Objective and automatic classification of Parkinson disease with Leap Motion controller

BackgroundThe main objective of this paper is to develop and test the ability of the Leap Motion controller (LMC) to assess the motor dysfunction in patients with Parkinson disease (PwPD) based on the MDS-UPDRSIII exercises. Four exercises (thumb forefinger tapping, hand opening/closing, pronation/supination, postural tremor) were used to evaluate the characteristics described in MDS-UPDRSIII. Clinical ratings according to the MDS/UPDRS-section III items were used as target. For that purpose, 16 participants with PD and 12 healthy people were recruited in Ospedale Cisanello, Pisa, Italy. The participants performed standardized hand movements with camera-based marker. Time and frequency domain features related to velocity, angle, amplitude, and frequency were derived from the LMC data.ResultsDifferent machine learning techniques were used to classify the PD and healthy subjects by comparing the subjective scale given by neurologists against the predicted diagnosis from the machine learning classifiers. Feature selection methods were used to choose the most significant features. Logistic regression (LR), naive Bayes (NB), and support vector machine (SVM) were trained with tenfold cross validation with selected features. The maximum obtained classification accuracy with LR was 70.37%; the average area under the ROC curve (AUC) was 0.831. The obtained classification accuracy with NB was 81.4%, with AUC of 0.811. The obtained classification accuracy with SVM was 74.07%, with AUC of 0.675.ConclusionsResults revealed that the system did not return clinically meaningful data for measuring postural tremor in PwPD. In addition, it showed limited potential to measure the forearm pronation/supination. In contrast, for finger tapping and hand opening/closing, the derived parameters showed statistical and clinical significance. Future studies should continue to validate the LMC as updated versions of the software are developed. The obtained results support the fact that most of the set of selected features contributed significantly to classify the PwPD and healthy subjects.

[1]  Alfredo Berardelli,et al.  Bradykinesia in early and advanced Parkinson's disease , 2016, Journal of the Neurological Sciences.

[2]  Dimitrios Hristu-Varsakelis,et al.  Machine learning-based classification of simple drawing movements in Parkinson's disease , 2017, Biomed. Signal Process. Control..

[3]  Filippo Cavallo,et al.  Biomechanical parameter assessment for classification of Parkinson’s disease on clinical scale , 2017, Int. J. Distributed Sens. Networks.

[4]  Guillermo Sapiro,et al.  A Shared Vision for Machine Learning in Neuroscience , 2018, The Journal of Neuroscience.

[5]  N Jeremy Hill,et al.  Validation of the Leap Motion Controller using markered motion capture technology. , 2016, Journal of biomechanics.

[6]  Carmen Rodriguez-Blazquez,et al.  Parkinson Symptoms and Health Related Quality of Life as Predictors of Costs: A Longitudinal Observational Study with Linear Mixed Model Analysis , 2015, PloS one.

[7]  D. Kong,et al.  Automatic Classification of Early Parkinson's Disease with Multi-Modal MR Imaging , 2012, PloS one.

[8]  M. Mukaka,et al.  Statistics corner: A guide to appropriate use of correlation coefficient in medical research. , 2012, Malawi medical journal : the journal of Medical Association of Malawi.

[9]  Senem Velipasalar,et al.  Autonomous tracking and counting of footsteps by mobile phone cameras , 2015, 2015 49th Asilomar Conference on Signals, Systems and Computers.

[10]  Pietro Zanuttigh,et al.  Hand gesture recognition with jointly calibrated Leap Motion and depth sensor , 2015, Multimedia Tools and Applications.

[11]  Matthew J Johnson,et al.  Detection of Parkinson Disease Rest Tremor , 2014 .

[12]  F F Nobre,et al.  Comparison among probabilistic neural network, support vector machine and logistic regression for evaluating the effect of subthalamic stimulation in Parkinson disease on ground reaction force during gait. , 2010, Journal of biomechanics.

[13]  Ludovico Minati,et al.  Slow Breathing and Hypoxic Challenge: Cardiorespiratory Consequences and Their Central Neural Substrates , 2015, PloS one.

[14]  Ottavio Arancio,et al.  An Intracellular Threonine of Amyloid-β Precursor Protein Mediates Synaptic Plasticity Deficits and Memory Loss , 2013, PloS one.

[15]  Valeria Dibilio,et al.  Side effects induced by the acute levodopa challenge in Parkinson’s Disease and atypical parkinsonisms , 2017, PloS one.

[16]  Pietro Zanuttigh,et al.  Hand gesture recognition with leap motion and kinect devices , 2014, 2014 IEEE International Conference on Image Processing (ICIP).

[17]  Bijan Najafi,et al.  Motor Performance Assessment in Parkinson’s Disease: Association between Objective In-Clinic, Objective In-Home, and Subjective/Semi-Objective Measures , 2015, PloS one.

[18]  Filippo Cavallo,et al.  Automated Systems Based on Wearable Sensors for the Management of Parkinson's Disease at Home: A Systematic Review. , 2019, Telemedicine journal and e-health : the official journal of the American Telemedicine Association.

