A new method based on quiet stance baseline is more effective in identifying freezing in Parkinson's disease

Abstract

Freezing, an episodic movement breakdown that goes from disrupted gait patterns to complete arrest, is a disabling symptom in Parkinson's disease. Several efforts have been made to objectively identify freezing episodes (FEs), although a standardized methodology to discriminate freezing from normal movement is lacking. Novel mathematical approaches that provide information in the temporal and frequency domains, such as the continuous wavelet transform, have demonstrated promising results detecting freezing, although still with limited effectiveness. We aimed to determine whether a computerized algorithm using the continuous wavelet transform based on baseline (i.e. no movement) rather than on amplitude decrease is more effective detecting freezing. Twenty-six individuals with Parkinson's disease performed two trials of a repetitive stepping-in-place task while they were filmed by a video camera and tracked by a motion capture system. The number of FEs and their total duration were determined from a visual inspection of the videos and from three different computed algorithms. Differences in the number and total duration of the FEs between the video inspection and each of the three methods were obtained. The accuracy to identify the time of occurrence of a FE by each method was also calculated. A significant effect of Method was found for the number (p = 0.016) and total duration (p = 0.013) of the FEs, with the method based on baseline being the closest one to the values reported from the videos. Moreover, the same method was the most accurate in detecting the time of occurrence, and the one reaching the highest sensitivity (88.2%). Findings suggest that threshold detection methods based on baseline and movement amplitude decreases capture different characteristics of Parkinsonian gait, with the first one being more effective at detecting FEs. Moreover, robust approaches that consider both time and frequency characteristics are more sensitive in identifying freezing.

Fig 1. Graphic representation of freezing detection by video inspection and a computerized algorithm.

A representative thirty-five second trial sample (5 s of baseline and 30 s of the stepping-in- place task) of the wavelet decomposition by the continuous wavelet transform of both heels, left (LHEE, blue line) and right (RHEE, red line). The gray windows on the top of the figure represent the freezing episodes identified by the algorithm of Method 1 (M1); the green windows at the bottom of the figure represent the freezing episodes identified by the observers in the Video 1 (V1). S1 represents the time where both, video and method, do not identify a freezing episode (FE), S2 represents the time where a FE was identified only in the video, S3 the time where a FE was identified only by the method, and S4 represents the time where both, video and method, identify a FE.

Fig 2. Area under the receiver operating characteristic (ROC) curve (AUC) obtained for the three methods.

Method 1 reached a higher AUC, followed by method 3 and then method 2.