Non-linear and time-domain sleep qEEG features predict CSF protein damage markers in early Alzheimer’s disease

Study Objectives

In preclinical Alzheimer’s disease (AD), oxidative stress plays a key role in the pathogenesis by promoting non-enzymatic protein modifications that lead to the accumulation of oxidized species, established biomarkers of oxidative damage detectable in cerebrospinal fluid (CSF). These molecular alterations contribute to impaired proteostasis and the dysfunction of sleep-regulating neural circuits, resulting in altered sleep electroencephalographic patterns. Due to the invasiveness of CSF sampling, quantitative electroencephalography (qEEG) is proposed as a non-invasive alternative for assessing oxidatively modified protein levels via Machine Learning (ML).

Methods

Forty-two mild-to-moderate AD patients underwent polysomnography (PSG). QEEG features were extracted. CSF protein oxidation markers levels —glutamic semialdehyde, aminoadipic semialdehyde, Nε-carboxyethyl-lysine, Nε-carboxymethyl-lysine, and Nε-malondialdehyde-lysine —were assessed by gas chromatography/mass spectrometry, and ML models trained to predict CSF biomarker levels. Model generalizability was validated using EEG data from healthy controls.

Results

qEEG features from slow-wave sleep (SWS) and rapid eye movement (REM) sleep, particularly over frontal and central regions, yielded R ² > 0.625 for patients biomarker prediction.

Conclusion

qEEG is a non-invasive, scalable tool for detecting AD-related oxidative processes, with potential implications for early diagnosis and risk stratification.

Highlights

• Sleep EEG features predict CSF oxidative biomarkers in early Alzheimer’s disease.

• Peak-to-peak amplitude, variance, and entropy were the top predictive features.

• NREM sleep, especially SWS, and REM sleep provided the most informative EEG signals.

• EEG-based models achieved accurate, non-invasive biomarker estimation.

• Sleep qEEG may enable early detection and risk stratification in Alzheimer’s.