Back

EEG Biomarkers for ATN Classification in Early Alzheimer's disease

Braboszcz, C.; Blanco, A. D.; Chugani, K.; Fernandez, V.; Rosende-Roca, M.; Canada, L.; Tartari, J. P.; Alarcon-Martin, E.; Alegret, M.; Cano, A.; Fernandez, V.; Boada, M.; Morato, X.; Soria-Frisch, A.

2026-06-29 neurology
10.64898/2026.06.26.26356640 medRxiv
Show abstract

INTRODUCTION: Early detection of Alzheimer's disease (AD) remains challenging. EEG offers a scalable, non-invasive tool for patient stratification, but its relationship to ATN-defined staging is poorly understood. METHODS: EEG was recorded in 60 participants (SCD, MCI--, MCI+, N=20 per group) using a battery of tasks (N-back, auditory oddball, 40 Hz ASSR, resting-state). Event-related, spectral, connectivity, and complexity features were extracted, compared across groups, correlated with CSF and plasma biomarkers, and evaluated for classification performance. RESULTS: Multiple EEG features showed discriminatory power among groups and correlated with amyloid and tau biomarkers. MCI-- showed a cortical hyperexcitability profile. EEG added no value for ATN-based discrimination where plasma pTau217 performed near ceiling (AUC=0.96--0.99), but uniquely separated SCD from MCI (EEG AUC {approx} 0.72--0.75) where plasma biomarkers failed (AUC{approx} 0.32--0.33). DISCUSSION: EEG biomarkers capture ATN-stage-dependent neurophysiological signatures, support a non-monotonic model of AD progression, and show promise as a first screening tool where plasma biomarkers are uninformative.

Matching journals

The top 10 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.