Download

Download Full Text (393 KB)

Description

Parkinson’s Disease (PD) is a progressive neurodegenerative disorder that impairs motor coordination, often resulting in measurable gait disturbances. Vertical ground reaction force (VGRF) signals provide a quantitative means of capturing these abnormalities and monitoring disease progression. This study focuses on the extraction and analysis of spatiotemporal gait features such as stride variability, stance duration, and force imbalance, from the PhysioNet Gait dataset to better understand their correlation with PD severity. Using gait analysis and machine learning techniques, recent computational models are reviewed and evaluated for their ability to assess PD progression through VGRF data. The analysis compares data-driven approaches with established clinical scales, including the Hoehn and Yahr (H&Y) system, emphasizing both interpretability and predictive performance. Preliminary findings reveal consistent associations between VGRF-derived gait features and PD severity levels reported in clinical studies. Key limitations include inconsistent preprocessing pipelines and limited generalizability across datasets. Collectively, the reviewed research highlights promising directions for developing non-invasive, data-driven tools that enable earlier detection and more precise monitoring of Parkinson’s Disease progression.

Publisher Location

Las Vegas (Nev.)

Publication Date

Fall 11-21-2025

Publisher

University of Nevada, Las Vegas

Language

English

Keywords

clinical interpretability; gait analysis; Parkinson’s Disease; severity classification; vertical ground; reaction force

Disciplines

Electrical and Computer Engineering | Engineering

File Format

PDF

File Size

333 KB

Permissions

Google Drive\Institutional Repository\OUR_OfficeOfUGResearch\Symposia\2025 Fall Symposium

Comments

Mentor: Shahram Latifi

Rights

IN COPYRIGHT. For more information about this rights statement, please visit http://rightsstatements.org/vocab/InC/1.0/

Spatiotemporal Feature Extraction from Vertical GRF Signals for Parkinson’s Disease Severity Assessment Using PhysioNet and GAITPD


Share

COinS