Using EEG spatial correlation, cross frequency energy, and wavelet coefficients for the prediction of Freezing of Gait in Parkinson's Disease patients

Abstract

Abstract-Parkinson's Disease (PD) patients with Freezing of Gait (FOG) often experience sudden and unpredictable failure in their ability to start or continue walking, making it potentially a dangerous symptom. Emerging knowledge about brain connectivity is leading to new insights into the pathophysiology of FOG and has suggested that electroencephalogram (EEG) may offer a novel technique for understanding and predicting FOG. In this study we have integrated spatial, spectral, and temporal features of the EEG signals utilizing wavelet coefficients as our input for the Multilayer Perceptron Neural Network and k-Nearest Neighbor classifier. This approach allowed us to predict transition from walking to freezing with 87 % sensitivity and 73 % accuracy. This preliminary data affirms the functional breakdown between areas in the brain during FOG and suggests that EEG offers potential as a therapeutic strategy in advanced PD.

Microstructural changes in white matter associated with freezing of gait in Parkinson's disease

“…Freezers also recruited striatofrontal areas differently than non‐freezers during rhythmical movement of the lower and upper limbs . Recent studies pointed to disturbed neuronal activation in basal ganglia and frontoparietal regions during the course of freezing episodes in the limbs and in gait . Despite the different methodological paradigms and neuroimaging techniques used, all of this work suggests that a dysfunction of higher‐order brain centers in conjunction with midbrain and brainstem regions involved in the dynamic and rhythmical control of gait and other movements are implicated in FOG.…”

“…13,14 Recent studies pointed to disturbed neuronal activation in basal ganglia and frontoparietal regions during the course of freezing episodes in the limbs and in gait. [14][15][16][17][18][19] Despite the different methodological paradigms and neuroimaging techniques used, all of this work suggests that a dysfunction of higher-order brain centers in conjunction with midbrain and brainstem regions involved in the dynamic and rhythmical control of gait 3 and other movements 20 are implicated in FOG. A similar view stems from structural imaging studies revealing reduced gray matter volume in frontal, precentral sensorimotor, posterior parietal regions, [21][22][23] and brainstem pathology 11 in freezers.…”

Prediction of freezing of gait using analysis of brain effective connectivity

“…Based on this analysis, two other groups were determined: normal walking data and transition data (5 seconds before freezing), as has been reported elsewhere [5]. After removing the EEG data segment that were affected by artifact using visual inspection, 843 selected samples data were filtered from the low and high frequency noise and 50 Hz line frequency using band-pass (0.5-60 Hz) and bandstop (50Hz) Butterworth IIR with zero phase shift.…”

“…This system enabled to detect FOG with a sensitivity of 83%, however the specificity was only 58% and accuracy 70% [5]. Compared to motion sensors, such as accelerometers or EMG [6], EEG has an advantage in its ability to track the physiological process of freezing from the earliest stage throughout the analysis of brain dynamics, which also provides insights into possible pathophysiological mechanisms underlying neurological development and disease.…”

Detection of Brain Diseases using EEG and Speech Signal

“…The freezing of PD patient is identified by back propagation neural network. James M.Shine.et.al [6] introduced multilayer perceptron neural network and k nearest neighbour classification method for integration of spatial, spectral and temporal features of EEG signals. Ingeborg H. Hansen.et.al [7] studied classification method of EEG with two classes control subjects and iRBD.…”