Can Speech Analysis Identify Early-Stage Huntington’s Disease? Can Speech Analysis Identify Early-Stage Huntington’s Disease?

The study covered in this summary was published on MedRxiv.org as a preprint and has not yet been peer reviewed.

Key Takeaways

  • Participants with premanifest Huntington’s disease (HD) demonstrated speech timing deficits with syllable repetition tests and during cognitively demanding tasks.

  • Speech tasks coupled with cognitive and motor demands differentiated participants with early HD from matched control persons when motor speech tasks alone did not.

  • In the HD group, the effect of the speech deficit increased with disease severity.

Why This Matters

  • Automated digital speech tests can potentially identify individuals with premanifest HD.

  • Digital acoustic analysis of speech is objective and repeatable, making it a valuable tool to monitor change in HD severity.

Study Design

  • Speech data from 110 participants were gathered from the ENROLL-HD registry at Calvary Health Care Bethlehem Hospital in Melbourne, Australia, and a Monash University HD research volunteer database in Melbourne to measure digital speech measures.

    • The study included 55 participants older than 55 with expanded HD gene and sex-matched control persons.

    • All participants with HD had ≥38 CAG repeats in one of the HD alleles.

  • Objective speech measures included sustained vowel, syllable, saying days of the week, reading a phonetically balanced passage from “The North Wind and the Sun,” and an unprepared monologue.

  • Objective acoustic measures of timing and voice quality included articulatory agility, voice quality, and speech-timing features.

  • The Montreal Cognitive Assessment 31 and the Cogstate Brief Battery were used to measure cognitive function, while fine motor ability was assessed using the Purdue Pegboard Test.

Key Results

  • The effect of speech timing and voice quality increased with disease severity between participants with HD and matched control persons.

  • For patients with presymptomatic HD, timing measures differed in the syllable repetition and monologue tests in comparison with matched control persons.

  • Prodromal HD presented with reduced articulatory agility, reduced speech rate, and longer variable pauses.

  • Speech agility correlated with poorer upper limb motor performance.

Limitations

  • The sample size was small; additional home-based assessments and consortia-based data collection may increase cohort size and statistical power.

  • Reported composite measures associated with individuals with premanifest HD may change as speech systems become affected in early to mid disease.

Disclosures

  • Adam Vogel received salaried support from the National Health and Medical Research Council, Australia, and institutional support from the University of Melbourne. He is the chief science officer of Redenlab Inc.

  • Julie Stout is funded by a National Health and Medical Research Council, Australia and an investigator grant and is the director of Zindametrix Pty Ltd.

  • Geoffrey Stuart is director of statistics for Redenlab Inc.

  • Paul Maruff is chief innovation officer of Cogstate Inc.

  • Cheuk Chan and Yenni Lie have disclosed no relevant financial relationships.

This is a summary of a preprint research study, “Automated and Objective Analysis of Speech in Premanifest and Early-Stage Huntington’s Disease,” written by Adam P. Vogel from the University of Melbourne in Australia and colleagues, published on MedRxiv.org, and provided to you by Medscape. This study has not yet been peer reviewed. The full text of the study can be found on MedRxiv.org.