Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Aug;40(8):1704-1708.
doi: 10.1002/mds.30256. Epub 2025 May 31.

Using Digital Speech Markers to Classify Functional Speech Disorder: A Proof-of-Concept Pilot Study

Jennifer L Freeburn  1   2 , Sara A Finkelstein  2 , Christiana Westlin  2   3 , David L Perez  2   3 , Neguine Rezaii  4
Affiliations

Using Digital Speech Markers to Classify Functional Speech Disorder: A Proof-of-Concept Pilot Study

Jennifer L Freeburn et al. Mov Disord. 2025 Aug.

Abstract

Background: Functional speech disorder (FND-speech) is a subtype of functional neurological disorder, yet quantitative characterization of its motor and cognitive-linguistic features remains underexplored.

Objective: This study aimed to quantitatively characterize FND-speech by comparing acoustic and linguistic features in individuals with FND-speech with healthy control subjects (HCs). The potential of digital speech features to serve as adjunctive diagnostic markers was also evaluated.

Methods: Thirty adults with FND-speech (females, n = 25; males, n = 5) and 47 age-, sex-, education-, and handedness-matched HCs (females, n = 29; males, n = 18) were compared using lexicosyntactic, rate-based, and acoustic markers extracted from a structured picture description task. Supervised machine learning was employed to classify FND-speech versus HCs.

Results: Lexicosyntactic features showed moderate predictive power (area under the curve [AUC] = 0.80), as did rate-based features (AUC = 0.81). Acoustic features demonstrated high discrimination (AUC = 0.98), and a combined model incorporating all feature categories achieved similar performance (AUC = 0.98).

Conclusions: This proof-of-principle pilot study successfully classified FND-speech versus HCs, highlighting the potential of digital speech markers to serve as adjunctive diagnostic markers for FND-speech. Out-of-sample replication and larger-scale classifier efforts incorporating neurological controls are needed. © 2025 International Parkinson and Movement Disorder Society.

Keywords: digital speech markers; functional neurological disorder; functional speech disorder; machine learning.

PubMed Disclaimer

References

    1. Hallett M, Aybek S, Dworetzky BA, McWhirter L, Staab JP, Stone J. Functional neurological disorder: new subtypes and shared mechanisms. Lancet Neurol 2022;21(6):537–550. https://doi.org/10.1016/S1474-4422(21)00422-1
    1. Baker J, Barnett C, Cavalli L, et al. Management of functional communication, swallowing, cough and related disorders: consensus recommendations for speech and language therapy. J Neurol Neurosurg Psychiatry 2021;92(10):1112–1125. https://doi.org/10.1136/jnnp-2021-326767
    1. Westlin C, Guthrie AJ, Paredes‐Echeverri S, et al. Machine learning classification of functional neurological disorder using structural brain MRI features. J Neurol Neurosurg Psychiatry 2025;96(3):249–257. https://doi.org/10.1136/jnnp-2024-333499
    1. Weber S, Heim S, Richiardi J, et al. Multi‐centre classification of functional neurological disorders based on resting‐state functional connectivity. NeuroImage Clin 2022;35:103090. https://doi.org/10.1016/j.nicl.2022.103090
    1. Freeburn JL, Baker J. Functional speech and voice disorders: approaches to diagnosis and treatment. Neurol Clin 2023;41(4):635–646. https://doi.org/10.1016/j.ncl.2023.02.005

LinkOut - more resources