EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Multi-Modal Decentralized Hybrid Learning for Early Parkinson’s Detection Using Voice Biomarkers and Contrastive Speech Embeddings

Khaled M Alhawiti iD

Sensors · 14.11.2025 · 25 (22) · 6959

DOI: 10.3390/s25226959 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 14.11.2025. Verfasst von Khaled M Alhawiti. Beteiligte Einrichtung: Faculty of Computers and Information Technology, University of Tabuk, Tabuk 47512, Saudi Arabia. Hauptthemen laut MEDLINE: Parkinson Disease, Voice, Speech. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Millions worldwide are affected by Parkinson’s disease, with the World Health Organization highlighting its growing prevalence. Early neuromotor speech impairments make voice analysis a promising tool for detecting Parkinson’s, aided by advances in deep speech embeddings. However, existing approaches often rely on either handcrafted acoustic features or opaque deep representations, limiting diagnostic performance and interoperability. To address this, we propose a multi-modal decentralized hybrid learning framework that combines structured voice biomarkers from the UCI Parkinson’s dataset (195 sustained-phonation samples from 31 subjects) with contrastive speech embeddings derived from the DAIC-WOZ corpus (189 interview recordings originally collected for depression detection) using Wav2Vec 2.0. This system employs an early fusion strategy followed by a dense neural classifier optimized for binary classification. By integrating both clinically interpretable and semantically rich features, the model captures complementary phonatory and affective patterns relevant to early-stage Parkinson’s detection. Extensive evaluation demonstrates that the proposed method achieves an accuracy of 96.2% and an AUC of 97.1%, outperforming unimodal and baseline fusion models. SHAP-based analysis confirms that a subset of features have disproportionately high discriminative value, enhancing interpretability. Overall, the proposed framework establishes a promising pathway toward data-driven, non-invasive screening for neurodegenerative conditions through voice analysis.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Parkinson DiseaseVoiceSpeechHumansBiomarkersMaleFemaleMiddle AgedAgedDeep Learning

Stichwörter der Autor:innen

DAIC-WOZParkinson’s detectionUCI datasetWav2Vec 2.0early fusionmulti-modal learningself-supervised contrastive embeddingsvoice biomarkers

Substanzen

Biomarkers

Autor:innen und Institutionen

  • Faculty of Computers and Information Technology, University of Tabuk, Tabuk 47512, Saudi Arabia.

ORCID-Profile: Khaled M Alhawiti

Zitieren

APA

Alhawiti, K. M. (2025). Multi-Modal Decentralized Hybrid Learning for Early Parkinson’s Detection Using Voice Biomarkers and Contrastive Speech Embeddings. Sensors, 25(22), 6959. https://doi.org/10.3390/s25226959

Vancouver

Alhawiti KM. Multi-Modal Decentralized Hybrid Learning for Early Parkinson’s Detection Using Voice Biomarkers and Contrastive Speech Embeddings. Sensors. 2025;25(22):6959. doi:10.3390/s25226959

BibTeX
@article{Alhawiti2025,
  author = {Alhawiti, Khaled M},
  title = {Multi-Modal Decentralized Hybrid Learning for Early Parkinson’s Detection Using Voice Biomarkers and Contrastive Speech Embeddings},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {22},
  pages = {6959},
  doi = {10.3390/s25226959}
}
Kostenlos starten →