English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  Predictive regression modeling with MEG/EEG: From source power to signals and cognitive states

Sabbagh, D., Ablin, P., Varoquaux, G., Gramfort, A., & Engemann, D. A. (2020). Predictive regression modeling with MEG/EEG: From source power to signals and cognitive states. NeuroImage, 222: 116893. doi:10.1016/j.neuroimage.2020.116893.

Item is

Basic

show hide
Genre: Journal Article

Files

show Files
hide Files
:
Sabbagh_2020.pdf (Publisher version), 3MB
Name:
Sabbagh_2020.pdf
Description:
-
Visibility:
Public
MIME-Type / Checksum:
application/pdf / [MD5]
Technical Metadata:
Copyright Date:
-
Copyright Info:
-
License:
-

Locators

show

Creators

show
hide
 Creators:
Sabbagh, David1, 2, 3, Author
Ablin, Pierre1, Author
Varoquaux, Gaël1, Author
Gramfort, Alexandre1, Author
Engemann, Denis A.1, 2, 3, 4, Author              
Affiliations:
1Centre Inria Saclay de l'université Paris Sud, France, ou_persistent22              
2Université Paris Diderot, France, ou_persistent22              
3Department of Anaesthesiology and Critical Care, Hôpital Lariboisière, Paris, France, ou_persistent22              
4Department Neurology, MPI for Human Cognitive and Brain Sciences, Max Planck Society, ou_634549              

Content

show
hide
Free keywords: MEG/EEG; Neuronal oscillations; Machine learning; Covariance; Spatial filters; Riemannian geometry
 Abstract: Predicting biomedical outcomes from Magnetoencephalography and Electroencephalography (M/EEG) is central to applications like decoding, brain-computer-interfaces (BCI) or biomarker development and is facilitated by supervised machine learning. Yet, most of the literature is concerned with classification of outcomes defined at the event-level. Here, we focus on predicting continuous outcomes from M/EEG signal defined at the subject-level, and analyze about 600 MEG recordings from Cam-CAN dataset and about 1000 EEG recordings from TUH dataset. Considering different generative mechanisms for M/EEG signals and the biomedical outcome, we propose statistically-consistent predictive models that avoid source-reconstruction based on the covariance as representation. Our mathematical analysis and ground-truth simulations demonstrated that consistent function approximation can be obtained with supervised spatial filtering or by embedding with Riemannian geometry. Additional simulations revealed that Riemannian methods were more robust to model violations, in particular geometric distortions induced by individual anatomy. To estimate the relative contribution of brain dynamics and anatomy to prediction performance, we propose a novel model inspection procedure based on biophysical forward modeling. Applied to prediction of outcomes at the subject-level, the analysis revealed that the Riemannian model better exploited anatomical information while sensitivity to brain dynamics was similar across methods. We then probed the robustness of the models across different data cleaning options. Environmental denoising was globally important but Riemannian models were strikingly robust and continued performing well even without preprocessing. Our results suggest each method has its niche: supervised spatial filtering is practical for event-level prediction while the Riemannian model may enable simple end-to-end learning.

Details

show
hide
Language(s): eng - English
 Dates: 2020-04-172019-11-152020-04-272020-05-182020-11-15
 Publication Status: Published in print
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: DOI: 10.1016/j.neuroimage.2020.116893
Other: ePub 2020
PMID: 32439535
 Degree: -

Event

show

Legal Case

show

Project information

show hide
Project name : -
Grant ID : ERC-StG-676943
Funding program : -
Funding organization : European Research Council

Source 1

show
hide
Title: NeuroImage
Source Genre: Journal
 Creator(s):
Affiliations:
Publ. Info: Orlando, FL : Academic Press
Pages: - Volume / Issue: 222 Sequence Number: 116893 Start / End Page: - Identifier: ISSN: 1053-8119
CoNE: https://pure.mpg.de/cone/journals/resource/954922650166