Joint Angle Gait Features Outperform Scalar Gait Metrics in Differentiating Parkinson’s Disease from Essential Tremor Public
Ngo, Savannah (Spring 2025)
Abstract
Introduction: Essential tremor (ET) and Parkinson's disease (PD) are frequently mistaken for each other due to overlapping clinical features, particularly those associated with tremor. Gait analyses may enhance differential diagnostic accuracy, especially in cases where the overall clinical presentation is consistent with both ET or PD. This study evaluates whether 3D kinematic motion captures provide reliable diagnostic markers for PD and ET.
Methods: 524 patients with PD or ET were analyzed. 3D kinematic motion capture recorded joint position, angle, and orientation for 42 joints throughout the gait cycle. Symmetry metrics for each joint were derived by computing the correlation between bilateral joint trajectories. Three models for predicting PD and ET were developed: (1) The Benchmark Model included standard quantifications of gait. (2) The Kinematic Model included the covariates from the Benchmark Model and the mean and extent of joint motion. (3) The Kinematic Model with Asymmetry included the derived symmetry covariates alongside covariates from Models 1 and 2. All models were created using cross-validated elastic net and performance was evaluated using sensitivity, specificity, accuracy, and area under the curve (AUC).
Results: The AUCs were 0.803 (95% CI: 0.765, 0.841) for the Benchmark Model, 0.923 (95% CI: 0.899, 0.946) for the Kinematic Model, and 0.931 (95% CI: 0.908, 0.953) for the Kinematic Model with Asymmetry. The symmetry metrics made up 7 out of the top 10 predictors in the Kinematic Model with Asymmetry.
Discussion: These findings highlight the potential of 3D kinematic motion capture in improving diagnostic accuracy for ET and PD. Additionally, derived features such as symmetry provide predictive value beyond standard gait parameters.
Table of Contents
1 Introduction 1
2 Methods 3
2.1 Participants 3
2.2 Data Collection 3
2.3 Deriving Features from Kinematic Motion Captures 5
2.4 Modeling 5
3 Results 6
4 Discussion 10
4.1 Findings 10
4.2 Comparison with Previous Research 11
4.3 Clinical Implications 11
4.4 Limitations 12
5 Conclusion 12
6 References 14
About this Master's Thesis
| School | |
|---|---|
| Department | |
| Subfield / Discipline | |
| Degree | |
| Submission | |
| Language |
|
| Research Field | |
| Mot-clé | |
| Committee Chair / Thesis Advisor | |
| Committee Members |
Primary PDF
| Thumbnail | Title | Date Uploaded | Actions |
|---|---|---|---|
|
|
Joint Angle Gait Features Outperform Scalar Gait Metrics in Differentiating Parkinson’s Disease from Essential Tremor () | 2025-04-23 14:47:27 -0400 |
|
Supplemental Files
| Thumbnail | Title | Date Uploaded | Actions |
|---|