Predicting Freezing of Gait in Parkinsons Disease Patients Using Machine Learning

Freezing of gait (FoG) is one of the most alarming motor symptoms of Parkinson's disease, most commonly experienced by subjects who have suffered from the disease for a long period of time. Furthermore, freezing of gait can lead to falls and may result to nursing home admissions which can negatively affect the quality of life for patients, in addition to raising a broader set of socioeconomic consequences. In this research, machine learning algorithms are utilised as means of identifying the freezing of gait event prior to its onset. An accelerometer time series dataset containing 237 individual Freezing of Gait events over 8 patients was considered, from which features were extracted and presented to 7 machine learning classifiers. Our simulation results indicated that machine learning algorithms are powerful tools for the early prediction of freezing of gait, capable of obtaining high sensitivity and specificity for the identification of the onset of Freezing of Gait. Support Vector Machines with Polynomial kernel achieved the highest performance in comparison with the benchmarked techniques. The classification algorithm was applied to 5 second windows using 18 features, obtaining balanced accuracies (the mean value of sensitivity and specificity) of 91 %, 90%, and 82% over the Walk, FoG and Transition classes, respectively.

[1]  Jeffrey M. Hausdorff,et al.  Time series analysis of leg movements during freezing of gait in Parkinson's disease: akinesia, rhyme or reason? , 2003 .

[2]  Fernanda Irrera,et al.  Reliable and Robust Detection of Freezing of Gait Episodes With Wearable Electronic Devices , 2017, IEEE Sensors Journal.

[3]  Pablo Martinez-Martin,et al.  Non-motor symptoms of Parkinson's disease A review…from the past , 2014, Journal of the Neurological Sciences.

[4]  T. Gneiting,et al.  Estimators of Fractal Dimension : Assessing the Roughness of Time Series and Spatial Data , 2010 .

[5]  C. Sutton Classification and Regression Trees, Bagging, and Boosting , 2005 .

[6]  Haritz Zabaleta,et al.  The effect of visual cues on the number and duration of freezing episodes in Parkinson's patients , 2012, 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[7]  Houeto Jean-Luc [Parkinson's disease]. , 2022, La Revue du praticien.

[8]  Andreas Christmann,et al.  Support vector machines , 2008, Data Mining and Knowledge Discovery Handbook.

[9]  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.

[10]  D. Aarsland,et al.  Predictors of Nursing Home Placement in Parkinson's Disease: A Population‐Based, Prospective Study , 2000, Journal of the American Geriatrics Society.

[11]  Federica Verdini,et al.  A smartphone-based architecture to detect and quantify freezing of gait in Parkinson's disease. , 2016, Gait & posture.

[12]  Hung T. Nguyen,et al.  Using EEG spatial correlation, cross frequency energy, and wavelet coefficients for the prediction of Freezing of Gait in Parkinson's Disease patients , 2013, 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[13]  Sinziana Mazilu,et al.  Feature Learning for Detection and Prediction of Freezing of Gait in Parkinson's Disease , 2013, MLDM.

[14]  Nir Giladi,et al.  Freezing phenomenon in patients with parkinsonian syndromes , 1997, Movement disorders : official journal of the Movement Disorder Society.

[15]  Nooritawati Md Tahir,et al.  Anomalous gait detection based on Support Vector Machine , 2011, 2011 IEEE International Conference on Computer Applications and Industrial Electronics (ICCAIE).

[16]  M Onofrj,et al.  Prevalence and associated features of self-reported freezing of gait in Parkinson disease: The DEEP FOG study. , 2015, Parkinsonism & related disorders.

[17]  Luca Palmerini,et al.  Identification of Characteristic Motor Patterns Preceding Freezing of Gait in Parkinson’s Disease Using Wearable Sensors , 2017, Front. Neurol..

[18]  Witold R. Rudnicki,et al.  Boruta - A System for Feature Selection , 2010, Fundam. Informaticae.

[19]  Bernhard Schölkopf,et al.  Comparing support vector machines with Gaussian kernels to radial basis function classifiers , 1997, IEEE Trans. Signal Process..

[20]  Jeffrey M. Hausdorff,et al.  Wearable Assistant for Parkinson’s Disease Patients With the Freezing of Gait Symptom , 2010, IEEE Transactions on Information Technology in Biomedicine.

[21]  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.

[22]  Mohammad Azzeh,et al.  User Movement Prediction: The Contribution of Machine Learning Techniques , 2016, 2016 15th IEEE International Conference on Machine Learning and Applications (ICMLA).

[23]  M. W Gardner,et al.  Artificial neural networks (the multilayer perceptron)—a review of applications in the atmospheric sciences , 1998 .

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

[25]  P. James An Essay on the Shaking Palsy , 1817, The Medico-Chirurgical Journal and Review.

[26]  Nick S. Jones,et al.  Highly Comparative Feature-Based Time-Series Classification , 2014, IEEE Transactions on Knowledge and Data Engineering.

[27]  Tianqi Chen,et al.  XGBoost: A Scalable Tree Boosting System , 2016, KDD.

[28]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[29]  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.

[30]  Jeffrey M. Hausdorff,et al.  The role of mental function in the pathogenesis of freezing of gait in Parkinson's disease , 2006, Journal of the Neurological Sciences.

[31]  Valentina Dilda,et al.  Autonomous identification of freezing of gait in Parkinson's disease from lower-body segmental accelerometry , 2013, Journal of NeuroEngineering and Rehabilitation.

[32]  Jeffrey M. Hausdorff,et al.  A Wearable System to Assist Walking of Parkinson´s Disease Patients , 2009, Methods of Information in Medicine.

[33]  Eryk Dutkiewicz,et al.  Freezing of Gait Detection in Parkinson's Disease: A Subject-Independent Detector Using Anomaly Scores , 2017, IEEE Transactions on Biomedical Engineering.

[34]  Andreu Català,et al.  Determining the optimal features in freezing of gait detection through a single waist accelerometer in home environments , 2017, Pattern Recognit. Lett..

[35]  Andreu Català,et al.  Home detection of freezing of gait using support vector machines through a single waist-worn triaxial accelerometer , 2017, PloS one.

[36]  M. Hallett,et al.  Freezing of gait: moving forward on a mysterious clinical phenomenon , 2011, The Lancet Neurology.

[37]  Ryan M. Rifkin,et al.  In Defense of One-Vs-All Classification , 2004, J. Mach. Learn. Res..

[38]  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.

[39]  James M. Shine,et al.  Analysis and Prediction of the Freezing of Gait Using EEG Brain Dynamics , 2015, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[40]  P. Rea Chapter 3 – Forebrain , 2015 .

[41]  W. Ondo,et al.  Ambulatory monitoring of freezing of gait in Parkinson's disease , 2008, Journal of Neuroscience Methods.

[42]  Lorene M Nelson,et al.  Incidence of Parkinson's disease: variation by age, gender, and race/ethnicity. , 2003, American journal of epidemiology.

[43]  J. M. Shine,et al.  The pathophysiological mechanisms underlying freezing of gait in Parkinson’s Disease , 2011, Journal of Clinical Neuroscience.

[44]  Sinziana Mazilu,et al.  Online detection of freezing of gait with smartphones and machine learning techniques , 2012, 2012 6th International Conference on Pervasive Computing Technologies for Healthcare (PervasiveHealth) and Workshops.

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

[46]  Oliver Kramer,et al.  K-Nearest Neighbors , 2013 .