Skip to main content
SpringerLink
Log in

Performance of machine learning methods in diagnosing Parkinson’s disease based on dysphonia measures

  • Original Article
  • Published:
Biomedical Engineering Letters Aims and scope Submit manuscript

Abstract

Parkinson’s disease (PD) is a widespread degenerative syndrome that affects the nervous system. Its early appearing symptoms include tremor, rigidity, and vocal impairment (dysphonia). Consequently, speech indicators are important in the identification of PD based on dysphonic signs. In this regard, computer-aided-diagnosis systems based on machine learning can be useful in assisting clinicians in identifying PD patients. In this work, we evaluate the performance of machine learning based techniques for PD diagnosis based on dysphonia symptoms. Several machine learning techniques were considered and trained with a set of twenty-two voice disorder measurements to classify healthy and PD patients. These machine learning methods included linear discriminant analysis (LDA), k nearest-neighbors (k-NN), naïve Bayes (NB), regression trees (RT), radial basis function neural networks (RBFNN), support vector machine (SVM), and Mahalanobis distance classifier. We evaluated the performance of these methods by means of a tenfold cross validation protocol. Experimental results show that the SVM classifier achieved higher average performance than all other classifiers in terms of overall accuracy, G-mean, and area under the curve of the receiver operating characteristic plot. The SVM classifier achieved higher performance measures than the majority of the other classifiers also in terms of sensitivity, specificity, and F-measure statistics. The LDA, k-NN and RT achieved the highest average precision. The RBFNN method yielded the highest F-measure.; however, it performed poorly in terms of other performance metrics. Finally, t tests were performed to evaluate statistical significance of the results, confirming that the SVM outperformed most of the other classifiers on the majority of performance measures. SVM is a promising method for identifying PD patients based on classification of dysphonia measurements.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2

Similar content being viewed by others

References

  1. Rojas A, Górriz JM, Ramírez J, Illán IA, Martínez-Murcia FJ, Ortiz A, Gómez Río M, Moreno-Caballero M. Application of empirical mode decomposition (EMD) on DaTSCAN SPECT images to explore Parkinson disease. Expert Syst Appl. 2013;40:2756–66.

    Article  Google Scholar 

  2. Lee S-H, Lim JS. Parkinson’s disease classification using gait characteristics and wavelet-based feature extraction. Expert Syst Appl. 2012;39:7338–44.

    Article  Google Scholar 

  3. Little MA, McSharry PE, Hunter EJ, Ramig LO. Suitability of dysphonia measurements for telemonitoring of Parkinson’s disease. IEEE Trans Biomed Eng. 2009;56:1015–22.

    Article  Google Scholar 

  4. Shabani H, Mikaili M, Noori SMR. Assessment of recurrence quantification analysis (RQA) of EEG for development of a novel drowsiness detection system. Biomed Eng Lett. 2016;6:196–204.

    Article  Google Scholar 

  5. Kumari VSR, Rajesh Kumar P. Fuzzy unordered rule induction for evaluating cardiac arrhythmia. Biomed Eng Lett. 2013;3:74–9.

    Article  Google Scholar 

  6. Bountris P, Topaka E, Pouliakis A, Haritou M, Karakitsos P, Koutsouris D. Development of a clinical decision support system using genetic algorithms and Bayesian classification for improving the personalised management of women attending a colposcopy room. Healthc Technol Lett. 2016;3:143–9.

    Article  Google Scholar 

  7. Vaijeyanthi V, Vishnuprasad K, Santhosh Kumar C, Ramachandran KI, Gopinath R, Kumar AA, Yadav PK. Towards enhancing the performance of multi-parameter patient monitors. Healthc Technol Lett. 2014;1:19–20.

    Article  Google Scholar 

  8. Das MK, Ari S. Patient-specific ECG beat classification technique. Healthc Technol Lett. 2014;1:98–103.

    Article  Google Scholar 

  9. Lahmiri S, Boukadoum M. New approach for automatic classification of Alzheimer’s disease, mild cognitive impairment and healthy brain magnetic resonance images. Healthc Technol Lett. 2014;1:32–6.

    Article  Google Scholar 

  10. Charisis VS, Hadjileontiadis LJ. Use of adaptive hybrid filtering process in Crohn’s disease lesion detection from real capsule endoscopy videos. Healthc Technol Lett. 2016;3:27–33.

    Article  Google Scholar 

  11. Tripathy RK, Sharma LN, Dandapat S. A new way of quantifying diagnostic information from multilead electrocardiogram for cardiac disease classification. Healthc Technol Lett. 2014;1:98–103.

