A multi-feature approach to the classification analysis of auditory event-related fields acquired with MEG
Journal of Neuroscience Methods · 2026-08 · 432 · 110754
DOI: 10.1016/j.jneumeth.2026.110754 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Neuroscience Methods, 2026-08. Verfasst von Tomasz Hawro und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Artificial Intelligence, Wrocław University of Science and Technology, Wrocław, Poland. Hauptthemen laut MEDLINE: Magnetoencephalography, Evoked Potentials, Auditory, Machine Learning, Signal Processing, Computer-Assisted. Die Arbeit nennt 44 Literaturangaben. Gefördert von: Wrocław University of Science and Technology.
Abstract (Originalsprache)
BACKGROUND In auditory magnetoencephalography (MEG) studies, it is common practice to search for differences between event-related fields (ERFs) measured in different experimental conditions and between the two hemispheres of the human brain. This differentiation is usually based on single ERF parameters such as the most prominent peak of the auditory waveform, the M100. NEW METHOD Here, we introduce a multi-feature approach to differentiate such ERFs, where a multitude of parameters extracted from the ERFs served as input to machine-learning (ML) models. RESULTS We applied this approach to illustrative MEG data taken from a study in which the up-down categorisation of frequency-modulated (FM) sweeps was addressed in search for differences between the MEG signals of the left and the right hemisphere as well as between the two experimental conditions (passive listening vs active categorisation). We obtained results complementary to those of an earlier study using the same experimental paradigm, within the confines rendered by the new multivariate classification methodology and a limited sample size. COMPARISON WITH EXISTING METHODS We argue that complex characteristics of evoked brain responses speak for multi-feature approaches with new measures of signal quantification, beyond those commonly used. However, we critically acknowledge the limitations of ML strategies in applications to MEG datasets of limited size. CONCLUSION We conclude that a sample size typical for neuroscience experimentation limits the usability of ML classification. We also point out some disadvantages of bootstrapping employed to generate surrogate data with the aim to increase dataset size.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Artificial Intelligence, Wrocław University of Science and Technology, Wrocław, Poland.
- Department of Biomedical Engineering, Wrocław University of Science and Technology, Wrocław, Poland. Electronic address: ewelina@tomana.net.
- Leibniz Institute for Neurobiology, Magdeburg, Germany.
- Department of Biomedical Engineering, Wrocław University of Science and Technology, Wrocław, Poland. Electronic address: cezary.sieluzycki@pwr.edu.pl.
Förderung
- Wrocław University of Science and Technology
Zitieren
APA
Hawro, T., Tomana, E., König, R., & Sielużycki, C. (2026). A multi-feature approach to the classification analysis of auditory event-related fields acquired with MEG. Journal of Neuroscience Methods, 432, 110754. https://doi.org/10.1016/j.jneumeth.2026.110754
Vancouver
Hawro T, Tomana E, König R, Sielużycki C. A multi-feature approach to the classification analysis of auditory event-related fields acquired with MEG. Journal of Neuroscience Methods. 2026;432:110754. doi:10.1016/j.jneumeth.2026.110754
BibTeX
@article{Hawro2026,
author = {Hawro, Tomasz and Tomana, Ewelina and König, Reinhard and Sielużycki, Cezary},
title = {A multi-feature approach to the classification analysis of auditory event-related fields acquired with MEG},
journal = {Journal of Neuroscience Methods},
year = {2026},
volume = {432},
pages = {110754},
doi = {10.1016/j.jneumeth.2026.110754}
}
EUVIMED