Novel single-channel EEG features correlate with working memory load

Neta B. Maimon, Lior Molcho, Nathan Intrator, Dominique Lamy

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Working Memory (WM) load is a cognitive feature, which is highly correlated with mental effort. Theta power, among other neurological biomarkers, shows increased activity with increasing WM load. These correspondences frequently break down in individuals with cognitive decline, making WM load biomarkers a potentially valuable tool for early detection of cognitive impairment. However, such studies used multiple-channel EEG headsets, which are not easy to use and accessible. Here we used a single-channel EEG set (Aurora by Neurosteer®) and evaluated the ability of novel features, previously extracted on a different dataset, to serve as WM load biomarkers. In a single experiment, fourteen participants underscored the widely used n-back task while their brain activity was recorded with the mobile EEG device. Frontal theta power, as well as two novel features, significantly correlated with the levels of WM load. However, the two novel features exhibited higher sensitivity to lower WM load changes. These more sensitive biomarkers of WM load are a promising tool for mass screening of mild cognitive impairment.

Original languageEnglish
Title of host publicationLifeTech 2021 - 2021 IEEE 3rd Global Conference on Life Sciences and Technologies
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages471-472
Number of pages2
ISBN (Electronic)9781665418751
DOIs
StatePublished - 9 Mar 2021
Event3rd IEEE Global Conference on Life Sciences and Technologies, LifeTech 2021 - Nara, Japan
Duration: 9 Mar 202111 Mar 2021

Publication series

NameLifeTech 2021 - 2021 IEEE 3rd Global Conference on Life Sciences and Technologies

Conference

Conference3rd IEEE Global Conference on Life Sciences and Technologies, LifeTech 2021
Country/TerritoryJapan
CityNara
Period9/03/2111/03/21

Keywords

  • EEG
  • Machine learning
  • Mental load

All Science Journal Classification (ASJC) codes

  • Biomedical Engineering
  • Health Informatics
  • Health(social science)
  • Biochemistry
  • Artificial Intelligence
  • Computer Science Applications

Fingerprint

Dive into the research topics of 'Novel single-channel EEG features correlate with working memory load'. Together they form a unique fingerprint.

Cite this