Cognitive determinants of dysarthria in Parkinsons disease. An automated machine learning approach

Abstract

Background: Dysarthric symptoms in Parkinson's disease vary greatly across cohorts. Abundant research suggests that such heterogeneity could reflect subject-level and task-related cognitive factors. However, the interplay of these variables during motor speech remains underexplored, let alone by administering validated materials to carefully matched samples with varying cognitive profiles and combining automated tools with machine learning methods. Objectives: We aimed to identify which speech dimensions best identify Parkinson's disease patients in cognitively heterogeneous, cognitively preserved, and cognitively impaired groups through tasks with low (reading) and high (retelling) processing demands. Methods: We used support vector machines to analyze prosodic, articulatory, and phonemic identifiability features. Patient groups were compared with healthy controls and against each other in both tasks, using each measure separately and in combination. Results: Relative to controls, patients in cognitively heterogeneous and cognitively preserved groups were best discriminated by combined dysarthric signs during reading (accuracy = 84% and 80.2%). Conversely, cognitively impaired patients were maximally discriminated from controls when considering phonemic identifiability during retelling (accuracy = 86.9%). This same pattern maximally distinguished between cognitively spared and impaired patients (accuracy = 72.1%). Also, cognitive (executive) symptom severity was predicted by prosody in cognitively preserved patients and by phonemic identifiability in cognitively heterogeneous and impaired groups. No measure predicted overall motor dysfunction in any group. Conclusions: Predominant dysarthric symptoms seem best captured through undemanding tasks in cognitively heterogeneous and preserved cohorts and through cognitively loaded tasks in cognitively impaired patients. Further applications of this framework could enhance dysarthria assessments in Parkinson's disease.