The Classification of Minor Gait Alterations Using Wearable Sensors and Deep Learning

Objective: This paper describes how non-invasive wearable sensors can be used in combination with deep learning to classify artificially induced gait alterations without the requirement for a medical professional or gait analyst to be present. This approach is motivated by the goal of diagnosing gait abnormalities on a symptom-by-symptom basis, irrespective of other neuromuscular movement disorders the patients may be affected by. This could lead to improvements in treatment and offer a greater insight into movement disorders. Methods: In-shoe pressure was measured for 12 able-bodied participants, each subject to eight artificially induced gait alterations, achieved by modifying the underside of the shoe. The data were recorded at 100 Hz over 2520 data channels and were analyzed using the deep learning architecture and the long term short term memory networks. Additionally, the rationale for the decision-making process of these networks was investigated. Conclusion: Long term short term memory networks are applicable to the classification of the gait function. The classifications can be made using only 2 s of sparse data (82.0% accuracy over 96 000 instances of test data) from participants who were not a part of the training set. Significance: This paper provides potential for the gait function to be accurately classified using non-invasive techniques, and at more regular intervals, outside of a clinical setting, without the need for healthcare professionals to be present.

[1]  Richard Socher,et al.  Ask Me Anything: Dynamic Memory Networks for Natural Language Processing , 2015, ICML.

[2]  David Vandyke,et al.  Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systems , 2015, EMNLP.

[3]  P. J. Valenciano,et al.  Correlation among the Visual Gait Assessment Scale, Edinburgh Visual Gait Scale and Observational Gait Scale in children with spastic diplegic cerebral palsy. , 2012, Revista brasileira de fisioterapia (Sao Carlos (Sao Paulo, Brazil)).

[4]  Thomas Kohlmann,et al.  Systematic literature review and validity evaluation of the Expanded Disability Status Scale (EDSS) and the Multiple Sclerosis Functional Composite (MSFC) in patients with multiple sclerosis , 2013, BMC Neurology.

[5]  R. D. McLeish,et al.  An investigation of the centres of pressure under the foot while walking. , 1975, The Journal of bone and joint surgery. British volume.

[6]  S. Solomonidis,et al.  Performance of insole in reducing plantar pressure on diabetic Patients in the early stages of the disease , 2010, 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology.

[7]  Adam Rozumalski,et al.  The gait profile score and movement analysis profile. , 2009, Gait & posture.

[8]  Charles Elkan,et al.  Learning to Diagnose with LSTM Recurrent Neural Networks , 2015, ICLR.

[9]  Xiaogang Wang,et al.  Medical image classification with convolutional neural network , 2014, 2014 13th International Conference on Control Automation Robotics & Vision (ICARCV).

[10]  Wu Liu,et al.  Learning Efficient Spatial-Temporal Gait Features with Deep Learning for Human Identification , 2018, Neuroinformatics.

[11]  Kannan Balakrishnan,et al.  Offline handwritten Malayalam character recognition using stacked LSTM , 2017, 2017 International Conference on Intelligent Computing, Instrumentation and Control Technologies (ICICICT).

[12]  Mohsen Guizani,et al.  Deep Multi-Layer Perceptron Classifier for Behavior Analysis to Estimate Parkinson’s Disease Severity Using Smartphones , 2018, IEEE Access.

[13]  Ahmad Almogren,et al.  A robust human activity recognition system using smartphone sensors and deep learning , 2018, Future Gener. Comput. Syst..

[14]  Sungkuk Chun,et al.  Gait Estimation from Anatomical Foot Parameters Measured by a Foot Feature Measurement System using a Deep Neural Network Model , 2018, Scientific Reports.

[15]  Jason Yosinski,et al.  Deep neural networks are easily fooled: High confidence predictions for unrecognizable images , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[16]  T. Wren,et al.  Prevalence of specific gait abnormalities in children with cerebral palsy revisited: influence of age, prior surgery, and Gross Motor Function Classification System level , 2017, Developmental medicine and child neurology.

[17]  Sattar Alshryda,et al.  Development and Reliability of a System to Classify Gross Motor Function in Children with Cerebral Palsy , 2014 .

[18]  G. Deuschl,et al.  MDS clinical diagnostic criteria for Parkinson's disease , 2015, Movement disorders : official journal of the Movement Disorder Society.

[19]  Fabio Martinelli,et al.  Try Walking in My Shoes, if You Can: Accurate Gait Recognition Through Deep Learning , 2017, SAFECOMP Workshops.

[20]  Hermann Ney,et al.  A comprehensive study of deep bidirectional LSTM RNNS for acoustic modeling in speech recognition , 2016, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[21]  M. Jin,et al.  MDS clinical diagnostic criteria for Parkinson’s disease in China , 2017, Journal of Neurology.

[22]  Daniel Zahra,et al.  A comparison of customised and prefabricated insoles to reduce risk factors for neuropathic diabetic foot ulceration: a participant-blinded randomised controlled trial , 2012, Journal of Foot and Ankle Research.

