Spectral measures of the effects of Friedreich's ataxia on speech

Disease Delineation for Multiple Sclerosis, Friedreich Ataxia, and Healthy Controls Using Supervised Machine Learning on Speech Acoustics

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. We broaden the utility of speech markers by examining how multiple acoustic features can delineate diseases. We used supervised machine learning with gradient boosting (CatBoost) to delineate healthy speech from speech of people with multiple sclerosis or Friedreich ataxia. Participants performed a diadochokinetic task where they repeated alternating syllables. We subjected 74 spectral and temporal prosodic features from the speech recordings 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. We 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. We propose large-scale initiatives to broaden the scope for differentiating other neurological diseases and affective disorders.

Longitudinal change in dysarthria associated with Friedreich ataxia: a potential clinical endpoint

CNS functions that show change across short periods of time are particularly useful clinical endpoints for Friedreich ataxia. This study determined whether there is measurable acoustical change in the dysarthria associated with Friedreich ataxia across yearly intervals. A total of 29 participants diagnosed with Friedreich ataxia were recorded across 4 years at yearly intervals. A repeated measures ANOVA was used to determine which acoustic measures differed across time, and pairwise t tests were used to assess the consistency of the change across the time intervals. The relationship between the identified measures with perceptual severity was assessed with stepwise regression. Significant longitudinal change was observed with four measures that relate to the utterance duration and spectral changes in utterances. The spectral measures consistently detected change across time intervals of two or more years. The four measures combined moderately predicted perceptual severity. Together, the results implicate longitudinal change in speaking rate and utterance duration. Changes in speech associated with Friedreich ataxia can be measured across intervals of 2 years and therefore show rich potential for monitoring disease progression and therapy outcomes.