Automatic Parkinson disease detection at early stages as a pre-diagnosis tool by using classifiers and a small set of vocal features

• Autorzy: Solana-Lavalle Gabriel , Galán-Hernández Juan-Carlos , Rosas-Romero Roberto

Identyfikatory

DOI

10.1016/j.bbe.2020.01.003

• Języki publikacji: EN

Abstrakty

EN

Recent research on Parkinson disease (PD) detection has shown that vocal disorders are linked to symptoms in 90% of the PD patients at early stages. Thus, there is an interest in applying vocal features to the computer-assisted diagnosis and remote monitoring of patients with PD at early stages. The contribution of this research is an increase of accuracy and a reduction of the number of selected vocal features in PD detection while using the newest and largest public dataset available. Whereas the number of features in this public dataset is 754, the number of selected features for classification ranges from 8 to 20 after using Wrappers feature subset selection. Four classifiers (k nearest neighbor, multi-layer perceptron, support vector machine and random forest) are applied to vocal-based PD detection. The proposed approach shows an accuracy of 94.7%, sensitivity of 98.4%, specificity of 92.68% and precision of 97.22%. The best resulting accuracy is obtained by using a support vector machine and it is higher than the one, which was reported on the first work to use the same dataset. In addition, the corresponding computational complexity is further reduced by selecting no more than 20 features.

Słowa kluczowe

EN

Parkinson disease; dysphonia features; feature subset selection; support vector machine

PL

choroba Parkinsona; dysfonia; wybór funkcji; maszyna wektorów wsparcia

• Wydawca: Nałęcz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences ; Elsevier
• Czasopismo: Biocybernetics and Biomedical Engineering
• Rocznik: 2020
• Tom: Vol. 40, no. 1
• Strony: 505--516
• Opis fizyczny: Bibliogr. 34 poz., rys., tab., wykr.

