Mild cognitive impairment detection and prediction system

Abstract

A method and system for assessing brain impairment includes generating electroencephalogram (EEG) signals from a plurality of electrodes, removing artifacts from the EEG signals to generate artifact reduced signals, generating current source density signals from the artifact reduced signals, performing multiscale analysis of dynamic functional connectivity of a brain based on the current source density signals using a plurality of different sized time windows, generating hard classifiers for each of the plurality of different size time windows, selecting classifiers from the hard classifiers to form selected classifiers, performing majority voting on a discrimination of normal cognition and mild cognitive impairment using the selected classifiers, generating an EEG-based health score of overall brain activity based on majority voting of the selected classifiers and generating a display corresponding to the health score of brain activity.