Early Detection of Parkinson’s Disease Using Deep Learning and Machine Learning

Accurately detecting Parkinson’s disease (PD) at an early stage is certainly indispensable for slowing down its progress and providing patients the possibility of accessing to disease-modifying therapy. Towards this end, the premotor stage in PD should be carefully monitored. An innovative deep-learning technique is introduced to early uncover whether an individual is affected with PD or not based on premotor features. Specifically, to uncover PD at an early stage, several indicators have been considered in this study, including Rapid Eye Movement and olfactory loss, Cerebrospinal fluid data, and dopaminergic imaging markers. A comparison between the proposed deep learning model and twelve machine learning and ensemble learning methods based on relatively small data including 183 healthy individuals and 401 early PD patients shows the superior detection performance of the designed model, which achieves the highest accuracy, 96.45% on average. Besides detecting the PD, we also provide the feature importance on the PD detection process based on the Boosting method.

[1]  Tsuyoshi Murata,et al.  {m , 1934, ACML.

[2]  Neha Singh,et al.  Advances in the treatment of Parkinson's disease , 2007, Progress in Neurobiology.

[3]  Wei-Yin Loh,et al.  Classification and regression trees , 2011, WIREs Data Mining Knowl. Discov..

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

[5]  R. Doty,et al.  Development of the university of pennsylvania smell identification test: A standardized microencapsulated test of olfactory function , 1984, Physiology & Behavior.

[6]  Resul Das,et al.  A comparison of multiple classification methods for diagnosis of Parkinson disease , 2010, Expert Syst. Appl..

[7]  Tara N. Sainath,et al.  Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups , 2012, IEEE Signal Processing Magazine.

[8]  W. Marsden.  I and J , 2012 .

[9]  Roberto Rosas-Romero,et al.  Automatic Parkinson disease detection at early stages as a pre-diagnosis tool by using classifiers and a small set of vocal features , 2020 .

[10]  Ian Butterworth,et al.  Detection of Motor Impairment in Parkinson's Disease Via Mobile Touchscreen Typing , 2017, IEEE Transactions on Biomedical Engineering.

[11]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[12]  R. Prashanth,et al.  Early detection of Parkinson's disease through patient questionnaire and predictive modelling , 2018, Int. J. Medical Informatics.

[13]  J. Friedman.  Greedy function approximation: A gradient boosting machine. , 2001 .

[14]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  Demis Hassabis,et al.  Improved protein structure prediction using potentials from deep learning , 2020, Nature.

[16]  Pavel Sovka,et al.  Validation of freely-available pitch detection algorithms across various noise levels in assessing speech captured by smartphone in Parkinson's disease , 2020, Biomed. Signal Process. Control..

[17]  Peter Buhlmann,et al.  BOOSTING ALGORITHMS: REGULARIZATION, PREDICTION AND MODEL FITTING , 2007, 0804.2752.

[18]  Max A. Little,et al.  Accurate Telemonitoring of Parkinson's Disease Progression by Noninvasive Speech Tests , 2009, IEEE Transactions on Biomedical Engineering.

[19]  Trevor Hastie,et al.  Regularization Paths for Generalized Linear Models via Coordinate Descent. , 2010, Journal of statistical software.

[20]  Ming Tang,et al.  Predictive Big Data Analytics: A Study of Parkinson’s Disease Using Large, Complex, Heterogeneous, Incongruent, Multi-Source and Incomplete Observations , 2016, PloS one.

[21]  David R Williams,et al.  The use of a color coded probability scale to interpret smell tests in suspected parkinsonism , 2009, Movement disorders : official journal of the Movement Disorder Society.

[22]  Yehezkel S. Resheff,et al.  A wavelet-based approach to monitoring Parkinson's disease symptoms , 2016, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[23]  Zdenek Smekal,et al.  Decision Support Framework for Parkinson’s Disease Based on Novel Handwriting Markers , 2015, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[24]  Nilanjan Dey,et al.  Long short term memory based patient-dependent model for FOG detection in Parkinson's disease , 2020, Pattern Recognit. Lett..

[25]  Jie Li,et al.  A hybrid spatio-temporal model for detection and severity rating of Parkinson's disease from gait data , 2018, Neurocomputing.

[26]  Ana Madureira,et al.  Automatic detection of Parkinson's disease based on acoustic analysis of speech , 2019, Eng. Appl. Artif. Intell..

[27]  Amir Shmuel,et al.  Detection of Parkinson's disease based on voice patterns ranking and optimized support vector machine , 2019, Biomed. Signal Process. Control..

[28]  Robert X. Gao,et al.  Deep learning and its applications to machine health monitoring , 2019, Mechanical Systems and Signal Processing.

[29]  A. Singleton,et al.  The Parkinson Progression Marker Initiative (PPMI) , 2011, Progress in Neurobiology.

[30]  Hakan Gunduz,et al.  Deep Learning-Based Parkinson’s Disease Classification Using Vocal Feature Sets , 2019, IEEE Access.

[31]  M. Ebadi,et al.  Biomarkers in Parkinson’s disease (recent update) , 2013, Neurochemistry International.

[32]  R. Prashanth,et al.  High-Accuracy Detection of Early Parkinson's Disease through Multimodal Features and Machine Learning , 2016, Int. J. Medical Informatics.

[33]  Marcos Faúndez-Zanuy,et al.  Evaluation of handwriting kinematics and pressure for differential diagnosis of Parkinson's disease , 2016, Artif. Intell. Medicine.

[34]  Max A. Little,et al.  Suitability of Dysphonia Measurements for Telemonitoring of Parkinson's Disease , 2008, IEEE Transactions on Biomedical Engineering.

[35]  Guillaume-Alexandre Bilodeau,et al.  Deep 1D-Convnet for accurate Parkinson disease detection and severity prediction from gait , 2019, Expert Syst. Appl..

[36]  Jason Weston,et al.  A unified architecture for natural language processing: deep neural networks with multitask learning , 2008, ICML '08.

[37]  Yoav Freund,et al.  Boosting the margin: A new explanation for the effectiveness of voting methods , 1997, ICML.

[38]  Geert Mayer,et al.  The REM sleep behavior disorder screening questionnaire—A new diagnostic instrument , 2007, Movement disorders : official journal of the Movement Disorder Society.

[39]  Süleyman Bilgin,et al.  The impact of feature extraction for the classification of amyotrophic lateral sclerosis among neurodegenerative diseases and healthy subjects , 2017, Biomed. Signal Process. Control..

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

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

[42]  Luca Citi,et al.  Assessment of spontaneous cardiovascular oscillations in Parkinson's disease , 2016, Biomed. Signal Process. Control..

[43]  Hritik Bansal,et al.  An improved sex-specific and age-dependent classification model for Parkinson's diagnosis using handwriting measurement , 2019, Comput. Methods Programs Biomed..