JMIR Publications

ABSTRACT

Background:

Speech analysis is a promising digital biomarker for early detection of Alzheimer’s disease. However, despite its importance, very few studies in this area have examined whether older adults produce spontaneous speech with characteristics that are sufficiently consistent to be utilized as a proxy marker of cognitive status.

Objective:

This preliminary study sought to investigate consistency across lexical characteristics of speech in older adults with and without cognitive impairment.

Methods:

Thirty-nine older adults from a larger, ongoing study (average age=81.1 years) were included. Participants completed neuropsychological testing and both Picture Description and Expository Tasks to elicit speech. Participants with t-scores ≤40 on 2+ cognitive tests were categorized as having MCI. Speech features were computed automatically using Python and the Natural Language Toolkit.

Results:

Reliability indices based on mean correlations for Picture Description Tasks and Expository Tasks were similar in persons with and without MCI (ranging from r = .49 to .65 within tasks). Intraindividual variability was generally preserved across lexical speech features. Speech rate and filler rate were the most consistent indices for the Intact group, and speech rate was the most consistent for the MCI group.

Conclusions:

The current findings suggest that automatically-calculated lexical properties of speech are consistent in older adults with varying levels of cognitive impairment. These findings encourage further investigation of the utility of speech analysis and other digital biomarkers to monitor cognitive status over time.