Identification of Freezing of Gait in Parkinson’s Patients Using Instrumented Shoes and Artificial Neural Networks

Freezing of gait is an episodic phenomena faced by many patients with Parkinson’s disease. It is characterized by episodes during which patients are unable to generate effective forward stepping movements, despite absence of motor deficits. It has been postulated that the degree of freezing can be reduced by providing external sensory feedback to the patients during the event. However, this intervention could be facilitated by accurate identification of freezing events in real-time. This manuscript presents an Artificial Neural Network model which uses signals recorded by an instrumented footwear to predict if a walking subject is having a freezing episode. Our model presented in this paper is capable of continuously predicting freezing of gait events at a high temporal resolution of 50 Hz, using a 0.5 second window of data recorded by the instrumented shoes, with a sensitivity of 96.0±2.5%, a specificity of 99.6±0.3%, a precision of 89.5±5.9%, and an accuracy of 99.5±0.4%. This algorithm was tested with data collected from 10 patients with Parkinson’s disease with frequent freezing of gait episodes.

[1]  Max A. Little,et al.  Freezing of gait and fall detection in Parkinson’s disease using wearable sensors: a systematic review , 2017, Journal of Neurology.

[2]  Thurmon E. Lockhart,et al.  Towards Real-Time Detection of Freezing of Gait Using Wavelet Transform on Wireless Accelerometer Data , 2016, Sensors.

[3]  J. van Leeuwen,et al.  Neural Networks: Tricks of the Trade , 2002, Lecture Notes in Computer Science.

[4]  M. Hallett.  The intrinsic and extrinsic aspects of freezing of gait , 2008, Movement disorders : official journal of the Movement Disorder Society.

[5]  Talia Herman,et al.  Reliability of the new freezing of gait questionnaire: agreement between patients with Parkinson's disease and their carers. , 2009, Gait & posture.

[6]  Ariel Linden.  Measuring diagnostic and predictive accuracy in disease management: an introduction to receiver operating characteristic (ROC) analysis. , 2006, Journal of evaluation in clinical practice.

[7]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[8]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[9]  Jeffrey M. Hausdorff,et al.  Falls and freezing of gait in Parkinson's disease: A review of two interconnected, episodic phenomena , 2004, Movement disorders : official journal of the Movement Disorder Society.

[10]  P. Lorenzi,et al.  Smart sensors for the recognition of specific human motion disorders in Parkinson's disease , 2015, 2015 6th International Workshop on Advances in Sensors and Interfaces (IWASI).

[11]  Yoshua Bengio,et al.  Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling , 2014, ArXiv.

[12]  A. Lozano,et al.  Deep brain stimulation for movement disorders: 2015 and beyond. , 2015, Current opinion in neurology.

[13]  Nir Giladi,et al.  Understanding and treating freezing of gait in parkinsonism, proposed working definition, and setting the stage , 2008, Movement disorders : official journal of the Movement Disorder Society.

[14]  G. Kwakkel,et al.  Cueing training in the home improves gait-related mobility in Parkinson’s disease: the RESCUE trial , 2007, Journal of Neurology, Neurosurgery & Psychiatry.

[15]  M. Suteerawattananon,et al.  Effects of visual and auditory cues on gait in individuals with Parkinson's disease , 2004, Journal of the Neurological Sciences.

[16]  Quoc V. Le,et al.  Sequence to Sequence Learning with Neural Networks , 2014, NIPS.

[17]  Dimitrios I. Fotiadis,et al.  Automatic detection of freezing of gait events in patients with Parkinson's disease , 2013, Comput. Methods Programs Biomed..

[18]  D. Tarsy,et al.  Laserlight cues for gait freezing in Parkinson's disease: an open-label study. , 2011, Parkinsonism & related disorders.

[19]  M. Hallett,et al.  Physiology of freezing of gait , 2016, Annals of neurology.

[20]  Jitendra Malik,et al.  Recurrent Network Models for Human Dynamics , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[21]  Nilanjan Dey,et al.  Discrete wavelet transform-based freezing of gait detection in Parkinson’s disease , 2018, J. Exp. Theor. Artif. Intell..

[22]  Alberto Costa,et al.  Detecting freezing of gait with a tri-axial accelerometer in Parkinson’s disease patients , 2015, Medical & Biological Engineering & Computing.

[23]  Nir Giladi,et al.  Characterization of freezing of gait subtypes and the response of each to levodopa in Parkinson's disease , 2003, European journal of neurology.

[24]  Nir Giladi,et al.  Freezing of gait in patients with advanced Parkinson's disease , 2001, Journal of Neural Transmission.

[25]  A. Gordon,et al.  Gait Segmentation of Data Collected by Instrumented Shoes Using a Recurrent Neural Network Classifier. , 2019, Physical medicine and rehabilitation clinics of North America.

[26]  Xiaoli Li,et al.  Deep Convolutional Neural Networks on Multichannel Time Series for Human Activity Recognition , 2015, IJCAI.

[27]  Sinziana Mazilu,et al.  Prediction of Freezing of Gait in Parkinson's From Physiological Wearables: An Exploratory Study , 2015, IEEE Journal of Biomedical and Health Informatics.

[28]  Andreu Català,et al.  Comparison of Features, Window Sizes and Classifiers in Detecting Freezing of Gait in Patients with Parkinson's Disease Through a Waist-Worn Accelerometer , 2016, CCIA.

[29]  E. Katunina,et al.  [Epidemiology of Parkinson's disease]. , 2013, Zhurnal nevrologii i psikhiatrii imeni S.S. Korsakova.