The abstract is read at the publisher; the summary is JClub's.
MLE EEG Toolbox enables a literature-informed AI assistant for EEG and MEG analysis, achieving 85.6% action-selection accuracy for EEG and 95.5% for MEG.
- Why it matters: Electrophysiology workflows are complex, and it is hard to combine methodological evidence, correct computational execution, and reproducibility in one place.
- What they did: The framework uses a constrained language model to convert research instructions into validated, researcher-approved operations, with literature-guided parameter selection and reproducible workflow provenance.
- The result: It reached 142 cross-platform tests with close numerical agreement and supported integrated spectral, network, decoding, and source analyses on public EEG/MEG datasets.
The findingWhy it mattersWhat they didThe result
AI summary of the abstract · may contain errors · not medical advice · read the paper.