Differential diagnosis of Parkinson and essential tremor with convolutional LSTM networks

Abstract This study aims to present a novel method for differentiation of Parkinsonian tremor (PT) and essential tremor (ET) using both postural and resting tremor. A convolutional long short-term memory (LSTM) that learns hand tremor recorded at both postural and resting positions is proposed for differentiation of PT and ET. 3D landmark points of hands at resting and postural positions are gathered using a Leap Motion Controller. A convolutional LSTM is trained for differentiation of ET and PT after preprocessing tremor data. The method is evaluated and tested on a dataset containing 40 subjects where 23 of them had PT and 17 of them had ET. The experiments showed that the accuracy of combined positions using both resting and postural tremor was higher than using single kind of positional tremor. The accuracy of tremor classification is 90% for the combined positions.

[1]  Xin-She Yang,et al.  Convolutional Neural Networks Applied for Parkinson's Disease Identification , 2016, Machine Learning for Health Informatics.

[2]  Tipu Z. Aziz,et al.  Resting tremor classification and detection in Parkinson's disease patients , 2015, Biomed. Signal Process. Control..

[3]  Z. Wszolek,et al.  Diagnosis and treatment of common forms of tremor. , 2011, Seminars in neurology.

[4]  Oren Cohen,et al.  Rest tremor in patients with essential tremor: prevalence, clinical correlates, and electrophysiologic characteristics. , 2003, Archives of neurology.

[5]  Steven K. Charles,et al.  Frequency response of the leap motion controller and its suitability for measuring tremor. , 2019, Medical engineering & physics.

[6]  M. Hoehn,et al.  Parkinsonism , 1967, Neurology.

[7]  Kwang Suk Park,et al.  Wrist sensor-based tremor severity quantification in Parkinson's disease using convolutional neural network , 2018, Comput. Biol. Medicine.

[8]  Muthuraman Muthuraman,et al.  A Neural Network Approach to Distinguish Parkinsonian Tremor from Advanced Essential Tremor , 2011, SocProS.

[9]  Philip R. Cohen,et al.  Application of machine learning and numerical analysis to classify tremor in patients affected with essential tremor or Parkinson's disease , 2012 .

[10]  Abhishek Nandy.  Introduction to Leap Motion , 2016 .

[11]  Peter H. Veltink,et al.  Quantification of Hand Motor Symptoms in Parkinson’s Disease: A Proof-of-Principle Study Using Inertial and Force Sensors , 2017, Annals of Biomedical Engineering.

[12]  Jun Dong,et al.  Premature ventricular contraction detection combining deep neural networks and rules inference , 2017, Artif. Intell. Medicine.

[13]  Luay Fraiwan,et al.  Parkinson’s disease hand tremor detection system for mobile application , 2016, Journal of medical engineering & technology.

[14]  W. Poewe,et al.  Prevalence of movement disorders in men and women aged 50–89 years (Bruneck Study cohort): a population-based study , 2005, The Lancet Neurology.

[15]  P. Kempster,et al.  A practical guide to the differential diagnosis of tremor , 2011, Postgraduate Medical Journal.

[16]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[17]  E. Tolosa,et al.  Differential diagnosis between Parkinson's disease and essential tremor using the smartphone's accelerometer , 2017, PloS one.

[18]  Kelvin L Chou.  Diagnosis and management of the patient with tremor. , 2004, Medicine and health, Rhode Island.

[19]  Fragile X-associated tremor/ataxia syndrome. , 2012, Handbook of clinical neurology.

[20]  M. Gresty,et al.  Tremor, the cogwheel phenomenon and clonus in Parkinson's disease. , 1981, Journal of neurology, neurosurgery, and psychiatry.

[21]  Ravi Sankar,et al.  Gait and tremor assessment for patients with Parkinson's disease using wearable sensors , 2016, ICT Express.

[22]  Paul Crawford,et al.  Differentiation and diagnosis of tremor. , 2011, American family physician.

[23]  A. Kocer,et al.  Nintendo Wii assessment of Hoehn and Yahr score with Parkinson's disease tremor. , 2016, Technology and health care : official journal of the European Society for Engineering and Medicine.

[24]  Pablo Mir,et al.  Distinguishing SWEDDs patients with asymmetric resting tremor from Parkinson's disease: A clinical and electrophysiological study , 2010, Movement disorders : official journal of the Movement Disorder Society.

[25]  G De Petris,et al.  Objective and automatic classification of Parkinson disease with Leap Motion controller , 2018, BioMedical Engineering OnLine.

[26]  Hyo Seon Jeon,et al.  Tremor frequency characteristics in Parkinson's disease under resting-state and stress-state conditions , 2016, Journal of the Neurological Sciences.

[27]  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).

[28]  M. Brin,et al.  Consensus Statement of the Movement Disorder Society on Tremor , 2008, Movement disorders : official journal of the Movement Disorder Society.

[29]  Yi Zheng,et al.  Time Series Classification Using Multi-Channels Deep Convolutional Neural Networks , 2014, WAIM.

[30]  Alex Graves,et al.  Generating Sequences With Recurrent Neural Networks , 2013, ArXiv.

[31]  Elan D Louis,et al.  Distinguishing essential tremor from Parkinson's disease: bedside tests and laboratory evaluations , 2012, Expert review of neurotherapeutics.

[32]  Clinical Differentiation of Essential Tremor and Parkinson’s Disease , 2013, Clinical medicine insights. Case reports.

[33]  Dit-Yan Yeung,et al.  Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting , 2015, NIPS.

[34]  J. Jankovic,et al.  Revisiting the relationship between essential tremor and Parkinson's disease , 2011, Movement disorders : official journal of the Movement Disorder Society.

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

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

[37]  Andrew M. Dai,et al.  Wearable sensors for Parkinson’s disease: which data are worth collecting for training symptom detection models , 2018, npj Digital Medicine.

[38]  J. Jankovic,et al.  Physiologic and pathologic tremors. Diagnosis, mechanism, and management. , 1980, Annals of internal medicine.

[39]  Tim Oates,et al.  Time series classification from scratch with deep neural networks: A strong baseline , 2016, 2017 International Joint Conference on Neural Networks (IJCNN).

[40]  J. Güttler,et al.  Unobtrusive Tremor Detection and Measurement via Human-Machine Interaction , 2015, EUSPN/ICTH.

[41]  Paola Pierleoni,et al.  A Classification System for Assessment and Home Monitoring of Tremor in Patients with Parkinson's Disease , 2018, Journal of medical signals and sensors.

[42]  K. Marder,et al.  Clinical correlates of action tremor in Parkinson disease. , 2001, Archives of neurology.

[43]  Björn Eskofier,et al.  Combined accelerometer and EMG analysis to differentiate essential tremor from Parkinson's disease , 2016, 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[44]  Martin K. Purvis,et al.  Parkinson's disease and essential tremor classification on mobile device , 2014, Pervasive Mob. Comput..

[45]  H. Katzen,et al.  An accelerometry-based study of lower and upper limb tremor in Parkinson’s disease , 2013, Journal of Clinical Neuroscience.