Nonlinear forecasting measurement of magnetoencephalogram recordings from Alzheimer's disease patients

Journal article


Research Areas

Publication Details

Author list: Gomez C, Hornero R, Mediavilla A, Fernandez A, Abasolo D
Publisher: Department of Signal Theory and Communications, E.T.S. Ingenieros de Telecomunicación, University of Valladolid
Publication year: 2008
Journal: Conference proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference (1557170X)
Start page: 2153
End page: 2156
Number of pages: 4
ISSN: 1557170X
Languages: English-Great Britain (EN-GB)


The goal of this study was to analyze the magnetoencephalogram (MEG)
background activity in patients with Alzheimer's disease (AD) using a
nonlinear forecasting measure. It is a nonparametric method to quantify
the predictability of time series. Five minutes of recording were
acquired with a 148-channel whole-head magnetometer in 15 patients with
probable AD and 15 elderly control subjects. Stationary epochs of 5
seconds (848 points, sample frequency of 169.55 Hz) were selected. Our
results showed that AD patients' MEGs were more predictable than
controls' recordings. Additionally, an accuracy of 76.7% (80.0%
sensitivity; 73.3% specificity) was reached using a receiver operating
characteristic curve. These preliminary results suggest the usefulness
of nonlinear forecasting to gain a better understanding of dynamical
processes underlying the MEG recording.


No matching items found.


No matching items found.

Last updated on 2019-10-08 at 00:30