Neurodegenerative disease often affects speech. Speech acoustics can be used as objective clinical markers of pathology. Previous investigations of pathological speech have primarily compared controls with one specific condition and excluded comorbidities. The authors broaden the utility of speech markers by examining how multiple acoustic features can delineate diseases. Supervised machine learning with gradient boosting (CatBoost) was used to delineate healthy speech from speech of people with multiple sclerosis or Friedreich ataxia. Participants performed a diadochokinetic task where they repeated alternating syllables. 74 spectral and temporal prosodic features from the speech recordings were subjected to machine learning. Results showed that Friedreich ataxia, multiple sclerosis and healthy controls were all identified with high accuracy (over 82%). Twenty-one acoustic features were strong markers of neurodegenerative diseases, falling under the categories of spectral qualia, spectral power, and speech rate. The authors demonstrated that speech markers can delineate neurodegenerative diseases and distinguish healthy speech from pathological speech with high accuracy. Findings emphasize the importance of examining speech outcomes when assessing indicators of neurodegenerative disease. The authors propose large-scale initiatives to broaden the scope for differentiating other neurological diseases and affective disorders.

Read More Here