Speech pause distribution as an early marker for Alzheimer's disease

Background: Pause duration analysis is a common feature in the study of discourse in Alzheimer's disease (AD) since this patient group has shown a consistent trend for longer pauses in comparison to healthy controls. This speech feature may also be helpful for early detection; however, studies involving patients at the pre-clinical, high-risk phase of amnestic mild cognitive impairment (aMCI) have yielded varying results. Objective: To characterize the probability density distribution of speech pause durations in 26 patients with AD, 57 amnestic multi-domain amnestic MCI patients (29 with memory encoding deficits, a-mdMCI-E, and 28 with retrieval impairment only, a-mdMCI-R) and 29 healthy controls (HC) in order assess whether there are significant differences between them. To explore the potential differences in pause production between patients with a-mdMCI-E and a-mdMCI-R, as the former are considered to be at higher risk of progressing to dementia. Methods: The 112 picture-based oral narratives obtained were manually transcribed and annotated for the automatic extraction and analysis of pause durations. Different probability distributions were tested for the fitting of pause durations while truncating shorter ranges. Recent findings in the field of Statistics were considered in order to avoid the inherent methodological uncertainty that this type of analysis entails by addressing the question of temporal thresholding and its potential repercussions on inter-annotator reliability in manual transcriptions. Results: A lognormal distribution (LND) explained the distribution of pause duration for all groups. Its fitted parameters (mu, sigma) followed a gradation from the group with shorter durations and a higher tendency to produce short pauses (HC) to the group with longer pause durations and a considerably higher tendency to produce long pauses with greater variance (AD). Importantly, a-mdMCI-E produced significantly longer pauses and with greater variability than their a-mdMCI-R counterparts (alpha = 0.05). Conclusion: We report significant differences at the group level in pause distribution across all groups of study that could be used in future diagnostic tools and discuss the clinical implications of these findings, particularly regarding the characterization of a-mdMCI.