Classifying mental motor tasks from chronic ECoG-BCI recordings using phase-amplitude coupling features

IntroductionPhase-amplitude coupling (PAC), the modulation of high-frequency neural oscillations by the phase of slower oscillations, is increasingly recognized as a marker of goal-directed motor behavior. Despite this interest, its specific role and potential value in decoding attempted motor movem...

Full description

Saved in:
Bibliographic Details
Main Authors: Morgane Marzulli, Alexandre Bleuzé, Joe Saad, Felix Martel, Philippe Ciuciu, Tetiana Aksenova, Lucas Struber
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-03-01
Series:Frontiers in Human Neuroscience
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fnhum.2025.1521491/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850069156053909504
author Morgane Marzulli
Alexandre Bleuzé
Joe Saad
Felix Martel
Philippe Ciuciu
Philippe Ciuciu
Tetiana Aksenova
Lucas Struber
author_facet Morgane Marzulli
Alexandre Bleuzé
Joe Saad
Felix Martel
Philippe Ciuciu
Philippe Ciuciu
Tetiana Aksenova
Lucas Struber
author_sort Morgane Marzulli
collection DOAJ
description IntroductionPhase-amplitude coupling (PAC), the modulation of high-frequency neural oscillations by the phase of slower oscillations, is increasingly recognized as a marker of goal-directed motor behavior. Despite this interest, its specific role and potential value in decoding attempted motor movements remain unclear.MethodsThis study investigates whether PAC-derived features can be leveraged to classify different motor behaviors from ECoG signals within Brain-Computer Interface (BCI) systems. ECoG data were collected using the WIMAGINE implant during BCI experiments with a tetraplegic patient performing mental motor tasks. The data underwent preprocessing to extract complex neural oscillation features (amplitude, phase) through spectral decomposition techniques. These features were then used to quantify PAC by calculating different coupling indices. PAC metrics served as input features in a machine learning pipeline to evaluate their effectiveness in predicting mental tasks (idle state, right-hand movement, left-hand movement) in both offline and pseudo-online modes.ResultsThe PAC features demonstrated high accuracy in distinguishing among motor tasks, with key classification features highlighting the coupling of theta/low-gamma and beta/high-gamma frequency bands.DiscussionThese preliminary findings hold significant potential for advancing our understanding of motor behavior and for developing optimized BCI systems.
format Article
id doaj-art-7c3e2f5ef8fe42b8a7e1c286cc4af316
institution DOAJ
issn 1662-5161
language English
publishDate 2025-03-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Human Neuroscience
spelling doaj-art-7c3e2f5ef8fe42b8a7e1c286cc4af3162025-08-20T02:47:50ZengFrontiers Media S.A.Frontiers in Human Neuroscience1662-51612025-03-011910.3389/fnhum.2025.15214911521491Classifying mental motor tasks from chronic ECoG-BCI recordings using phase-amplitude coupling featuresMorgane Marzulli0Alexandre Bleuzé1Joe Saad2Felix Martel3Philippe Ciuciu4Philippe Ciuciu5Tetiana Aksenova6Lucas Struber7Clinatec, CEA, LETI, University Grenoble Alpes, Grenoble, FranceClinatec, CEA, LETI, University Grenoble Alpes, Grenoble, FranceCEA, LIST, University Grenoble Alpes, Grenoble, FranceClinatec, CEA, LETI, University Grenoble Alpes, Grenoble, FranceCEA, Joliot, NeuroSpin, Université Paris-Saclay, Gif-sur-Yvette, FranceMIND Team, Inria, Université Paris-Saclay, Palaiseau, FranceClinatec, CEA, LETI, University Grenoble Alpes, Grenoble, FranceClinatec, CEA, LETI, University Grenoble Alpes, Grenoble, FranceIntroductionPhase-amplitude coupling (PAC), the modulation of high-frequency neural oscillations by the phase of slower oscillations, is increasingly recognized as a marker of goal-directed motor behavior. Despite this interest, its specific role and potential value in decoding attempted motor movements remain unclear.MethodsThis study investigates whether PAC-derived features can be leveraged to classify different motor behaviors from ECoG signals within Brain-Computer Interface (BCI) systems. ECoG data were collected using the WIMAGINE implant during BCI experiments with a tetraplegic patient performing mental motor tasks. The data underwent preprocessing to extract complex neural oscillation features (amplitude, phase) through spectral decomposition techniques. These features were then used to quantify PAC by calculating different coupling indices. PAC metrics served as input features in a machine learning pipeline to evaluate their effectiveness in predicting mental tasks (idle state, right-hand movement, left-hand movement) in both offline and pseudo-online modes.ResultsThe PAC features demonstrated high accuracy in distinguishing among motor tasks, with key classification features highlighting the coupling of theta/low-gamma and beta/high-gamma frequency bands.DiscussionThese preliminary findings hold significant potential for advancing our understanding of motor behavior and for developing optimized BCI systems.https://www.frontiersin.org/articles/10.3389/fnhum.2025.1521491/fullbrain-computer interfaceelectrocorticographymotor decodingneural featuresphase-amplitude coupling
spellingShingle Morgane Marzulli
Alexandre Bleuzé
Joe Saad
Felix Martel
Philippe Ciuciu
Philippe Ciuciu
Tetiana Aksenova
Lucas Struber
Classifying mental motor tasks from chronic ECoG-BCI recordings using phase-amplitude coupling features
Frontiers in Human Neuroscience
brain-computer interface
electrocorticography
motor decoding
neural features
phase-amplitude coupling
title Classifying mental motor tasks from chronic ECoG-BCI recordings using phase-amplitude coupling features
title_full Classifying mental motor tasks from chronic ECoG-BCI recordings using phase-amplitude coupling features
title_fullStr Classifying mental motor tasks from chronic ECoG-BCI recordings using phase-amplitude coupling features
title_full_unstemmed Classifying mental motor tasks from chronic ECoG-BCI recordings using phase-amplitude coupling features
title_short Classifying mental motor tasks from chronic ECoG-BCI recordings using phase-amplitude coupling features
title_sort classifying mental motor tasks from chronic ecog bci recordings using phase amplitude coupling features
topic brain-computer interface
electrocorticography
motor decoding
neural features
phase-amplitude coupling
url https://www.frontiersin.org/articles/10.3389/fnhum.2025.1521491/full
work_keys_str_mv AT morganemarzulli classifyingmentalmotortasksfromchronicecogbcirecordingsusingphaseamplitudecouplingfeatures
AT alexandrebleuze classifyingmentalmotortasksfromchronicecogbcirecordingsusingphaseamplitudecouplingfeatures
AT joesaad classifyingmentalmotortasksfromchronicecogbcirecordingsusingphaseamplitudecouplingfeatures
AT felixmartel classifyingmentalmotortasksfromchronicecogbcirecordingsusingphaseamplitudecouplingfeatures
AT philippeciuciu classifyingmentalmotortasksfromchronicecogbcirecordingsusingphaseamplitudecouplingfeatures
AT philippeciuciu classifyingmentalmotortasksfromchronicecogbcirecordingsusingphaseamplitudecouplingfeatures
AT tetianaaksenova classifyingmentalmotortasksfromchronicecogbcirecordingsusingphaseamplitudecouplingfeatures
AT lucasstruber classifyingmentalmotortasksfromchronicecogbcirecordingsusingphaseamplitudecouplingfeatures