Early Detection of Markers for Neurodegenerative Diseases

Project Details

Description

Early diagnosis of neurodegenerative diseases is vital in order to provide treatment and inhibit progression at the early stages. In that relation, it has been suggested that the K-complex (KC) density in sleep EEG might be correlated with a predisposition for neurodegenerative diseases.
In order to be able to investigate such a correlation, it is necessary to have a functional and reliable KC detection algorithm, as manual KC annotation is an extensive job.
In this project we developed a semi-automatic K-Complex detection algorithm, using wavelet transformation to identify pseudo- K-Complexes and various feature thresholds to reject false positives.
The algorithm was trained and tested on sleep EEG from two databases to enhance its general applicability.
StatusFinished
Effective start/end date01/02/201330/08/2014