Background: Pause duration analysis is a common feature in the study of discourse in Alzheimer's disease (AD) and may also be helpful for its early detection. However, studies involving patients at the preclinical stage of mild cognitive impairment (MCI) have yielded varying results.Objectives: To characterize the probability density distribution of speech pause duration in AD, two multi-domain amnestic MCI patients (with memory encoding deficits, a-mdMCI-E, and only with retrieval impairment, a-mdMCI-R) and healthy control groups (HC) and to check if there are significant differences between them. To discuss the potential of those findings in clinical practice.Method: 112 picture-based oral narratives were manually transcribed and annotated for the automatic extraction of pause durations and their subsequent logconversion. We consider different probability distributions to fit speech pause duration truncating shorter ranges taking into account latest statistical findings to avoid inherent methodological uncertainties present in them.Results: Lognormal distribution (LND) explains the distribution of pause duration in speech for all groups, and its fitted parameters (µ,σ ) 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 more variance (AD). Importantly, a-mdMCI-E produced significantly longer pauses with greater variability than their a-mdMCI-R counterparts (α = 0.05) across all groups of study. Conclusion:We characterize and report significant differences at group level in the speech pause distribution across all groups of study that could be used to design tools and experiments for early prediction of AD progression.

BackgroundPause duration analysis is a common feature in the study of discourse in Alzheimer’s disease (AD) and may also be helpful for its early detection. However, studies involving patients with amnestic mild cognitive impairment (aMCI) have yielded varying results.ObjectivesTo characterize the probability density distribution of speech pause durations in AD, two multi-domain amnestic MCI patients (with memory encoding deficits, a-mdMCI-E, and with retrieval impairment only, a-mdMCI-R) and healthy controls (HC) in order check whether there are significant differences between them.Method112 picture-based oral narratives 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.ResultsA lognormal distribution (LND) explained the distribution of pause duration for all groups. Its fitted parameters (µ,σ) 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 (α = 0.05).ConclusionWe 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 aMCI.

No abstract