Linear Prediction Residual for Efficient Diagnosis of Parkinson's Disease from Gait

TL;DR

This paper introduces LPGNet, a fast and accurate gait-based diagnostic tool for Parkinson's Disease that leverages Linear Prediction Residuals and deep learning, outperforming existing methods in speed and efficiency.

Contribution

The paper presents LPGNet, a novel approach combining Linear Prediction Residuals with a lightweight CNN for improved PD diagnosis from gait data, with a thorough analysis of validation strategies.

Findings

Achieves an AUC of 0.91 in PD diagnosis

Provides 21x speedup over state-of-the-art methods

Uses 99% fewer parameters in the model

Abstract

Parkinson's Disease (PD) is a chronic and progressive neurological disorder that results in rigidity, tremors and postural instability. There is no definite medical test to diagnose PD and diagnosis is mostly a clinical exercise. Although guidelines exist, about 10-30% of the patients are wrongly diagnosed with PD. Hence, there is a need for an accurate, unbiased and fast method for diagnosis. In this study, we propose LPGNet, a fast and accurate method to diagnose PD from gait. LPGNet uses Linear Prediction Residuals (LPR) to extract discriminating patterns from gait recordings and then uses a 1D convolution neural network with depth-wise separable convolutions to perform diagnosis. LPGNet achieves an AUC of 0.91 with a 21 times speedup and about 99% lesser parameters in the model compared to the state of the art. We also undertake an analysis of various cross-validation strategies used in literature in PD diagnosis from gait and find that most methods are affected by some form of data leakage between various folds which leads to unnecessarily large models and inflated performance due to overfitting. The analysis clears the path for future works in correctly evaluating their methods.