Summary
EEG signals from the brain are often used to diagnose diseases, but the way they are analyzed can mix up detecting the disease and showing where exactly the brain is affected. The authors propose a method to separate diagnosis from the brain's disease patterns by combining two views: one that focuses on diagnosing from scalp signals and another that maps detailed brain activity changes. This approach lets doctors see not just if a disease is present but also which brain areas and rhythms are involved, improving understanding and potentially guiding treatments. They tested it on depression, psychosis, and Parkinson’s disease and found it matched or outperformed other methods.
What this means in practice
- •For neurological device developers: Design EEG-based closed-loop systems that provide both accurate disease diagnosis and localized brain activity maps for targeted neuromodulation.
- •For clinical data analysts: Use anatomically coordinated EEG representations to extract interpretable brain region and frequency attributions aligned with known disease patterns for better patient assessment.
Authors
Jiaying Wang, Shouqian Shi, Yutong Chen, Xu Yang, Jie Chen, Xingyu Pan, Lei Zhang, Sheng Zhong
Abstract
Electroencephalography (EEG)-based closed-loop neuromodulation calls for a subject-specific structured state, as opposed to a single disease probability, specifying which brain regions are deviant, at which frequencies, and at which lags. Sensor-space models keep the strongest diagnostic evidence without anatomy, source-space models give anatomy at a loss of predictive signal, and post-hoc attributions stay outside the prediction. We separate the two instead of forcing them into one representation, and propose DMD-EEG (Dual-view Multiscale Deformation for EEG), which keeps a fixed scalp spectral expert for diagnosis and models the source-space disease-related representation as a low-rank, sparse, iterative deformation of a healthy neural-dynamics prior in a $46$-region-of-interest (ROI) $\times$ $5$-frequency $\times$ $4$-lag (autocorrelation-timescale) space. The two experts meet only at a fixed decision level, so the source state is architecturally separate from the scalp expert. Across major depressive disorder (MDD), first-episode psychosis (FEP), and Parkinson's disease (PD), decision-level fusion matches the strongest single expert on MDD and FEP and exceeds the source branch on PD. On FEP the source expert is the strongest branch, the task where the deformation contributes most. The source state is an explicit ROI-frequency-lag attribution defined in a shared source coordinate system across montages, which we treat as an anatomically-coordinated predictive representation whose coordinates are directly readable and hypothesis-generating. The highest-saliency coordinates align with established disease circuitry (fronto-limbic-temporal regions in MDD, motor-cortex beta in PD), and the MDD state transfers by rank to an unseen cohort recorded with a different montage.