    Article  Google Scholar 

  12. Kambhampati SS, Singh V, Manikandan MS, Ramkumar B. Unified framework for triaxial accelerometer-based fall event detection and classification using cumulants and hierarchical decision tree classifier. Healthc Technol Lett. 2015;2:101–7.

    Article  Google Scholar 

  13. Sayeed Ud Doulah ABM, Fattah SA, Zhu W-P, Ahmad MO. DCT domain feature extraction scheme based on motor unit action potential of EMG signal for neuromuscular disease classification. Healthc Technol Lett. 2014;1:26–31.

    Article  Google Scholar 

  14. Gandomkar Z, Bahrami F. Method to classify elderly subjects as fallers and non-fallers based on gait energy image. Healthc Technol Lett. 2014;1:110–4.

    Article  Google Scholar 

  15. Sahu O, Anand V, Kanhangad V, Pachori RB. Classification of magnetic resonance brain images using bi-dimensional empirical mode decomposition and autoregressive model. Biomed Eng Lett. 2015;5:311–20.

    Article  Google Scholar 

  16. Lahmiri S. Glioma detection based on multi-fractal features of segmented brain MRI by particle swarm optimization techniques. Biomed Signal Process Control. 2017;31:148–55.

    Article  Google Scholar 

  17. Lahmiri S. Image characterization by fractal descriptors in variational mode decomposition domain: application to brain magnetic resonance. Phys A. 2016;456:235–43.

    Article  MathSciNet  Google Scholar 

  18. Choi JY. A generalized multiple classifier system for improving computer-aided classification of breast masses in mammography. Biomed Eng Lett. 2015;5:251–62.

    Article  Google Scholar 

  19. Mert A, Kılıç N, Akan A. An improved hybrid feature reduction for increased breast cancer diagnostic performance. Biomed Eng Lett. 2014;4:285–91.

    Article  Google Scholar 

  20. Bajaj V, Pachori RB. Epileptic seizure detection based on the instantaneous area of analytic intrinsic mode functions of EEG signals. Biomed Eng Lett. 2013;3:17–21.

    Article  Google Scholar 

  21. Mohammadi MR, Khaleghi A, Nasrabadi AM, Rafieivand S, Begol M, Zarafshan H. EEG classification of ADHD and normal children using non-linear features and neural network. Biomed Eng Lett. 2016;6:66–73.

    Article  Google Scholar 

  22. Lahmiri S. High frequency based features for low and high retina hemorrhage classification. IET Healthc Technol Lett. 2017;. doi:10.1049/htl.2016.0067.

    Google Scholar 

  23. Lahmiri S, Gargour C, Gabrea M. Automated pathologies detection in retina digital images based on the complex continuous wavelet transform phase angles. IET Healthc Technol Lett. 2014;1:104–8.

    Google Scholar 

  24. Xu F, Zhou W, Zhen Y, Yuan Q. Classification of motor imagery tasks for electrocorticogram based brain–computer interface. Biomed Eng Lett. 2014;4:149–57.

    Article  Google Scholar 

  25. Zhang Z, Luo X. Heartbeat classification using decision level fusion. Biomed Eng Lett. 2014;4:388–95.

    Article  Google Scholar 

  26. Raj S, Maurya K, Ray KC. A knowledge-based real time embedded platform for arrhythmia beat classification. Biomed Eng Lett. 2015;5:271–80.

    Article  Google Scholar 

  27. Åström F, Koker R. A parallel neural network approach to prediction of Parkinson’s disease. Expert Syst Appl. 2011;38:12470–4.

    Article  Google Scholar 

  28. Babu GS, Suresh S, Mahanand BS. A novel PBL-McRBFN-RFE approach for identification of critical brain regions responsible for Parkinson’s disease. Expert Syst Appl. 2014;41:478–88.

    Article  Google Scholar 

  29. Cho C-W, Chao W-H, Lin S-H, Chen Y-Y. A vision-based analysis system for gait recognition in patients with Parkinson’s disease. Expert Syst Appl. 2009;36:7033–9.

    Article  Google Scholar 

  30. Zuo W-L, Wang Z-Y, Liu T, Chen H-L. Effective detection of Parkinson’s disease using an adaptive fuzzy k-nearest neighbor approach. Biomed Signal Process Control. 2013;8:364–73.

    Article  Google Scholar 

  31. Skodda S, Rinsche H, Schlegel U. Progression of dysprosody in Parkinson’s disease over time—a longitudinal study. Mov Disord. 2009;24:716–22.

