Automatic subtyping of individuals with Primary Progressive Aphasia

Abstract

BackgroundThe classification of patients with Primary Progressive Aphasia (PPA) into variants is time-consuming, costly, and requires combined expertise by clinical neurologists, neuropsychologists, speech pathologists, and radiologists. ObjectiveThe aim of the present study is to determine whether acoustic and linguistic variables provide accurate classification of PPA patients into one of three variants: nonfluent PPA, semantic PPA, and logopenic PPA. MethodsIn this paper, we present a machine learning model based on Deep Neural Networks (DNN) for the subtyping of patients with PPA into three main variants, using combined acoustic and linguistic information elicited automatically via acoustic and linguistic analysis. The performance of the DNN was compared to the classification accuracy of Random Forests, Support Vector Machines, and Decision Trees, as well as expert clinicians classifications. ResultsThe DNN model outperformed the other machine learning models with 80% classification accuracy, providing reliable subtyping of patients with PPA into variants and it even outperformed auditory classification of patients into variants by clinicians. ConclusionsWe show that the combined speech and language markers from connected speech productions provide information about symptoms and variant subtyping in PPA. The end-to-end automated machine learning approach we present can enable clinicians and researchers to provide an easy, quick and inexpensive classification of patients with PPA.