Twórcy

autor

Solana-Lavalle Gabriel

• Universidad de las Américas-Puebla, Puebla, Mexico

autor

Galán-Hernández Juan-Carlos

• Universidad de las Américas-Puebla, Puebla, Mexico

autor

Rosas-Romero Roberto

• Universidad de las Américas-Puebla, Puebla, Mexico

Bibliografia

• [1] Michael J. Fox Foundation for Parkinson research, Parkinson's disease causes; 2018, Retrieved from: https://www.michaeljfox.org/understanding-parkinsons/ living-with-pd.html.
• [2] Braga D, Madureira AM, Cuelho L, Ajith R. Automatic detection of Parkinson's disease based on acoustic analysis of speech. Eng Appl Artif Intell 2019;77:148–58. http://dx.doi.org/10.1016/j.engappai.2018.09.018.
• [3] Sakar BE, Isenkul ME, Sakar CO, Sertbas A, Gurgen F, Delil S, et al. Collection and analysis of a parkinson speech dataset with multiple types of sound recordings. IEEE J Biomed Health Inform 2013;19(4):828–34. http://dx.doi.org/10.1109/JBHI.2013.2245674.
• [4] Sakar BE, Serbes G, Sakar CO. Analyzing the effectiveness of vocal features in early telediagnosis of Parkinson's disease. PLOS ONE 2017;1–18. http://dx.doi.org/10.1371/journal.pone.0182428.
• [5] Peker M. A decision support system to improve medical diagnosis using a combination of k-medoids clustering based attribute weighting and SVM. J Med Syst 2016;40 (116):1–16. http://dx.doi.org/10.1007/s10916-016-0477-6.
• [6] Tsanas A, Little MA, McSharry PE, Spielman J, Ramig LO. A decision support system to improve medical diagnosis using a combination of k-medoids clustering based attribute weighting and SVM. IEEE Trans Biomed Eng 2012;59(5):1264–71. http://dx.doi.org/10.1109/TBME.2012.2183367.
• [7] Zhang HH, Yang L, Liu Y, Wang P, Yin J, Li Y, et al. Classification of Parkinson's disease utilizing multi-edit nearest-neighbor and ensemble learning algorithms with speech samples. Biomed Eng Online 2016;15(122). http://dx.doi.org/10.1186/s12938-016-0242-6.
• [8] Berus L, Klancnik S, Brezocnik M, Ficko M. Classifying Parkinson's disease based on acoustic measures using artificial neural networks. Sensors 2019;19(1). http://dx.doi.org/10.3390/s19010016.
• [9] Guruler H. A novel diagnosis system for Parkinson's disease using complex-valued artificial neural network with k-means clustering feature weighting method. Neural Comput Appl 2017;28:1657–66. http://dx.doi.org/10.1007/s00521-015-2142-2.
• [10] Tsanas A, Little MA, McSharry PE, Ramig LO. Nonlinear speech analysis algorithms mapped to a standard metric achieve clinically useful quantification of average Parkinson's disease symptom severity. J R Soc Interface 2011;8(59):842–55. http://dx.doi.org/10.1098/rsif.2010.0456.
• [11] 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). http://dx.doi.org/10.1186/1475-925X-6-23.
• [12] Little MA, McSharry PE, Hunter EJ, Spielman J, Ramig LO. Suitability of dysphonia measurements for telemonitoring of Parkinson's disease. IEEE Trans Biomed Eng 2009;56 (4):1010–22. http://dx.doi.org/10.1109/TBME.2008.2005954.
• [13] Sakar CO, Serbes G, Gunduz A, Tunc HC, Nizam H, Sakar BE, et al. A comparative analysis of speech signal processing algorithms for Parkinson's disease classification and the use of the tunable q-factor wavelet transform. Appl Soft Comput 2019;74:255–63. http://dx.doi.org/10.1016/j.asoc.2018.10.022.
• [14] Tsanas A, Little MA, McSharry PE, Ramig LO. Accurate telemonitoring of Parkinson's disease progression by noninvasive speech tests. IEEE Trans Biomed Eng 2010;57 (4):884–93. http://dx.doi.org/10.1109/TBME.2009.2036000.
• [15] Selesnick IW. Wavelet transform with tunable q-factor. IEEE Trans Signal 2011;59(8):3560–75. http://dx.doi.org/10.1109/TSP.2011.2143711.
• [16] Selesnick IW. Resonance-based signal decomposition: a new sparsity-enabled signal analysis method. Signal Process 2011;91(12):2793–809. http://dx.doi.org/10.1016/j.sigpro.2010.10.018.
• [17] Peker M, Sen B, Delen D. Computer-aided diagnosis of Parkinson's disease using complex-valued neural networks and MRMR feature selection algorithm. J Healthc Eng 2015;6 (3):281–302. http://dx.doi.org/10.1260/2040-2295.6.3.281.
• [18] Kohavi R, John GH. Wrappers for feature subset selection. Artif Intell 1997;97:273–324.
• [19] Braak H, Ghebremedhin E, Rüb U, Bratzke H, Del Tredici K. Stages in the development of Parkinson's disease-related pathology. Cell Tissue Res 2004;(318):121–34. http://dx.doi.org/10.1007/s00441-004-0956-9.
• [20] Banga YI, Minc K, Sohnd YH, Choa SR. Acoustic characteristics of vowel sounds in patients with parkinson disease. Neuro Rehabil 2013;32:649–54. http://dx.doi.org/10.3233/NRE-130887.
• [21] Boersma P. Praat: doing phonetics by computer, ear hear; 2011, http://www.fon.hum.uva.nl/praat/.
• [22] Peng H, Long F, Ding C. Feature selection based on mutual information: criteria of max-dependency, max-relevance, and min-redundancy. IEEE Trans Pattern Anal Mach Intell 2005;8(27):1226–38. http://dx.doi.org/10.1109/TPAMI.2005.159.
• [23] Jafari GR, Pedram P, Ghafoori Tabrizi K. Detrended fluctuation analysis of Bach's inventions and sinfonias pitches. AIP Conf Proc 2007;889(1). http://dx.doi.org/10.1063/1.2713472.
• [24] Peng CK, Buldyrev SV, Havlin S, Simons M, Stanley HE, Goldberger AL. Mosaic organization of DNA nucleotides. Phys Rev E 1994;49(2).
• [25] Muda L, Begam M, Elamvazuthi I. Voice recognition algorithms using Mel frequency cepstral coefficient (MFCC) and dynamic time warping (DTW) techniques. J Comput 2010;2(3):674–93.
• [26] Sigurdsson S, Petersen KB, Lehn-Schiøler T. Mel frequency cepstral coefficients: an evaluation of robustness of MP3 encoded music. ISMIR 2006.
• [27] Picone J. Signal modeling techniques in speech recognition. Proc IEEE 1993;81(9):1215–47.
• [28] Mallat S. A theory for multiresolution signal decomposition: the wavelet representation. IEEE Trans Pattern Anal Mach Intell 1989;11(7):674–93.
• [29] Upadhya SS, Sheeran AN. Discriminating Parkinson and healthy people using phonation and cepstral features of speech. Proc Comput Sci 2018;143:197–202. http://dx.doi.org/10.1016/j.procs.2018.10.376.
• [30] Proença J, Perdigão F, Veira A, Candeias S, Lemos J, Januário C. Characterizing Parkinson's disease speech by acoustic and phonetic features. Lect Notes Comput Sci 2014;8775: 24–35.
• [31] Bache K, Lichman M. UCI machine learning repository; 2013, Available at http://archive.ics.uci.edu/ml.
• [32] UCI. UCI Machine Learning Repository: Parkinson speech dataset with multiple types of sound recordings data set; 2014, Available at: https://archive.ics.uci.edu/ml/machine-learning- databases/00470/.
• [33] Tsanas A, Little MA, McSharry PE, Spielman J, Ramig LO. Novel speech signal processing algorithms for high-accuracy classification of Parkinson's disease. IEEE Trans Biomed Eng 2012;59(5):1264–71. http://dx.doi.org/10.1109/TBME.2012.2183367.
• [34] Grover S, Bhartia S, Akshama, Yadav A, Seeja KR. Predicting severity of Parkinson's disease using deep learning. Proc Comput Sci 2018;132:1788–94. http://dx.doi.org/10.1016/j.procs.2018.05.154.

Uwagi

PL

Opracowanie rekordu ze środków MNiSW, umowa Nr 461252 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2020).