    Article  Google Scholar 

  32. McLachlan GJ. Discriminant analysis and statistical pattern recognition. Hoboken: Wiley; 2004.

    MATH  Google Scholar 

  33. Cover T, Hart P. Nearest neighbor pattern classification. IEEE Trans Inf Theory. 1967;13:21–7.

    Article  MATH  Google Scholar 

  34. He QP, Wang J. Fault detection using the K-nearest neighbor rule for semiconductor manufacturing processes. IEEE Trans Semicond Manuf. 2007;20:345–54.

    Article  Google Scholar 

  35. Russell S, Norvig P. Artificial intelligence: a modern approach. Upper Saddle River: Prentice Hall; 2003.

    MATH  Google Scholar 

  36. Breiman L, Friedman JH, Olshen RA, Stone CJ. Classification and regression trees. Belmont: Wadsworth; 1984.

    MATH  Google Scholar 

  37. Poggio T, Girosi F. Networks for approximation and learning. Proc IEEE. 1990;78:1481–97.

    Article  MATH  Google Scholar 

  38. Vapnik VN. The nature of statistical learning theory. New York: Springer; 1995.

    Book  MATH  Google Scholar 

  39. Das R. A comparison of multiple classification methods for diagnosis of Parkinson disease. Expert Syst Appl. 2010;37:1568–72.

    Article  Google Scholar 

  40. Eskidere Ö, Ertas F, Hanilçi C. A comparison of regression methods for remote tracking of Parkinson’s disease progression. Expert Syst Appl. 2012;39:5523–8.

    Article  Google Scholar 

  41. Little MA, McSharry PE, Roberts SJ, Costello DAE, Moroz IM. Exploiting nonlinear recurrence and fractal scaling properties for voice disorder detection. Biomed Eng Online. 2007;6:23.

    Article  Google Scholar 

  42. Tsanas A, Little MA, McSharry PE, Ramig LO. Accurate telemonitoring of Parkinson’s disease progression by non-invasive speech tests. IEEE Trans Biomed Eng. 2010;57:884–93.

    Article  Google Scholar 

  43. Ergena B, Baykarab M, Polat C. An investigation on magnetic imaging findings of the inner ear: a relationship between the internal auditory canal, its nerves and benign paroxysmal positional vertigo. Biomed Signal Process Control. 2014;9:14–8.

    Article  Google Scholar 

  44. Flake GW. Square unit augmented, radially extended, multilayer perceptrons. In: Montavon G, Orr GB, Müller K-R, editors. Neural networks: tricks of the trade. Lecture Notes in Computer Science, vol. 7700. Berlin: Springer; 2012. p. 143–61.

    Google Scholar 

  45. Hastie T, Tibshirani R, Friedman J. The elements of statistical learning, data mining, inference, and prediction. 2nd ed. New York: Springer; 2009.

    MATH  Google Scholar 

Download references

Acknowledgements

We thank Rachel Szwimer and Hui Harriet Yan for scientific English editing.

Author information

Authors and Affiliations

  1. Montreal Neurological Institute, McGill University, Montreal, QC, Canada

    Salim Lahmiri, Debra Ann Dawson & Amir Shmuel

  2. Departments of Neurology, McGill University, Montreal, QC, Canada

    Salim Lahmiri, Debra Ann Dawson & Amir Shmuel

  3. Neurosurgery, McGill University, Montreal, QC, Canada

    Salim Lahmiri, Debra Ann Dawson & Amir Shmuel

  4. Physiology, McGill University, Montreal, QC, Canada

    Amir Shmuel

  5. Biomedical Engineering, McGill University, Montreal, QC, Canada

    Amir Shmuel

Authors
  1. Salim Lahmiri
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Debra Ann Dawson
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Amir Shmuel
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Salim Lahmiri or Amir Shmuel.

Ethics declarations

Conflict of interest

Salim Lahmiri, Debra Ann Dawson and Amir Shmuel declare that they have no conflict of interest in relation to the work in this article.

Ethical approval

This article does not contain any studies with human participants or animals performed by any of the authors.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Lahmiri, S., Dawson, D.A. & Shmuel, A. Performance of machine learning methods in diagnosing Parkinson’s disease based on dysphonia measures. Biomed. Eng. Lett. 8, 29–39 (2018). https://doi.org/10.1007/s13534-017-0051-2

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s13534-017-0051-2

Keywords

Search

Navigation