[19]  Dag Nyholm,et al.  A smartphone-based system to quantify dexterity in Parkinson's disease patients , 2017 .

[20]  S Micera,et al.  Technology and Innovative Services , 2011, IEEE Pulse.

[21]  A. Antonini,et al.  Anatomical Correlates of Cognitive Functions in Early Parkinson's Disease Patients , 2013, PloS one.

[22]  Alexandra Pfister,et al.  Comparative abilities of Microsoft Kinect and Vicon 3D motion capture for gait analysis , 2014, Journal of medical engineering & technology.

[23]  Phil Page,et al.  Beyond statistical significance: clinical interpretation of rehabilitation research literature. , 2014, International journal of sports physical therapy.

[24]  Dana Kulic,et al.  Data augmentation of wearable sensor data for parkinson’s disease monitoring using convolutional neural networks , 2017, ICMI.

[25]  John Cosmas,et al.  Recognition of postures and Freezing of Gait in Parkinson's disease patients using Microsoft Kinect sensor , 2015, 2015 7th International IEEE/EMBS Conference on Neural Engineering (NER).

[26]  C. Tanner,et al.  Projected number of people with Parkinson disease in the most populous nations, 2005 through 2030 , 2007, Neurology.

[27]  Jessica K. Hodgins,et al.  Quantitative measurement of motor symptoms in Parkinson's disease: A study with full-body motion capture data , 2011, 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[28]  P. Olivier,et al.  Accuracy of the Microsoft Kinect sensor for measuring movement in people with Parkinson's disease. , 2014, Gait & posture.

[29]  R. C. Oldfield.  The assessment and analysis of handedness: the Edinburgh inventory. , 1971, Neuropsychologia.

[30]  Debi Prosad Dogra,et al.  Computer-Vision-Assisted Palm Rehabilitation With Supervised Learning , 2016, IEEE Transactions on Biomedical Engineering.

[31]  F. Cavallo,et al.  How Wearable Sensors Can Support Parkinson's Disease Diagnosis and Treatment: A Systematic Review , 2017, Front. Neurosci..

[32]  Natasha M. Maurits,et al.  A Method for Automatic and Objective Scoring of Bradykinesia Using Orientation Sensors and Classification Algorithms , 2016, IEEE Transactions on Biomedical Engineering.

[33]  Mehrbakhsh Nilashi,et al.  A hybrid intelligent system for the prediction of Parkinson's Disease progression using machine learning techniques , 2017 .

[34]  David Ayares,et al.  Genetically-Engineered Pig-to-Baboon Liver Xenotransplantation: Histopathology of Xenografts and Native Organs , 2012, PloS one.

[35]  Filippo Cavallo,et al.  Leap motion evaluation for assessment of upper limb motor skills in Parkinson's disease , 2017, 2017 International Conference on Rehabilitation Robotics (ICORR).

[36]  Daphna Weinshall,et al.  Quantifying Levodopa-Induced Dyskinesia Using Depth Camera , 2015, 2015 IEEE International Conference on Computer Vision Workshop (ICCVW).

[37]  Anne Beuter,et al.  The measurement of tremor using a velocity transducer: comparison to simultaneous recordings using transducers of displacement, acceleration and muscle activity , 1999, Journal of Neuroscience Methods.

[38]  Kai-Hsiang Chen,et al.  Development of method for quantifying essential tremor using a small optical device , 2016, Journal of Neuroscience Methods.

[39]  Andrew Metcalfe,et al.  Feasibility of using the Leap Motion hand gesture sensor for tracking wrist fracture physiotherapy , 2017 .

[40]  Thomas Blaschke,et al.  Evaluation of Feature Selection Methods for Object-Based Land Cover Mapping of Unmanned Aerial Vehicle Imagery Using Random Forest and Support Vector Machine Classifiers , 2017, ISPRS Int. J. Geo Inf..

[41]  François Villeneuve,et al.  Feasibility Study of Hand Motion Analysis by the Leap Motion Sensor , 2016 .

[42]  R. Porcher,et al.  P Value and the Theory of Hypothesis Testing: An Explanation for New Researchers , 2010, Clinical orthopaedics and related research.

[43]  F. Marvasti.  Nonuniform sampling : theory and practice , 2001 .

[44]  J. Jankovic,et al.  Movement Disorder Society‐sponsored revision of the Unified Parkinson's Disease Rating Scale (MDS‐UPDRS): Scale presentation and clinimetric testing results , 2008, Movement disorders : official journal of the Movement Disorder Society.

[45]  Eric Yun,et al.  Analysis Of Machine Learning Classifier Performance In Adding Custom Gestures To The Leap Motion , 2016 .

[46]  David Schmidt,et al.  An Adaptive Interface Design (AID) for enhanced computer accessibility and rehabilitation , 2017, Int. J. Hum. Comput. Stud..

[47]  F. Cavallo,et al.  Comparative Motor Pre-clinical Assessment in Parkinson’s Disease Using Supervised Machine Learning Approaches , 2018, Annals of Biomedical Engineering.