Multi‐task analysis of oculographic biomarkers to evaluate motoric and cognitive patterns in Alzheimer’s Disease

• DOI: 10.1002/alz.080242
• Publication Date: 2023-12-25T11:14:02Z
• Authors: Deming Li; Trevor Meyer; Esther S Oh; Ankur Butala; Najim Dehak; Laureano Moro‐Vel...
• Keywords: Smooth pursuit

Abstract Background Alzheimer’s disease (AD) is characterized by progressive loss or damage to the nervous system which can cause impairment in movement, coordination, and cognition. Due complexity of clinical features at different stages disease, it may require months for an accurate diagnosis. Oculomotor researchers have demonstrated utility examining eye movements differentiating various neurodegenerative disorders including AD, Parkinson’s (PD), other PD mimics (PDM). In this study, we propose automatic pipeline identify saccade, fixation, blinks extract response‐to‐stimuli‐derived interpretable biomarkers that could inform clinicians making assessment. Method Eye tracking data smooth pursuit, pro‐saccade, anti‐saccade tasks were recorded from 146 participants ‐ 14 with AD Mild Cognitive Impairment (MCI), 46 PD, 16 PDM, 70 age‐matched normal controls (CTL). Biomarkers based on identified movement interaction stimuli extracted our algorithms. Then, pairwise Kruskal‐Wallis H tests conducted determine if there statistically significant differences between groups. The Benjamini‐Hochberg correction was performed control false discovery rate. Result results show that, pursuit task, AD/MCI group had a significantly higher (p < 0.05) saccade count than CTL also exhibited longer average duration PDM mean standard deviation number saccadic adjustments reach stay target differed trials pro‐saccade task. magnitude overshoot undershoot greater AD/MCI, compared CTL. Moreover, saccades wrong direction Conclusion Oculographic be leveraged within machine learning framework useful distinguishing types diseases their early yielding more objective precise protocols monitor progression current methods.