Poster No:
1315
Submission Type:
Abstract Submission
Authors:
Roman Kessler1, Alexander Enge2, Michael Skeide1
Institutions:
1Max Planck Institute for Human Cognitive and Brain Sciences, Leipzig, Saxony, 2Humboldt-Universität zu Berlin, Berlin, Berlin
First Author:
Roman Kessler
Max Planck Institute for Human Cognitive and Brain Sciences
Leipzig, Saxony
Co-Author(s):
Michael Skeide
Max Planck Institute for Human Cognitive and Brain Sciences
Leipzig, Saxony
Introduction:
EEG preprocessing varies widely between studies, but its impact on classification accuracy, i.e., decoding performance, remains poorly understood. To address this gap, we analyzed seven different EEG experiments with 40 participants drawn from the public ERP CORE dataset (Kappenman et al., 2021).
Methods:
We systematically varied key preprocessing steps, such as ocular and muscle artifact correction using independent component analysis, filtering, referencing, baseline interval, detrending, and the use of the autoreject package (Jas et al., 2017). Then we performed trial-wise binary classification (i.e., decoding) using neural networks (EEGNet) (Lawhern et al., 2018; Schirrmeister et al., 2017), or time-resolved logistic regressions (Gramfort et al., 2013).
Results:
Our findings demonstrate that preprocessing choices influenced decoding performance considerably. Generally, artifact correction steps reduced decoding performance across all experiments and models, while higher high-pass filter cutoffs consistently enhanced decoding. For EEGNet, baseline correction further improved performance, and for time-resolved classifiers, linear detrending, and lower low-pass filter cutoffs were beneficial. Other optimal preprocessing choices were specific for each experiment. Avoiding high-pass-filtering, detrending, and baseline correction had detrimental effects on decoding performance.
Conclusions:
The current results underline the importance of carefully selecting preprocessing steps for EEG-based decoding. If not corrected, artifacts facilitate decoding but compromise conclusive interpretation. Crucially, optimal preprocessing steps for event-related potential analysis do not necessarily align with optimal preprocessing steps for decoding.
Modeling and Analysis Methods:
Classification and Predictive Modeling 2
EEG/MEG Modeling and Analysis 1
Exploratory Modeling and Artifact Removal
Multivariate Approaches
Keywords:
Data analysis
Electroencephaolography (EEG)
Machine Learning
Modeling
Multivariate
Other - Preprocessing
1|2Indicates the priority used for review
By submitting your proposal, you grant permission for the Organization for Human Brain Mapping (OHBM) to distribute your work in any format, including video, audio print and electronic text through OHBM OnDemand, social media channels, the OHBM website, or other electronic publications and media.
I accept
The Open Science Special Interest Group (OSSIG) is introducing a reproducibility challenge for OHBM 2025. This new initiative aims to enhance the reproducibility of scientific results and foster collaborations between labs. Teams will consist of a “source” party and a “reproducing” party, and will be evaluated on the success of their replication, the openness of the source work, and additional deliverables. Click here for more information.
Propose your OHBM abstract(s) as source work for future OHBM meetings by selecting one of the following options:
I do not want to participate in the reproducibility challenge.
Please indicate below if your study was a "resting state" or "task-activation” study.
Task-activation
Healthy subjects only or patients (note that patient studies may also involve healthy subjects):
Healthy subjects
Was this research conducted in the United States?
No
Were any human subjects research approved by the relevant Institutional Review Board or ethics panel?
NOTE: Any human subjects studies without IRB approval will be automatically rejected.
Not applicable
Were any animal research approved by the relevant IACUC or other animal research panel?
NOTE: Any animal studies without IACUC approval will be automatically rejected.
No
Please indicate which methods were used in your research:
EEG/ERP
Computational modeling
Which processing packages did you use for your study?
Other, Please list
-
MNE
Provide references using APA citation style.
1. Gramfort, A. et al. (2013). MEG and EEG data analysis with MNE-Python. Frontiers in Neuroscience, 7, 267. https://doi.org/10.3389/fnins.2013.00267
2. Jas, M., et al. (2017). Autoreject: Automated artifact rejection for MEG and EEG data. NeuroImage, 159, 417–429. https://doi.org/10.1016/j.neuroimage.2017.06.030
3. Kappenman, E. et al. (2021). ERP CORE: An open resource for human event-related potential research. NeuroImage, 225, 117465. https://doi.org/10.1016/j.neuroimage.2020.117465
4. Lawhern, V. J. et al. (2018). EEGNet: A compact convolutional neural network for EEG-based brain–computer interfaces. Journal of Neural Engineering, 15(5), 056013. https://doi.org/10.1088/1741-2552/aace8c
5. Schirrmeister, R. T. et al. (2017). Deep learning with convolutional neural networks for EEG decoding and visualization. Human Brain Mapping. https://doi.org/10.1002/hbm.23730
No