New method finds hidden brain activity changes from EEG signals
Identifying Neural Source Dynamics from Unknown Local Interventions
Machine Learning
Summary
EEG recordings mix signals from different brain areas, making it hard to understand individual brain source activity. The authors show that unknown local changes in brain dynamics leave unique patterns in EEG that can be identified using a known brain model. By comparing responses before and after these changes, their method recovers how brain sources interact without needing full baseline information or knowing the exact change details. Simulations on realistic brain anatomy confirm the method works well even when traditional approaches fail.
What this means in practice
- •For clinical neurophysiologists: Detect and identify localized changes in brain dynamics from EEG during medical interventions without extensive baseline data.
- •For brain-computer interface developers: Improve decoding of neural source activity by isolating signatures of unknown local changes from EEG signals.
Authors
Ayana Mussabayeva, Jiaqi Sun, Anuar Aimoldin, Olivier Oullier, Kun Zhang
Abstract
Electroencephalography (EEG) records mixtures of brain-source activity. Even with a known anatomical forward model, experiments that excite only part of the source-state space leave the dynamics unidentified, and repetition cannot resolve the ambiguity. We show that unknown local mechanism changes can supply the missing information. We consider linear dynamics among fixed anatomical sources with known source-state initialization patterns. Changing one source's update rule for one transition leaves a rank-one, source-specific signature in subsequent EEG: subtracting matched baseline responses isolates it, and the forward model identifies the source and calibrates its response history. Combining these histories with initialization responses recovers source interactions without baseline reachability and without first identifying the intervention coefficients. We establish sufficient recovery conditions, a direct estimator, and a noise-sensitivity bound conditional on correct source labels. Simulated EEG on anatomy derived from magnetic resonance imaging confirms the information gain: with baseline excitation confined to four of twelve source coordinates, eight unknown changes recover all dynamics in 32/32 systems, whereas baseline realization, baseline regression through an invertible forward model, and changes that leave the tested states unexposed all fail, and explicitly constructed alternative dynamics reproduce every baseline mean. Where baseline information suffices, direct reconstruction is also more reliable than a matched-information spectral estimator. Nonlocal changes and forward-model error limit accuracy even when source labels are correct.