Retinal Electrophysiological Patterns in Alzheimer's Disease: A Multi-Domain Signal Processing Framework for Non-Invasive Biomarker Discovery Using a Portable ERG Device

Abstract

Alzheimers disease (AD) is a neurodegenerative disorder affecting more than 55 million people worldwide, with a diagnosis that remains predominantly clinical and frequently delayed. The electroretinogram (ERG) offers a non-invasive electrophysiological method for detecting retinal dysfunction associated with neurodegeneration; however, it remains unclear whether robust and reliable candidate biomarkers can be extracted from ERG signals beyond conventional amplitude- and latency-based parameters. Here we present a pilot study of a multi-domain signal processing framework applied to ERGs recorded from 46 participants (20 AD patients, 26 controls) with a handheld device (RETeval, LKC Technologies) using sinusoidal (1-50 Hz) and photopic ISCEV protocols. Five complementary techniques were implemented: (i) multiscale fuzzy entropy (MSFuzzyEn); (ii) FFT harmonic analysis; (iii) stimulus-response wavelet time-frequency coherence (WTC); (iv) a novel inter-cycle lag variant of sample entropy (SampEnT), introduced to isolate cycle-to-cycle retinal response consistency independently of stimulus periodicity; and (v) discrete wavelet transform (DWT) for energetic extraction of oscillatory potentials (OPs). Univariate comparisons (Mann-Whitney, Cliffs{delta} , Benjamini-Hochberg FDR) identified seven significant candidate biomarkers (q < 0.05), five with large effect size: AUCfast (|{delta}| = 0.546, q = 0.009), Slopevery-slow (|{delta}| = 0.554, q = 0.007), R14f (|{delta}| = 0.515, q = 0.031), SampEnT (|{delta}| = 0.504, q = 0.019) and WTCR,mean (|{delta}| = 0.531, q = 0.023); and two with medium effect size (OP_amp_sum, band_snr). A logistic regression classifier combining three candidate biomarkers, validated by leave-one-out cross-validation, achieved ROC-AUC = 0.858, sensitivity = 70.0% and specificity = 88.5% (n = 46). These proof-of-concept results demonstrate that multi-domain ERG analysis captures retinal temporal dysfunction signatures in AD that are inaccessible to standard clinical analysis, supporting further investigation of portable ERG devices as a source of non-invasive candidate biomarkers for early AD detection.