High frequency post-pause word choices and task-dependent speech behavior characterize connected speech in individuals with mild cognitive impairment

Abstract

Background: Alzheimer's disease (AD) is characterized by progressive cognitive decline, including impairments in speech production and fluency. Mild cognitive impairment (MCI), a prodrome of AD, has also been linked with changes in speech behavior but to a more subtle degree.

Objective: This study aimed to investigate whether speech behavior immediately following both filled and unfilled pauses (post-pause speech behavior) differs between individuals with MCI and healthy controls (HCs), and how these differences are influenced by the cognitive demands of various speech tasks.

Methods: Transcribed speech samples were analyzed from both groups across different tasks, including immediate and delayed narrative recall, picture descriptions, and free responses. Key metrics including lexical and syntactic complexity, lexical frequency and diversity, and part of speech usage, both overall and post-pause, were examined.

Results: Significant differences in pause usage were observed between groups, with a higher incidence and longer latencies following these pauses in the MCI group. Lexical frequency following filled pauses was higher among MCI participants in the free response task but not in other tasks, potentially due to the relative cognitive load of the tasks. The immediate recall task was most useful at differentiating between groups. Predictive analyses utilizing random forest classifiers demonstrated high specificity in using speech behavior metrics to differentiate between MCI and HCs.

Conclusions: Speech behavior following pauses differs between MCI participants and healthy controls, with these differences being influenced by the cognitive demands of the speech tasks. These post-pause speech metrics can be easily integrated into existing speech analysis paradigms.

Keywords: Mild cognitive impairment; machine learning; neuropsychological assessment; speech; verbal behavior.

Figure 1.

Count and duration of pause types separated by impairment status. (A) Total number of pauses separated by type of pause (all pauses, filled, unfilled, filled with “um”, filled with “uh”) and by impairment status (HC in orange vs MCI in green). All tasks were included in these comparisons. Significant differences between impairment status can be observed when examining All pauses, Filled pauses, and “Uh” pauses, all of which increased in the MCI group, with no differences found for unfilled and “um” pauses when all tasks were included. (B) Total duration in seconds separated by type of pause and impairment status. Unfilled pauses and All pauses were found to significantly increase in the MCI group. Significance is indicated using asterisks, with *** = p < .001, ** = p < .01, * = p < .05.

Figure 2.

Correlation matrix using Pearson’s correlations to compare significant speech metrics with cognitive and neuropsychological assessments for each of the four tasks. Spaces without color are non-significant determined by a p-value above 0.015.

Figure 3.

Task comparisons of post-“uh” pause lexical frequency rankings. This measure was used for comparison to highlight differences in pause and post-pause behavior between tasks. In both narrative recall tasks, all groups tended to be searching for comparatively uncommon words following “uh” pauses, while in the picture description task all groups searched for more common words. Only in the free response task were there differences between impairment status, with healthy controls (HC) searching only for more uncommon words and participants with mild cognitive impairment (MCI) producing words of more variable frequency following “uh” pauses.

Figure 4.

Areas under ROC curves for predictive models. (A) After performing feature selection on all available lexical features, 16 features were identified to best identify impairment status (HC vs MCI). Incorporating these into a repeated stratified 3-fold 3-repeat cross-validation procedure using LightGBM gradient boosted machines as the models generated a mean AUC of 0.828. AUCs for individual folds are depicted in multiple colors. (B) The best identified post-pause features (post-“uh” lexical frequency in free response and post-“um” latency in delayed narrative recall) were selected and used as sole features in a LightGBM gradient boosted machine, examined using repeated stratified 3-fold 3-repeat cross-validation. This parsimonious model performed similarly to the larger model with an AUC of 0.791. AUCs for individual folds are depicted in multiple colors.