Assessment of sensorimotor deterioration caused by Mild Cognitive Impairment or early Alzheimer's Disease using a novel deep neural network algorithm

Overview

Professor of Electrical and Computer Engineering University of Puerto Rico at Mayaguez Cognitive deterioration caused by Mild Cognitive Imp airment (MCI), which is often a transition be tween regular aging and neurodegenerative disease (Alzheimer’s disease), is displayed before symptoms are. Timely detection of cognitive deterioration is currently inaccessible. A Brain-Com puter Interface b ased on a sensorimotor paradigm (auditory, olfactory, movement, and motor-imagery) that employs a subject-agnostic Bidirectional Long Short-Term Memory (BLSTM) Network was developed to assess cognitiv e deterioration and identify its re lationship with brain signal features, hypothesized to consistently indicate cognitive decline. Testing occurred with healthy subjects of age 20-40, 40-60, and >60, and MCI patients. Auditory and olfactory stimuli were presented, and the s ubjects imagined and conducted movement of each arm. The a pplication trains a d eep BLSTM Neural Network with Principal Component features from ev oked signals and assesses their corr esponding pathways. Wa velet an alysis w as conducted to decompose ev oked signals, and calcu late the band po wer of component frequency bands. This BCI system perf orms better th an conventional deep neural networks in detecting MCI. Most fea tures studied peaked at age range 40-60 and was lower for the MCI group than for any other group tested. Detection accuracy of left-hand motor imagery signals best indicated cognitive aging ( p=0.0012); here, the me an classification accuracy per age group declined from 82.31% to 79.63%, and w as 76.86% f or M CI s ubjects. Motor-imagery- evoked band power, particularly in gamma bands, best indicated (p=0.007) cognitive aging. Although classification accuracy of the potentials effectively distinguished cognitive aging from MCI (p<0.05), band power did not. This application can be conducive in developing effective diagnostic tools for dementia.

Competition history

• JSHS 2020 Category not listed

Resources

• National JSHS abstract book ↗

Related projects

Closest projects by meaning, across every fair and year in the corpus.