How EEG preprocessing shapes decoding performance
Gorde:
| Argitaratua izan da: | Communications Biology vol. 8, no. 1 (2025), p. 1039 |
|---|---|
| Egile nagusia: | |
| Beste egile batzuk: | , |
| Argitaratua: |
Nature Publishing Group
|
| Gaiak: | |
| Sarrera elektronikoa: | Citation/Abstract Full Text Full Text - PDF |
| Etiketak: |
Etiketarik gabe, Izan zaitez lehena erregistro honi etiketa jartzen!
|
MARC
| LEADER | 00000nab a2200000uu 4500 | ||
|---|---|---|---|
| 001 | 3228992121 | ||
| 003 | UK-CbPIL | ||
| 022 | |a 2399-3642 | ||
| 024 | 7 | |a 10.1038/s42003-025-08464-3 |2 doi | |
| 035 | |a 3228992121 | ||
| 045 | 2 | |b d20250101 |b d20251231 | |
| 100 | 1 | |a Kessler, Roman |u Max Planck Institute for Human Cognitive and Brain Sciences, Leipzig, Germany (GRID:grid.419524.f) (ISNI:0000 0001 0041 5028) | |
| 245 | 1 | |a How EEG preprocessing shapes decoding performance | |
| 260 | |b Nature Publishing Group |c 2025 | ||
| 513 | |a Journal Article | ||
| 520 | 3 | |a Electroencephalography (EEG) preprocessing varies widely between studies, but its impact on classification performance remains poorly understood. To address this gap, we analyzed seven experiments with 40 participants drawn from the public ERP CORE dataset. We systematically varied key preprocessing steps, such as filtering, referencing, baseline interval, detrending, and multiple artifact correction steps, all of which were implemented in MNE-Python. Then we performed trial-wise binary classification (i.e., decoding) using neural networks (EEGNet), or time-resolved logistic regressions. Our findings demonstrate that preprocessing choices influenced decoding performance considerably. All artifact correction steps reduced decoding performance across experiments and models, while higher high-pass filter cutoffs consistently increased decoding performance. For EEGNet, baseline correction further increased decoding performance, and for time-resolved classifiers, linear detrending, and lower low-pass filter cutoffs increased decoding performance. The influence of other preprocessing choices was specific for each experiment or event-related potential component. The current results underline the importance of carefully selecting preprocessing steps for EEG-based decoding. While uncorrected artifacts may increase decoding performance, this comes at the expense of interpretability and model validity, as the model may exploit structured noise rather than the neural signal.Systematic evaluation of EEG preprocessing reveals how filtering, artifact handling, and other steps influence decoding performance, highlighting trade-offs between classification accuracy and neural interpretability. | |
| 653 | |a Accuracy | ||
| 653 | |a Event-related potentials | ||
| 653 | |a Design of experiments | ||
| 653 | |a Regression analysis | ||
| 653 | |a Electrodes | ||
| 653 | |a Electroencephalography | ||
| 653 | |a Time series | ||
| 653 | |a Teams | ||
| 653 | |a EEG | ||
| 653 | |a Classification | ||
| 653 | |a Neural networks | ||
| 700 | 1 | |a Enge, Alexander |u Max Planck Institute for Human Cognitive and Brain Sciences, Leipzig, Germany (GRID:grid.419524.f) (ISNI:0000 0001 0041 5028); Humboldt-Universität zu Berlin, Berlin, Germany (GRID:grid.7468.d) (ISNI:0000 0001 2248 7639) | |
| 700 | 1 | |a Skeide, Michael A. |u Max Planck Institute for Human Cognitive and Brain Sciences, Leipzig, Germany (GRID:grid.419524.f) (ISNI:0000 0001 0041 5028) | |
| 773 | 0 | |t Communications Biology |g vol. 8, no. 1 (2025), p. 1039 | |
| 786 | 0 | |d ProQuest |t Science Database | |
| 856 | 4 | 1 | |3 Citation/Abstract |u https://www.proquest.com/docview/3228992121/abstract/embedded/L8HZQI7Z43R0LA5T?source=fedsrch |
| 856 | 4 | 0 | |3 Full Text |u https://www.proquest.com/docview/3228992121/fulltext/embedded/L8HZQI7Z43R0LA5T?source=fedsrch |
| 856 | 4 | 0 | |3 Full Text - PDF |u https://www.proquest.com/docview/3228992121/fulltextPDF/embedded/L8HZQI7Z43R0LA5T?source=fedsrch |