisted*