Similarity Gait Networks with XAI for Parkinson’s Disease Classification: A Pilot Study
Bioengineering · 28.01.2026 · 13 (2) · 151
DOI: 10.3390/bioengineering13020151 ↗Kurz gefasst
Fachartikel in der Zeitschrift Bioengineering, online erschienen am 28.01.2026. Verfasst von Maria Giovanna Bianco und 11 weiteren Autor:innen. Beteiligte Einrichtung: Neuroscience Research Center, Department of Medical and Surgical Sciences, Magna Graecia University of Catanzaro, 88100 Catanzaro, Italy. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Parkinson’s disease (PD) is characterized by alterations in movement dynamics that are difficult to quantify with conventional clinical assessment. This study proposes an integrated approach combining graph-based kinematic analysis with explainable machine learning to identify digital biomarkers of Parkinsonian motor impairment. Kinematic signals were acquired using Xsens inertial sensors from 51 patients with PD and 53 healthy controls. For each participant, subject-specific kinematic networks were constructed by modeling inter-segment similarities through Jensen–Shannon divergence, from which global and local graph-theoretical metrics were extracted. A machine learning pipeline incorporating voting feature selection, and XGBoost classification was evaluated using a nested cross-validation design. The model achieved robust performance (AUC = 0.87), and explainability analyses using SHAP identified a subset of 13 features capturing alterations in velocity, inter-segment connectivity, and network centrality. PD was characterized by increased positional variability, reduced distal limb velocity, and a redistribution of network centrality towards proximal body segments. These features were associated with clinical severity, confirming their physiological relevance. By integrating graph-theoretical modeling, explainable artificial intelligence, and machine learning methodology, this work provides a method of discovering quantitative biomarkers capturing alterations in motor coordination. These findings highlight the potential of ML and kinematic networks to support objective motor assessment in PD.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Neuroscience Research Center, Department of Medical and Surgical Sciences, Magna Graecia University of Catanzaro, 88100 Catanzaro, Italy.
- Laboratory of Biomedical Applications Technologies and Sensors (BATS), Department of Health Sciences, Magna Graecia University of Catanzaro, 88100 Catanzaro, Italy.
- Department of Electrical Engineering and Computer Science, University of Missouri, Columbia, MO 65211, USA.
- Institute of Neurology, Department of Medical and Surgical Sciences, Magna Graecia University of Catanzaro, 88100 Catanzaro, Italy.
ORCID-Profile: Maria Giovanna Bianco, Camilla Calomino, Alessia Cristofaro, Salvatore Andrea Pullano, Syed Kamrul Islam, Jolanda Buonocore, Andrea Quattrone, Rita Nisticò
Zitieren
APA
Bianco, M. G., Calomino, C., Crasà, M., Cristofaro, A., Sgrò, G., Novellino, F., Pullano, S. A., Islam, S. K., Buonocore, J., Quattrone, A., Quattrone, A., & Nisticò, R. (2026). Similarity Gait Networks with XAI for Parkinson’s Disease Classification: A Pilot Study. Bioengineering, 13(2), 151. https://doi.org/10.3390/bioengineering13020151
Vancouver
Bianco MG, Calomino C, Crasà M, Cristofaro A, Sgrò G, Novellino F, et al. Similarity Gait Networks with XAI for Parkinson’s Disease Classification: A Pilot Study. Bioengineering. 2026;13(2):151. doi:10.3390/bioengineering13020151
BibTeX
@article{Bianco2026,
author = {Bianco, Maria Giovanna and Calomino, Camilla and Crasà, Marianna and Cristofaro, Alessia and Sgrò, Giulia and Novellino, Fabiana and Pullano, Salvatore Andrea and Islam, Syed Kamrul and Buonocore, Jolanda and Quattrone, Aldo and Quattrone, Andrea and Nisticò, Rita},
title = {Similarity Gait Networks with XAI for Parkinson’s Disease Classification: A Pilot Study},
journal = {Bioengineering},
year = {2026},
volume = {13},
number = {2},
pages = {151},
doi = {10.3390/bioengineering13020151}
}
EUVIMED