Related Experiment Video
Updated: Jul 18, 2026
Clinical-oriented Three-dimensional Gait Analysis Method for Evaluating Gait Disorder
Published on: March 4, 2018
Machine Learning-Driven Approach to Identify Freezing of Gait in Individuals with Parkinson Disease Using
Gaurav N Rathi1, Alan J Gardner1, Jason K Longhurst2
1From the Department of Radiology (G.N.R., A.G., V.R.M.), University of Alabama at Birmingham, Birmingham, Alabama.
Background And Purpose:
Freezing of gait (FOG) presents a significant challenge in the management of Parkinson disease (PD). Our study explored the potential to predict PD-FOG using an unbiased machine learning (ML) approach that leverages conventional T1-weighted MRI and clinical measures.
Materials And Methods:
Thirty-seven participants (16 with PD-FOG, 21 PD without freezing of gate [PD-nFOG]) underwent standard isotropic 1 mm³ T1-weighted MRI. Brain morphometric measures, including subcortical volume, cortical volume, mean curvature, area, local gyrification index, and thickness, were extracted using FreeSurfer7. Participants were divided into discovery (13 PD-FOG, 17 PD-nFOG) and independent testing (3 PD-FOG, 4 PD-nFOG) data sets. We tested the predictive ability of each FreeSurfer-derived measure, each clinical measure, and every combination of those measures using 3 ML models: random forest (RF), support vector machine (SVM)-linear, and SVM-nonlinear. Feature reduction was performed using the least absolute shrinkage and selection operator before model development.
Results:
The SVM-linear model outperformed SVM-nonlinear and RF when tested on the independent data set (area under the curve [AUC] = 0.71, precision: 75%, sensitivity: 75%, specificity: 66.67%). FreeSurfer-derived cortical area (CA) from 27 regions predicted PD-FOG, involving several cortical and subcortical regions. None of the other measures, either in combination or isolation, predicted PD-FOG. The identified features were significantly correlated with clinical and physical therapy measures of PD-FOG using univariate and multivariate statistics, bolstering confidence in the selected feature set.
Conclusions:
Our results demonstrate that FreeSurfer-derived CA measures from 27 key regions across the frontal, temporal, parietal, and occipital lobes can moderately predict FOG in PD (AUC = 0.71) using a linear SVM model. While preliminary, our work outlines an MRI-based analytical approach that may inform future external validation efforts and contribute to understanding the potential role of cortical morphology in PD-FOG risk. However, given the limited sample size and constrained independent testing cohort, these findings should be interpreted as exploratory and warrant replication in larger, multicenter studies.