[23]  J E Robb,et al.  Reliability and validity of the Edinburgh Visual Gait Score for cerebral palsy when used by inexperienced observers. , 2008, Gait & posture.

[24]  W. Poewe,et al.  Validation of the MDS clinical diagnostic criteria for Parkinson's disease , 2018, Movement disorders : official journal of the Movement Disorder Society.

[25]  Guang-Zhong Yang,et al.  Toward Pervasive Gait Analysis With Wearable Sensors: A Systematic Review , 2016, IEEE Journal of Biomedical and Health Informatics.

[26]  Joan Cabestany,et al.  Deep Learning for Detecting Freezing of Gait Episodes in Parkinson's Disease Based on Accelerometers , 2017, IWANN.

[27]  M. Gaston,et al.  The relationship between the Edinburgh Visual Gait Score, the Gait Profile Score and GMFCS levels I-III. , 2015, Gait & posture.

[28]  J. Nutt,et al.  Neurological disorders of gait, balance and posture: a sign-based approach , 2018, Nature Reviews Neurology.

[29]  Shyamal Patel,et al.  Automated assessment of gait deviations in children with cerebral palsy using a sensorized shoe and Active Shape Models , 2013, 2013 IEEE International Conference on Body Sensor Networks.

[30]  J. Kurtzke.  Rating neurologic impairment in multiple sclerosis , 1983, Neurology.

[31]  Guang-Zhong Yang,et al.  Deep Learning for Health Informatics , 2017, IEEE Journal of Biomedical and Health Informatics.

[32]  Massimiliano Pau,et al.  Clinical assessment of gait in individuals with multiple sclerosis using wearable inertial sensors: Comparison with patient-based measure. , 2016, Multiple sclerosis and related disorders.

[33]  Manuela Galli,et al.  Novel characterization of gait impairments in people with multiple sclerosis by means of the gait profile score , 2014, Journal of the Neurological Sciences.

[34]  Fernanda Irrera,et al.  l-DOPA and Freezing of Gait in Parkinson’s Disease: Objective Assessment through a Wearable Wireless System , 2017, Front. Neurol..

[35]  Susan J Hillman,et al.  Edinburgh Visual Gait Score for Use in Cerebral Palsy , 2003, Journal of pediatric orthopedics.

[36]  Shyamal Patel,et al.  A machine learning approach for gait speed estimation using skin-mounted wearable sensors: From healthy controls to individuals with multiple sclerosis , 2017, PloS one.

[37]  Pallavi Kulkarni,et al.  Integrated sensor system for gait analysis , 2016, 2016 International Conference on Electrical, Electronics, and Optimization Techniques (ICEEOT).

[38]  Samuel J. Reinfelder,et al.  Wearable sensors objectively measure gait parameters in Parkinson’s disease , 2017, PloS one.

[39]  Jürgen Schmidhuber,et al.  Framewise phoneme classification with bidirectional LSTM and other neural network architectures , 2005, Neural Networks.

[40]  M. Schwartz,et al.  The minimal clinically important difference for the Gait Profile Score. , 2012, Gait & posture.

[41]  F. Miller,et al.  Reliability and validity of Edinburgh visual gait score as an evaluation tool for children with cerebral palsy. , 2016, Gait & posture.

[42]  Heng Ji,et al.  A Language-Independent Neural Network for Event Detection , 2016, ACL 2016.

[43]  Li Fei-Fei,et al.  Every Moment Counts: Dense Detailed Labeling of Actions in Complex Videos , 2015, International Journal of Computer Vision.

[44]  Nira Herrmann,et al.  Accuracy, reliability, and validity of a spatiotemporal gait analysis system. , 2006, Medical engineering & physics.

[45]  I. Mackenzie.  GAIT, ABNORMALITIES OF , 1979 .

[46]  Houshang Darabi,et al.  LSTM Fully Convolutional Networks for Time Series Classification , 2017, IEEE Access.

[47]  P. Pronovost,et al.  A targeted real-time early warning score (TREWScore) for septic shock , 2015, Science Translational Medicine.

[48]  Jürgen Schmidhuber,et al.  LSTM: A Search Space Odyssey , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[49]  George D. Magoulas,et al.  Deep learning Parkinson's from smartphone data , 2017, 2017 IEEE International Conference on Pervasive Computing and Communications (PerCom).

[50]  Jérôme Louradour,et al.  Segmentation-free handwritten Chinese text recognition with LSTM-RNN , 2015, 2015 13th International Conference on Document Analysis and Recognition (ICDAR).

[51]  Sebastian Thrun,et al.  Dermatologist-level classification of skin cancer with deep neural networks , 2017, Nature.

[52]  Yvonne Freer,et al.  A Hierarchical Switching Linear Dynamical System Applied to the Detection of Sepsis in Neonatal Condition Monitoring , 2014, UAI.

[53]  Lovekesh Vig,et al.  Long Short Term Memory Networks for Anomaly Detection in Time Series , 2015, ESANN.

[54]  Seyed-Ahmad Ahmadi,et al.  V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation , 2016, 2016 Fourth International Conference on 3D Vision (3DV).