Physiological classification of Parkinson’s disease severity using multimodal speech biomarkers with a hybrid CNN-Mamba framework
Frontiers in Physiology · 18.05.2026 · 17
DOI: 10.3389/fphys.2026.1806415 ↗Kurz gefasst
Fachartikel in der Zeitschrift Frontiers in Physiology, online erschienen am 18.05.2026. Verfasst von Taisheng Zeng und 7 weiteren Autor:innen. Beteiligte Einrichtung: School of Mathematics and Computer Science, Quanzhou Normal University, Quanzhou, China. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Introduction
Hypokinetic dysarthria in Parkinson’s disease provides an accessible non-invasive biomarker, but multi-class severity grading remains difficult because of overlapping acoustic patterns and limited long-range temporal modeling in existing approaches.
Methods
We developed a hybrid CNN-Mamba framework using multimodal speech features transformed into 2D representations. The model was trained and validated on speaker-disjoint PC-GITA Spanish data and tested on an independent Mandarin clinical cohort, with additional external evaluation on a public Parkinsonian speech corpus. Speaker-level results were obtained by aggregating segment predictions within each subject.
Results
Segment-level accuracy reached 97.8% on PC-GITA and 95.4% on the Mandarin cohort. Speaker-level accuracy reached 94.0% and 91.2% using majority voting, improving to 94.8% and 91.9% with mean-probability aggregation. SHAP analysis supported physiological interpretability, and ablation studies showed advantages over CNN-BiLSTM, Transformer, and SVM baselines.
Discussion
The proposed CNN-Mamba framework provides an interpretable, computationally efficient, and non-invasive approach for Parkinson’s disease severity assessment and remote monitoring, with promising cross-lingual transfer under structured clinical speech tasks.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Mathematics and Computer Science, Quanzhou Normal University, Quanzhou, China.
- Fujian Provincial Key Laboratory of Data-Intensive Computing, Quanzhou Normal University, Quanzhou, China.
- Key Laboratory of Intelligent Computing and Information Processing (Quanzhou Normal University), Fujian Province University, Quanzhou, China.
- Department of Mathematics and Information Technology, The Education University of Hong Kong, Hong Kong, Hong Kong SAR, China.
- Department of Diagnostic Radiology, Huaqiao University Affiliated Strait Hospital, Quanzhou, Fujian, China.
- Department of Mechanical Engineering, Division of Biomedical Engineering, University of Saskatchewan, Saskatoon, SK, Canada.
Zitieren
APA
Zeng, T., Ye, Y., Zeng, Y., Shi, J., Huang, Y., Ding, B., Chipusu, K., & Huang, J. (2026). Physiological classification of Parkinson’s disease severity using multimodal speech biomarkers with a hybrid CNN-Mamba framework. Frontiers in Physiology, 17. https://doi.org/10.3389/fphys.2026.1806415
Vancouver
Zeng T, Ye Y, Zeng Y, Shi J, Huang Y, Ding B, et al. Physiological classification of Parkinson’s disease severity using multimodal speech biomarkers with a hybrid CNN-Mamba framework. Frontiers in Physiology. 2026;17. doi:10.3389/fphys.2026.1806415
BibTeX
@article{Zeng2026,
author = {Zeng, Taisheng and Ye, Yuguang and Zeng, Yunyi and Shi, Jianshe and Huang, Yifeng and Ding, Bijiao and Chipusu, Kavimbi and Huang, Jianlong},
title = {Physiological classification of Parkinson’s disease severity using multimodal speech biomarkers with a hybrid CNN-Mamba framework},
journal = {Frontiers in Physiology},
year = {2026},
volume = {17},
doi = {10.3389/fphys.2026.1806415}
}
EUVIMED