Context Recognition Algorithms for Energy-Efficient Freezing-of-Gait Detection in Parkinson's Disease

Abstract

Freezing of gait (FoG) is a disabling clinical phenomenon of Parkinson's disease (PD) characterized by the inability to move the feet forward despite the intention to walk. It is one of the most troublesome symptoms of PD, leading to an increased risk of falls and reduced quality of life. The combination of wearable inertial sensors and machine learning (ML) algorithms represents a feasible solution to monitor FoG in real-world scenarios. However, traditional FoG detection algorithms process all data indiscriminately without considering the context of the activity during which FoG occurs. This study aimed to develop a lightweight, context-aware algorithm that can activate FoG detection systems only under certain circumstances, thus reducing the computational burden. Several approaches were implemented, including ML and deep learning (DL) gait recognition methods, as well as a single-threshold method based on acceleration magnitude. To train and evaluate the context algorithms, data from a single inertial sensor were extracted using three different datasets encompassing a total of eighty-one PD patients. Sensitivity and specificity for gait recognition ranged from 0.95 to 0.96 and 0.80 to 0.93, respectively, with the one-dimensional convolutional neural network providing the best results. The threshold approach performed better than ML- and DL-based methods when evaluating the effect of context awareness on FoG detection performance. Overall, context algorithms allow for discarding more than 55% of non-FoG data and less than 4% of FoG episodes. The results indicate that a context classifier can reduce the computational burden of FoG detection algorithms without significantly affecting the FoG detection rate. Thus, implementation of context awareness can present an energy-efficient solution for long-term FoG monitoring in ambulatory and free-living settings.

Keywords: Parkinson’s disease; accelerometer; context awareness; convolutional neural network; freezing of gait (FoG); human activity recognition; machine learning; random forest; wearable sensors.

Figure 1

Proposed framework that uses context recognition algorithms for FoG detection. RF: random forest; LR: logistic regression; CNN: convolutional neural network; PD: Parkinson’s disease; FoG: freezing of gait.

Figure 2

Segmentation process performed on raw acceleration data using windows of 2 s sliding with a step of 0.5 s.

Figure 3

Proposed architecture of the 1D CNN with separable convolutions.

Figure 4

(Left) The 3D acceleration signals along with the resulting magnitude vector (violet). A zoomed image of gait signals is also reported. (Right) Histograms reporting the distribution of the magnitude vector values for gait and other activities. Data represents the ADL dataset.

Figure 5

Schematic of the measures computed for evaluating the performance of the gait recognition approaches for context-aware FoG detection. A: activation horizon; B: activation delay.

Figure 6

Performance in gait detection as the threshold on the magnitude vector varies.