Wearable sensor-derived gait signatures for Parkinson's disease: an exploratory diagnostic study integrating dimensionality reduction and machine learning.
- 1Department of Geriatrics, Shenzhen Second People's Hospital (The First Affiliated Hospital of Shenzhen University), Shenzhen, China.
- 2Department of Neurology, Shenzhen People's Hospital (The Second Clinical Medical College, Jinan University; The First Affiliated Hospital, Southern University of Science and Technology), Shenzhen, China.
- 3Department of Neurology, Shenzhen Second People's Hospital (The First Affiliated Hospital of Shenzhen University), Shenzhen, China.
Abstract
Background
Parkinson's disease (PD) is characterized by progressive motor dysfunction, in which gait disturbances often emerge early yet remain underutilized in diagnostic frameworks. Advances in wearable sensor technology enable high-resolution quantification of gait dynamics, but the clinical translation of such high-dimensional data is limited by redundancy and model overfitting.Objective
To determine the exploratory diagnostic efficacy of synthesizing wearable sensor-derived gait parameters, cognitive scores, and blood biomarkers utilizing a dual-stage dimensionality reduction framework coupled with logistic regression machine learning for the precise identification of PD.Methods
In this cross-sectional study, demographic characteristics, blood biomarkers, cognitive assessments, and wearable sensor-derived gait parameters were collected from patients with PD and matched controls. Following initial group comparisons, least absolute shrinkage and selection operator (LASSO) regression was applied to identify candidate predictors from multimodal variables. Principal component analysis (PCA) was subsequently performed to reduce dimensionality and extract latent structures. Logistic regression models were constructed using both the original LASSO-selected variables and PCA-derived components. Model performance was assessed using 10-fold cross-validation, with discrimination quantified by the area under the receiver operating characteristic curve (AUC) and accuracy.Results
Baseline characteristics were comparable between groups except for age. LASSO identified 22 potential predictors spanning demographic, biochemical, cognitive, and gait domains. PCA further condensed these variables into six principal components, explaining 62.983% of the total variance. Using a rigorous nested cross-validation framework on the primary cohort, the PCA-based model achieved an internal mean AUC of 0.949 with an accuracy of 0.827. Furthermore, when evaluated on a completely independent external cohort (N = 36) to ensure generalizability, the finalized PCA-based model demonstrated robust diagnostic performance, yielding an AUC of 0.891 and an accuracy of 0.750. Both approaches showed robust discriminative capacity, with dimensionality reduction enhancing overall efficiency and stability.Conclusion
Integrating wearable gait signatures with LASSO-PCA dimensionality reduction and logistic regression yields reliable, interpretable PD classification, with PCA-condensed features demonstrating enhanced diagnostic efficiency. These findings warrant external validation in multicentre, longitudinal cohorts to advance non-invasive, sensor-based PD screening.
Related
- An acoustic-only multivariable diagnostic model for Parkinson's disease using bowel sound acoustic signatures
- The whistle-smile reflex in Parkinson's disease: an exploratory case-control study
- Disease Duration Differentiates Freezing of Gait Response to Subthalamic and Nigral Stimulation for Parkinson's Disease in an Exploratory Multicenter Controlled Trial
- Integrating AI-Assisted World Café Discussion Into Clinical Reasoning Training: an Exploratory Study in Medical Education
- Circulating and tumor microenvironment immunomarkers associate with immunotherapy efficacy in advanced bladder urothelial carcinoma: an exploratory multicenter study integrating genomic and immunophenotypic profiling
BibTeX
@article{hong2026wearable,
title = {{Wearable sensor-derived gait signatures for Parkinson's disease: an exploratory diagnostic study integrating dimensionality reduction and machine learning.}},
author = {Guo Hong and Xueyi Wen and Jinggui Gao and Jiayan Lin and Shawutijiang Zumulaiti and Yunzhu Yang and Xiaohua Xiao},
journal = {Frontiers in medicine},
year = {2026},
month = oct,
doi = {10.3389/fmed.2026.1939598},
url = {https://europepmc.org/article/MED/42923105},
note = {CC BY},
}
RIS
TY - JOUR
TI - Wearable sensor-derived gait signatures for Parkinson's disease: an exploratory diagnostic study integrating dimensionality reduction and machine learning.
AU - Guo Hong
AU - Xueyi Wen
AU - Jinggui Gao
AU - Jiayan Lin
AU - Shawutijiang Zumulaiti
AU - Yunzhu Yang
AU - Xiaohua Xiao
PY - 2026
DA - 2026/10/08
JO - Frontiers in medicine
DO - 10.3389/fmed.2026.1939598
UR - https://europepmc.org/article/MED/42923105
AB - Background Parkinson's disease (PD) is characterized by progressive motor dysfunction, in which gait disturbances often emerge early yet remain underutilized in diagnostic frameworks. Advances in wearable sensor technology enable high-resolution quantification of gait dynamics, but the clinical translation of such high-dimensional data is limited by redundancy and model overfitting.Objective To determine the exploratory diagnostic efficacy of synthesizing wearable sensor-derived gait parameters, cognitive scores, and blood biomarkers utilizing a dual-stage dimensionality reduction framework coupled with logistic regression machine learning for the precise identification of PD.Methods In this cross-sectional study, demographic characteristics, blood biomarkers, cognitive assessments, and wearable sensor-derived gait parameters were collected from patients with PD and matched controls. Following initial group comparisons, least absolute shrinkage and selection operator (LASSO) regression was applied to identify candidate predictors from multimodal variables. Principal component analysis (PCA) was subsequently performed to reduce dimensionality and extract latent structures. Logistic regression models were constructed using both the original LASSO-selected variables and PCA-derived components. Model performance was assessed using 10-fold cross-validation, with discrimination quantified by the area under the receiver operating characteristic curve (AUC) and accuracy.Results Baseline characteristics were comparable between groups except for age. LASSO identified 22 potential predictors spanning demographic, biochemical, cognitive, and gait domains. PCA further condensed these variables into six principal components, explaining 62.983% of the total variance. Using a rigorous nested cross-validation framework on the primary cohort, the PCA-based model achieved an internal mean AUC of 0.949 with an accuracy of 0.827. Furthermore, when evaluated on a completely independent external cohort (N = 36) to ensure generalizability, the finalized PCA-based model demonstrated robust diagnostic performance, yielding an AUC of 0.891 and an accuracy of 0.750. Both approaches showed robust discriminative capacity, with dimensionality reduction enhancing overall efficiency and stability.Conclusion Integrating wearable gait signatures with LASSO-PCA dimensionality reduction and logistic regression yields reliable, interpretable PD classification, with PCA-condensed features demonstrating enhanced diagnostic efficiency. These findings warrant external validation in multicentre, longitudinal cohorts to advance non-invasive, sensor-based PD screening.
SN - 2296-858X
ER -