Unveiling early signs of Parkinson's disease via a longitudinal analysis of celebrity speech recordings

Anna Favaro; Ankur Butala; Thomas Thebaud; Jesús Villalba; Najim Dehak; Laureano Moro-Velázquez

doi:10.1038/s41531-024-00817-9

Unveiling early signs of Parkinson's disease via a longitudinal analysis of celebrity speech recordings

NPJ Parkinsons Dis. 2024 Oct 27;10(1):207. doi: 10.1038/s41531-024-00817-9.

Authors

Anna Favaro^{1

2}, Ankur Butala^{3

4}, Thomas Thebaud⁵, Jesús Villalba^{6

5}, Najim Dehak^{6

5}, Laureano Moro-Velázquez^{6

5}

Affiliations

¹ Department of Electrical and Computer Engineering, The Johns Hopkins University, Baltimore, MD, USA. [email protected].
² Center for Language and Speech Processing, The Johns Hopkins University, Baltimore, MD, USA. [email protected].
³ Department of Neurology, Johns Hopkins Medicine, Baltimore, MD, USA.
⁴ Department of Psychiatry and Behavioral Sciences, Johns Hopkins Medicine, Baltimore, MD, USA.
⁵ Center for Language and Speech Processing, The Johns Hopkins University, Baltimore, MD, USA.
⁶ Department of Electrical and Computer Engineering, The Johns Hopkins University, Baltimore, MD, USA.

Abstract

Numerous studies proposed methods to detect Parkinson's disease (PD) via speech analysis. However, existing corpora often lack prodromal recordings, have small sample sizes, and lack longitudinal data. Speech samples from celebrities who publicly disclosed their PD diagnosis provide longitudinal data, allowing the creation of a new corpus, ParkCeleb. We collected videos from 40 subjects with PD and 40 controls and analyzed evolving speech features from 10 years before to 20 years after diagnosis. Our longitudinal analysis, focused on 15 subjects with PD and 15 controls, revealed features like pitch variability, pause duration, speech rate, and syllable duration, indicating PD progression. Early dysarthria patterns were detectable in the prodromal phase, with the best classifiers achieving AUCs of 0.72 and 0.75 for data collected ten and five years before diagnosis, respectively, and 0.93 post-diagnosis. This study highlights the potential for early detection methods, aiding treatment response identification and screening in clinical trials.