Detection of Freezing of Gait Using Convolutional Neural Networks and Data From Lower Limb Motion Sensors.

Parkinson's disease (PD) is a chronic, non-reversible neurodegenerative disorder, and freezing of gait (FOG) is one of the most disabling symptoms in PD as it is often the leading cause of falls and injuries that drastically reduces patients' quality of life. In order to monitor continuously and objectively PD patients who suffer from FOG and enable the possibility of on-demand cueing assistance, a sensor-based FOG detection solution can help clinicians manage the disease and help patients overcome freezing episodes. Many recent studies have leveraged deep learning models to detect FOG using signals extracted from inertial measurement unit (IMU) devices. Usually, the latent features and patterns of FOG are discovered from either the time or frequency domain. In this study, we investigated the use of the time-frequency domain by applying the Continuous Wavelet Transform to signals from IMUs placed on the lower limbs of 63 PD patients who suffered from FOG. We built convolutional neural networks to detect the FOG occurrences, and employed the Bayesian Optimisation approach to obtain the hyper-parameters. The results showed that the proposed subject-independent model was able to achieve a geometric mean of 90.7% and a F1 score of 91.5%.

Convolutional Neural Network for Freezing of Gait Detection Leveraging the Continuous Wavelet Transform on Lower Extremities Wearable Sensors Data.

Freezing of Gait is the most disabling gait disturbance in Parkinson's disease. For the past decade, there has been a growing interest in applying machine learning and deep learning models to wearable sensor data to detect Freezing of Gait episodes. In our study, we recruited sixty-seven Parkinson's disease patients who have been suffering from Freezing of Gait, and conducted two clinical assessments while the patients wore two wireless Inertial Measurement Units on their ankles. We converted the recorded time-series sensor data into continuous wavelet transform scalograms and trained a Convolutional Neural Network to detect the freezing episodes. The proposed model achieved a generalisation accuracy of 89.2% and a geometric mean of 88.8%.

The effects of toe spreader in people with overactive toe flexors post stroke: a randomized controlled pilot study.

OBJECTIVES: To investigate the long-term effects of the toe spreader on gait characteristics, pain, activity level and balance in individuals with chronic stroke who exhibited tonic toe flexion reflex. The secondary objectives were to determine the sample size for future studies and to assess compliance to the use of the toe spreader. DESIGN: Single-blind, randomized controlled pilot trial. SETTING: Outpatient clinic of a tertiary hospital in Singapore. SUBJECTS: Nine ambulatory participants with tonic toe flexion reflex more than six months post stroke. INTERVENTION: Control or customized toe spreader groups for six months. The toe spreader was made of Rolyan Ezemix elastomer putty and worn with sport sandals during ambulation. MAIN MEASURES: Gait speed and plantar surface contact area, pain visual analogue scale (VAS), Berg Balance Scale, Modified Ashworth Scale, activity level measured on pedometer and compliance via logbook. RESULTS: There were no significant differences between the groups. Both groups showed non-significant improvements in gait speed (toe spreader 0.34 (0.26) versus 0.37 (0.29) m/s; control 0.40 (0.27) versus 0.50 (0.17) m/s), activity level, step length of the hemiplegic leg and stride length at six months. All participants in the intervention group used the toe spreader less than 50% of the days, indicating suboptimal compliance. CONCLUSION: The use of the toe spreader did not result in significant improvements in any outcomes. Studies with sample sizes of at least 56 participants and strategies to increase compliance to the use of the toe spreader are recommended.