Automatic detection of Parkinson's disease based on acoustic analysis of speech

Abstract This paper proposes a methodology to detect early signs of Parkinson’s disease (PD) through free-speech in uncontrolled background conditions. The early detection mechanism uses signal and speech processing techniques integrated with machine learning algorithms. Three distinct speech databases containing patients’ recordings at different stages of the PD are used for estimation of the parameters during the training and evaluation stages. The results reveal the potential in using Random Forest (RF) or Support Vector Machine (SVM) techniques. Once tuned, these algorithms provide a reliable computational method for estimating the presence of PD with a very high accuracy.

[1]  Danial Taheri Far,et al.  Speech Analysis for Diagnosis of Parkinson’s Disease Using Genetic Algorithm and Support Vector Machine , 2014 .

[2]  M. Daliri,et al.  Diagnosis of Parkinson's disease in human using voice signals , 2011 .

[3]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[4]  Bernhard E. Boser,et al.  A training algorithm for optimal margin classifiers , 1992, COLT '92.

[5]  Douglas C. Montgomery,et al.  Applied Statistics and Probability for Engineers, Third edition , 1994 .

[6]  Kesari Verma,et al.  Investigations on Impact of Feature Normalization Techniques on Classifier's Performance in Breast Tumor Classification , 2015 .

[7]  K. Bötzel,et al.  Costs of illness and care in Parkinson's Disease: An evaluation in six countries , 2011, European Neuropsychopharmacology.

[8]  Joaquin Vanschoren,et al.  Fast Algorithm Selection Using Learning Curves , 2015, IDA.

[9]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[10]  Saurabh Prasad,et al.  Limitations of Principal Components Analysis for Hyperspectral Target Recognition , 2008, IEEE Geoscience and Remote Sensing Letters.

[11]  Mehrbakhsh Nilashi,et al.  Accuracy Improvement for Predicting Parkinson’s Disease Progression , 2016, Scientific Reports.

[12]  Magnus Johnsson,et al.  Diagnosing Parkinson by using artificial neural networks and support vector machines , 2009 .

[13]  Youri Maryn,et al.  Perturbation Measures of Voice: A Comparative Study between Multi-Dimensional Voice Program and Praat , 2009, Folia Phoniatrica et Logopaedica.

[14]  Yongming Li,et al.  Classification of Parkinson’s disease utilizing multi-edit nearest-neighbor and ensemble learning algorithms with speech samples , 2016, BioMedical Engineering OnLine.

[15]  H. Abdi,et al.  Principal component analysis , 2010 .

[16]  F. Pagan,et al.  Improving outcomes through early diagnosis of Parkinson's disease. , 2012, The American journal of managed care.

[17]  Nello Cristianini,et al.  An Introduction to Support Vector Machines and Other Kernel-based Learning Methods , 2000 .

[18]  Fikret S. Gürgen,et al.  Collection and Analysis of a Parkinson Speech Dataset With Multiple Types of Sound Recordings , 2013, IEEE Journal of Biomedical and Health Informatics.

[19]  Antanas Verikas,et al.  Detecting Parkinson’s disease from sustained phonation and speech signals , 2017, PloS one.

[20]  Ahmed Hammouch,et al.  Voice analysis for detecting patients with Parkinson's disease using the hybridization of the best acoustic features , 2016 .

[21]  Henning Müller,et al.  Optimized Distributed Hyperparameter Search and Simulation for Lung Texture Classification in CT Using Hadoop , 2016, J. Imaging.

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

[23]  J. Os,et al.  Cost of disorders of the brain in Europe 2010 , 2011, European Neuropsychopharmacology.