Linear Prediction Residual for Efficient Diagnosis of Parkinson's Disease from Gait
This provides a more efficient and accurate diagnostic tool for Parkinson's Disease patients, though it is incremental as it builds on existing gait analysis methods.
The study tackled the problem of inaccurate Parkinson's Disease diagnosis from gait by proposing LPGNet, which uses Linear Prediction Residuals and a 1D CNN to achieve an AUC of 0.91 with a 21 times speedup and 99% fewer parameters compared to state-of-the-art methods.
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.