Multimodal Deep Learning–Based EEG Health Scoring Model for Mild Cognitive Impairment
Bibliographic record
Abstract
With global population aging, Alzheimer’s disease (AD) and its prodromal stage—mild cognitive impairment (MCI)—are major public health concerns, and early detection is crucial. This study characterizes frequency-specific reorganization of functional networks in MCI and develops an interpretable EEG-based health scoring model. Sixty-nine older adults (MCI and healthy controls) underwent 64-channel resting-state EEG; functional connectivity across five bands was computed using the weighted phase lag index (WPLI). We designed a multimodal framework integrating a graph attention network (GAT) for spatial connectivity, a Transformer for temporal dynamics, and clinical features; attention was examined at group, edge, and ROI levels to enhance interpretability. Results showed pronounced beta-band (13–30 Hz) abnormalities in fronto-temporo-parietal circuits, whereas delta-band (1–4 Hz) differences were mainly in temporal dynamics. Network analysis revealed reduced organized subnetworks with compensatory increases in selected connections. The health scoring model performed best in the beta band (MAE=2.28; RMSE=3.57). A consistent offset from Montreal Cognitive Assessment (MoCA) suggested sensitivity to preclinical neurophysiological changes. Combining GAT-based spatial and Transformer-based temporal modeling shows potential for accurate and interpretable MCI assessment, with promise for rapid and scalable early screening and longitudinal monitoring.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.004 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 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 teacher head, 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".