Eye-movement artifact correction in infant EEG: A systematic comparison between ICA and Artifact Blocking
Bibliographic record
Abstract
Abstract Background Independent Component Analysis (ICA) is a well-established approach to clean EEG and remove the impact of signals of non-neural origin, such as those from muscular activity and eye movements. However, evidence suggests that ICA removes artifacts less effectively in infants than in adults. This study systematically compares ICA and Artifact Blocking (AB), an alternative approach proposed to improve eye-movement artifact correction in infant EEG. Methods We analyzed EEG collected from 50 infants between 6 and 18 months of age as part of the International Infant EEG Data Integration Platform (EEG-IP), a longitudinal multi-study dataset. EEG was recorded while infants sat on their caregivers’ laps and watched videos. We used ICA and AB to correct for eye-movement artifacts in the EEG and calculated the proportion of effectively corrected segments, signal-to-noise ratio (SNR), power-spectral density (PSD), and multiscale entropy (MSE) in manually selected EEG segments with and without eye-movement artifacts. Results On the one hand, the proportion of effectively corrected segments indicated that ICA corrected eye-movement artifacts (sensitivity) better than AB. SNR and PSD indicated that both AB and ICA correct eye-movement artifacts with equal sensitivity. MSE gave mixed results. On the other hand, AB caused less distortion to the clean segments (specificity) for SNR, PSD, and MSE. Conclusions Our results suggest that ICA is more sensitive (i.e., it better removes artifacts) but less specific (it distorts clean signals) than AB for correcting eye-movement artifacts in infant EEG.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.004 | 0.021 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".