EEG Biomarkers for ATN Classification in Early Alzheimer's disease

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.