A Multivariate Neuroinformatics Framework for Predicting Cognitive Performance from Resting-State EEG Functional Network Characteristics

Resting-state electroencephalography (EEG) has become an important non-invasive neuroimaging technique for investigating intrinsic brain activity and understanding the neural mechanisms associated with cognitive performance. Graph-theoretical network modeling and functional connectivity analysis offer useful information on the organization of the brain on large scales. Nevertheless, the majority of existing studies mainly concentrate on individual measures of connectivity or single metrics of networks, which restricts their capacity to fully describe complex brain interactions that work to form the basis of cognitive functioning. The purpose of this study is to create and confirm a multivariate neuroinformatics model that combines various resting-state EEG functional network properties to effectively predict cognitive performance. EEG data of healthy subjects were recorded in the Resting-state and band-pass filtered, artifact removed, Independent Component Analysis (ICA), epoch cut, and signal quality evaluated. Phase Locking Value (PLV), Weighted Phase Lag Index (wPLI), and measure of coherence were used to construct functional connectivity matrices. Graph-theoretical measures of functional brain networks were then calculated, such as global and local efficiency, characteristic path length, clustering coefficient, small-worldness, modularity, network density, and centrality measures. The features extracted were combined into a multivariate predictive framework and tested with the help of statistical and cross-validation measures. The suggested framework was effective in defining intrinsic functional brain organization and found strong connections between EEG functional network measures and cognitive functioning. By incorporating several graph-theoretical characteristics, the results of prediction became more accurate and better performing than those of methods based on single network measures. The multivariate neuroinformatics framework suggested gives a reliable and detailed methodology of predicting cognitive performance based on resting-state EEG functional networks. The results indicate the possibility of the graph-theoretical brain network properties as potent neurophysiological biomarkers in the future in cognitive assessment, neuroinformatics and custom brain health assessment.

Authors

Publication Details

Journal
Advances in Cognitive and Neural Studies
Published
2026-11-16
Primary Topic
Functional Brain Connectivity Studies
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

A Multivariate Neuroinformatics Framework for Predicting Cognitive Performance from Resting-State EEG Functional Network Characteristics

D.Chitra
3 links
Advances in Cognitive and Neural Studies
Functional Brain Connectivity Studies
article

A Multivariate Neuroinformatics Framework for Predicting Cognitive Performance from Resting-State EEG Functional Network Characteristics

D.Chitra
article en

Abstract

Resting-state electroencephalography (EEG) has become an important non-invasive neuroimaging technique for investigating intrinsic brain activity and understanding the neural mechanisms associated with cognitive performance. Graph-theoretical network modeling and functional connectivity analysis offer useful information on the organization of the brain on large scales. Nevertheless, the majority of existing studies mainly concentrate on individual measures of connectivity or single metrics of networks, which restricts their capacity to fully describe complex brain interactions that work to form the basis of cognitive functioning. The purpose of this study is to create and confirm a multivariate neuroinformatics model that combines various resting-state EEG functional network properties to effectively predict cognitive performance. EEG data of healthy subjects were recorded in the Resting-state and band-pass filtered, artifact removed, Independent Component Analysis (ICA), epoch cut, and signal quality evaluated. Phase Locking Value (PLV), Weighted Phase Lag Index (wPLI), and measure of coherence were used to construct functional connectivity matrices. Graph-theoretical measures of functional brain networks were then calculated, such as global and local efficiency, characteristic path length, clustering coefficient, small-worldness, modularity, network density, and centrality measures. The features extracted were combined into a multivariate predictive framework and tested with the help of statistical and cross-validation measures. The suggested framework was effective in defining intrinsic functional brain organization and found strong connections between EEG functional network measures and cognitive functioning. By incorporating several graph-theoretical characteristics, the results of prediction became more accurate and better performing than those of methods based on single network measures. The multivariate neuroinformatics framework suggested gives a reliable and detailed methodology of predicting cognitive performance based on resting-state EEG functional networks. The results indicate the possibility of the graph-theoretical brain network properties as potent neurophysiological biomarkers in the future in cognitive assessment, neuroinformatics and custom brain health assessment.

Advances in Cognitive and Neural Studies
Good health and well-being
Functional Brain Connectivity Studies
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon