Linguistic Features Identify Alzheimer’s Disease in Narrative Speech

TLDR

Language impairment is an important marker of Alzheimer's disease, complementing the primary symptom of memory loss. The study aims to achieve state‑of‑the‑art accuracy in automatically detecting AD from brief narrative speech and to identify key linguistic factors via factor analysis. The authors extracted linguistic and acoustic features from DementiaBank transcripts and audio, then trained a machine‑learning classifier and performed exploratory factor analysis to distinguish AD from controls. The classifier achieved over 81% accuracy, and factor analysis revealed four distinct impairment factors—semantic, acoustic, syntactic, and informational—underscoring the value of machine learning for AD assessment.

Abstract

Although memory impairment is the main symptom of Alzheimer's disease (AD), language impairment can be an important marker. Relatively few studies of language in AD quantify the impairments in connected speech using computational techniques.We aim to demonstrate state-of-the-art accuracy in automatically identifying Alzheimer's disease from short narrative samples elicited with a picture description task, and to uncover the salient linguistic factors with a statistical factor analysis.Data are derived from the DementiaBank corpus, from which 167 patients diagnosed with "possible" or "probable" AD provide 240 narrative samples, and 97 controls provide an additional 233. We compute a number of linguistic variables from the transcripts, and acoustic variables from the associated audio files, and use these variables to train a machine learning classifier to distinguish between participants with AD and healthy controls. To examine the degree of heterogeneity of linguistic impairments in AD, we follow an exploratory factor analysis on these measures of speech and language with an oblique promax rotation, and provide interpretation for the resulting factors.We obtain state-of-the-art classification accuracies of over 81% in distinguishing individuals with AD from those without based on short samples of their language on a picture description task. Four clear factors emerge: semantic impairment, acoustic abnormality, syntactic impairment, and information impairment.Modern machine learning and linguistic analysis will be increasingly useful in assessment and clustering of suspected AD.