Artificial intelligence classifies primary progressive aphasia from connected speech.

ABSTRACT

Neurodegenerative dementia syndromes, such as Primary Progressive Aphasias (PPA), have traditionally been diagnosed based in part on verbal and nonverbal cognitive profiles. Debate continues about whether PPA is best divided into three variants and also regarding the most distinctive linguistic features for classifying PPA variants. In this cross-sectional study, we first harnessed the capabilities of artificial intelligence (AI) and Natural Language Processing (NLP) to perform unsupervised classification of short, connected speech samples from 78 PPA patients. We then used NLP to identify linguistic features that best dissociate the three PPA variants. Large Language Models (LLMs) discerned three distinct PPA clusters, with 88.5% agreement with independent clinical diagnoses. Patterns of cortical atrophy of three data-driven clusters corresponded to the localization in the clinical diagnostic criteria. In the subsequent supervised classification, seventeen distinctive features emerged, including the observation that separating verbs into high and low-frequency types significantly improves classification accuracy. Using these linguistic features derived from the analysis of short, connected speech samples, we developed a classifier that achieved 97.9% accuracy in classifying the four groups (three PPA variants and healthy controls). The data-driven section of this study showcases the ability of LLMs to find natural partitioning in the speech of patients with PPA consistent with conventional variants. In addition, the work identifies a robust set of language features indicative of each PPA variant, emphasizing the significance of dividing verbs into high and low-frequency categories. Beyond improving diagnostic accuracy, these findings enhance our understanding of the neurobiology of language processing.