Comparing longitudinal changes in speech‐based digital measures in cognitively healthy, possible cognitive impairment, and MCI/AD individuals

Abstract

AbstractBackgroundIn Alzheimer’s disease (AD), changes to speech and language differentiate individuals with AD from healthy controls and may be detectable years prior to clinical diagnosis. Speech‐based digital biomarkers are objective, naturalistic measures, which could detect early signs of mild cognitive impairment (MCI) and AD and track disease progression. The objective of this study was to compare speech‐based digital measures across older adults who were cognitively healthy, had possible cognitive impairment based on cognitive screening measures, or had diagnoses of MCI or AD.Method103 community‐dwelling older adults and 27 individuals with MCI or AD were recruited for this study in North America. Participants completed a tablet‐based speech assessment at Baseline and 6 month timepoints. Verbal responses were recorded, transcribed and analyzed to produce 8 composite measures pertaining to different aspects of speech and language. Participants were divided into a cognitively healthy group (>25 on the MoCA at baseline and at 6‐months), a possible cognitive impairment group (≤25 at both timepoints), and the MCI/AD group. Two‐way mixed ANOVAs were used to compare language scores across groups and assess change over time.ResultThere was a significant effect of group on five of the eight language composite scores: information units, local and global coherence, word finding difficulty and syntactic complexity, with the cognitively healthy group performing the best in all cases. There were significant overall declines in information units, global coherence and discourse mapping over the 6‐month period, but the interactions of time and group did not reach significance. Phonemic and semantic fluency scores also had significant main effects of group and significant declines over time. MoCA scores did not change over 6 months.ConclusionThis study demonstrates that speech‐based biomarkers are sensitive to detect differences in individuals based on cognitive status and MCI/AD diagnosis. A number of these measures declined over a 6 month period, unlike MoCA scores, but the rate of change did not differ significantly across groups. Ongoing work with larger samples and longer study periods will continue to examine which aspects of speech and language are most sensitive to cognitive status and disease progression and validate novel digital biomarkers.