EUVIMEDEUVIMED entdecken
Open Access

Cognitive Phenotyping of Parkinson's Disease Patients Via Digital Analysis of Spoken Word Properties

Franco J Ferrante, Daniel Escobar Grisales, María Fernanda López, Pamela Lopes da Cunha, Lucas Federico Sterpin, Jet M J Vonk, Pedro Chaná Cuevas iD, Claudio Estienne, Eugenia Hesse, Lucía Amoruso, Juan Rafael Orozco Arroyave, Adolfo M García

Movement Disorders · 2025-11 · 40 (11) · 2354-2366

DOI: 10.1002/mds.70005 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Movement Disorders, online erschienen am 12.08.2025. Verfasst von Franco J Ferrante und 11 weiteren Autor:innen. Beteiligte Einrichtung: Centro de Neurociencias Cognitivas, Universidad de San Andrés, Buenos Aires, Argentina. Hauptthemen laut MEDLINE: Parkinson Disease, Cognitive Dysfunction. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 78 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NIA NIH HHS, Agencia Nacional de Promoción Científica y Tecnológica, HORIZON EUROPE Marie Sklodowska-Curie Actions.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Cognitive symptoms are highly prevalent in Parkinson's disease (PD), often manifesting as mild cognitive impairment (MCI). Yet, their detection and characterization remain suboptimal because standard approaches rely on subjective impressions derived from lengthy, univariate tests.

Objective

We examined whether digital analysis of verbal fluency predicts cognitive status in PD.

Methods

We asked 464 Spanish speakers with PD to complete taxonomic (animal), thematic (supermarket), and phonemic (/p/) fluency tasks. We quantified six response properties: semantic variability, granularity, concreteness, length, frequency, and phonological neighborhood. In Study 1, these properties were fed to a ridge regressor to predict Mattis Dementia Rating Scale (MDRS) scores and subscores. In Study 2, we used the same properties to compare (via a generalized linear model) and classify (via random forest) between 123 patients with and 124 without MCI.

Results

In Study 1, predicted MDRS scores and subscores strongly correlated with actual ones, adjusting for clinical and cognitive variables ( R = 0.51, P < 0.001). In Study 2, MCI patients' words were less semantically variable, less concrete, and shorter, adjusting for clinical and cognitive variables ( P ‐values < 0.05). Machine learning discrimination between patients with and without MCI was robust in the validation set (area under the curve [AUC] = 0.76), with good generalization to unseen pre‐surgical (AUC = 0.68) and post‐surgical (AUC = 0.72) samples, surpassing MDRS scores (AUC = 0.54). Results were consistently driven by semantic variability, granularity, and concreteness.

Conclusions

Digital word property analysis predicts cognitive symptom severity and distinguishes between cognitive phenotypes of PD, enabling scalable neuropsychological screenings. © 2025 International Parkinson and Movement Disorder Society.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Parkinson DiseaseCognitive DysfunctionHumansMaleFemaleAgedMiddle AgedNeuropsychological TestsPhenotypeSemantics

Stichwörter der Autor:innen

Parkinson's diseasecognitive statusdigital biomarkersmachine learningsemantic memoryword properties

Autor:innen und Institutionen

  • Centro de Neurociencias Cognitivas, Universidad de San Andrés, Buenos Aires, Argentina.
  • Consejo Nacional de Investigaciones Científicas y Técnicas (CONICET) Godoy Cruz, Buenos Aires, Argentina.
  • Facultad de Ingeniería, Universidad de Buenos Aires, Colón, Argentina.
  • GITA Lab, Faculty of Engineering, University of Antioquia Universidad de Antioquia, Medellín, Colombia.
  • Hospital Nacional Posadas, Buenos Aires, Argentina.
  • Universidad de Flores, Buenos Aires, Argentina.

ORCID-Profile: Pedro Chaná Cuevas

Förderung

  • NIA NIH HHS
  • Agencia Nacional de Promoción Científica y Tecnológica
  • HORIZON EUROPE Marie Sklodowska-Curie Actions
  • Dirección General de Investigación Científica y Técnica
  • Agencia Nacional de Investigación y Desarrollo
  • Agencia Nacional de Investigación e Innovación
  • ZonMw
  • Universidad de Antioquia

Zitieren

APA

Ferrante, F. J., Escobar Grisales, D., López, M. F., Lopes da Cunha, P., Sterpin, L. F., Vonk, J. M. J., Chaná Cuevas, P., Estienne, C., Hesse, E., Amoruso, L., Orozco Arroyave, J. R., & García, A. M. (2025). Cognitive Phenotyping of Parkinson's Disease Patients Via Digital Analysis of Spoken Word Properties. Movement Disorders, 40(11), 2354-2366. https://doi.org/10.1002/mds.70005

Vancouver

Ferrante FJ, Escobar Grisales D, López MF, Lopes da Cunha P, Sterpin LF, Vonk JMJ, et al. Cognitive Phenotyping of Parkinson's Disease Patients Via Digital Analysis of Spoken Word Properties. Movement Disorders. 2025;40(11):2354-2366. doi:10.1002/mds.70005

BibTeX
@article{Ferrante2025,
  author = {Ferrante, Franco J and Escobar Grisales, Daniel and López, María Fernanda and Lopes da Cunha, Pamela and Sterpin, Lucas Federico and Vonk, Jet M J and Chaná Cuevas, Pedro and Estienne, Claudio and Hesse, Eugenia and Amoruso, Lucía and Orozco Arroyave, Juan Rafael and García, Adolfo M},
  title = {Cognitive Phenotyping of Parkinson's Disease Patients Via Digital Analysis of Spoken Word Properties},
  journal = {Movement Disorders},
  year = {2025},
  volume = {40},
  number = {11},
  pages = {2354--2366},
  doi = {10.1002/mds.70005}
}
Kostenlos starten →