A comparison of different connected-speech tasks for detecting mild cognitive impairment using multivariate pattern analysis

Abstract

ABSTRACT Background It is common for the elderly population to have age-associated cognitive decline and/or develop neurodegenerative diseases such as dementia. Several studies have suggested that classification algorithms based on linguistic features may be useful for the early detection of mild cognitive impairment (MCI). Aims The current study aimed to examine connected-speech performance in people with MCI and cognitively healthy controls (HC). It tests whether patterns of lexical-semantic features extracted from these tasks could distinguish participants with MCI from HC, using univariate and multivariate analyses. Methods & procedure We selected 16 English-speaking participants with MCI and 16 matched HC from the Delaware corpus. Four connected-speech tasks (a picture description, a story narrative, a story recall, and a procedural narrative). Eight lexical-semantic features were selected for analyses. Outcomes & results Univariate analyses showed inter-group differences in revision ratio, core lexicon, or open/closed class words ratio, depending on the task. Multivariate pattern analysis (MVPA) results demonstrated that the story recall task is the only task that can discriminate the two groups above chance. Conclusion To conclude, results showed that connected-speech tasks have the potential to detect subtle language changes in people with MCI. In particular, the story recall task had the potential to predict the group of a participant (MCI or HC).