Abstract
Parkinson’s disease is related to nervous system disorders in human beings. In this paper, the status of Parkinson’s disease has been predicted based on the analysis of features of two Parkinson’s disease symptoms: Dysphonia and Dysarthria. The Dysphonia symptom has been measured by analyzing the features extracted from the vocal sounds of a patient. The Dysarthria symptom of Parkinson’s disease has been analyzed by the features extracted from the speech signals of a patient. Hence, two different prediction models have been built for deriving the status of Parkinson’s disease. The derivation of these prediction systems is based on statistical and discriminant feature analysis. The statistical-based feature analysis is carried out using descriptive and inferential analysis. In contrast, the enteric, deviation, and correlation-based information between the features are utilized for descriptive analysis. The inferential analysis has been performed using hypothetical testing of the distribution of features. The descriptive and inferential feature analyses are used to derive effective features for the Parkinson’s disease problem based on the Dysphonia and Dysarthria symptoms. In the discriminant feature analysis, the feature sets undergo deriving discriminant features. The best-selected features are used to build a prediction model for detecting Parkinson’s disease problems in a patient. Extensive experimentation has been carried out using a Dysphonia dataset containing 195 samples. Each sample has 23 features. One dataset for Dysarthria symptoms contains 756 observations, with each observation having 754 features. The best prediction models that have been obtained correspond to these datasets, and 93.50% is obtained for Dysphonia and 87.63% for Dysarthria symptoms databases, respectively. The performance of the proposed system has been compared with some existing methods concerning each employed dataset, showing the superiority of the proposed approach.
![](https://cdn.statically.io/img/media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10742-023-00316-z/MediaObjects/10742_2023_316_Fig1_HTML.png)
![](https://cdn.statically.io/img/media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10742-023-00316-z/MediaObjects/10742_2023_316_Fig2_HTML.png)
![](https://cdn.statically.io/img/media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10742-023-00316-z/MediaObjects/10742_2023_316_Fig3_HTML.png)
![](https://cdn.statically.io/img/media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10742-023-00316-z/MediaObjects/10742_2023_316_Fig4_HTML.png)
![](https://cdn.statically.io/img/media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10742-023-00316-z/MediaObjects/10742_2023_316_Fig5_HTML.png)
![](https://cdn.statically.io/img/media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10742-023-00316-z/MediaObjects/10742_2023_316_Fig6_HTML.png)
![](https://cdn.statically.io/img/media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10742-023-00316-z/MediaObjects/10742_2023_316_Fig7_HTML.png)
![](https://cdn.statically.io/img/media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10742-023-00316-z/MediaObjects/10742_2023_316_Fig8_HTML.png)
![](https://cdn.statically.io/img/media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10742-023-00316-z/MediaObjects/10742_2023_316_Fig9_HTML.png)
![](https://cdn.statically.io/img/media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10742-023-00316-z/MediaObjects/10742_2023_316_Fig10_HTML.png)
![](https://cdn.statically.io/img/media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10742-023-00316-z/MediaObjects/10742_2023_316_Fig11_HTML.png)
![](https://cdn.statically.io/img/media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10742-023-00316-z/MediaObjects/10742_2023_316_Fig12_HTML.png)
Similar content being viewed by others
Data Availibility
In this manuscript, the employed datasets have been taken with license agreements from the corresponding institutions with proper channels.
References
Abdi, H., Williams, L.J.: Principal component analysis. Wiley interdisciplinary reviews: computational statistics 2(4), 433–459 (2010)
Chaokai, H., Ke, C.J., Chungyu, W.: Identification of biomarkers for early diagnosis of Parkinson’s disease by multi-omics joint analysis. Saudi J. Biol. Sci. 27(8), 2082–2088 (2020)
Davis, J., Goadrich, M.: The relationship between precision-recall and roc curves. In Proceedings of the 23rd International Conference on Machine Learning, pp. 233–240, (2006)
Diaz, M., Moetesum, M., Siddiqi, I., Vessio, G.: Sequence-based dynamic handwriting analysis for Parkinsons disease detection with one-dimensional convolutions and bigrus. Expert Syst. Appl. 168, 114405 (2021)
Gottapu, R.D., Dagli, C.H.: Analysis of Parkinsons disease data. Proc. Comput. Sci. 140, 334–341 (2018)
Goyal, J., Khandnor, P., Aseri, T.C.: Classification, prediction, and monitoring of Parkinsons disease using computer assisted technologies: A comparative analysis. Eng. Appl. Artif. Intell. 96, 103955 (2020)
Gunduz, H.: Deep learning-based Parkinson’s disease classification using vocal feature sets. IEEE Access 7, 115540–115551 (2019)
Hossain, S., Umer, S., Asari, V., Rout, R.K.: A unified framework of deep learning-based facial expression recognition system for diversified applications. Appl. Sci. 11(19), 9174 (2021)
Howland, P., Park, H.: Generalizing discriminant analysis using the generalized singular value decomposition. IEEE Trans. Pattern Anal. Mach. Intell. 26(8), 995–1006 (2004)
Inguanzo, A., Roser Sala-Llonch, B., Segura, H.E., Abós, A., Anna Campabadal, C., Uribe, H.C., Baggio, Y.C., Marti, M.J., et al.: Hierarchical cluster analysis of multimodal imaging data identifies brain atrophy and cognitive patterns in Parkinsons disease. Parkinsonism Related Disorders 82, 16–23 (2021)
Jankovic, J.: Parkinsons disease: clinical features and diagnosis. J. Neurol. Neurosurg. Psychiatry 79(4), 368–376 (2008)
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(1), 29–39 (2018)
Landers, M.R., Jacobson, K.M., Matsunami, N.E., McCarl, H.E., Regis, M.T., Longhurst, J.K.: A vicious cycle of fear of falling avoidance behavior in Parkinsons disease: Aa path analysis. Clin. Parkinsonism Related Disorders 4, 100089 (2021)
Little, M., McSharry, P., Hunter, E., Spielman, J., Ramig, L.: Suitability of dysphonia measurements for telemonitoring of Parkinson’s disease. Nat. Prec. 12, 1–1 (2008)
Manfei, X., Fralick, D., Zheng, J.Z., Wang, B., Tu, X.M., Feng, C.: The differences and similarities between two-sample t-test and paired t-test. Shanghai Arch. Psychiatry 29(3), 184 (2017)
McLachlan, Geoffrey J.: Discriminant analysis and statistical pattern recognition. John Wiley & Sons, UK (2004)
Mitzenmacher, M., Upfal, E.: Probability and computing: Randomization and probabilistic techniques in algorithms and data analysis. Cambridge University Press, Cambridge (2017)
Nasar, N., Ray, S., Umer, S., Mohan, Pandey H.: Design and data analytics of electronic human resource management activities through internet of things in an organization. Softw. Practice Exp. 51(12), 2411–2427 (2020)
Okan Sakar, C., Serbes, G., Gunduz, A., Tunc, H.C., Nizam, H., Sakar, B.E., Tutuncu, M., Tarkan Aydin, M., Isenkul, E., Apaydin, H.: 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. 74, 255–263 (2019)
Poewe, W., Klaus, S., Tanner, C., Halliday, G.M., Brundin, P., Volkmann, J., Lang, A.E.: Parkinson disease. Nat. Rev. Dis. Primers 3(1), 1–21 (2017)
Rana, A.Q., Kabir, A., Jesudasan, M., Siddiqui, I., Khondker, S.: Pain in Parkinson’s disease: analysis and literature review. Clin. Neurol. Neurosurg. 115(11), 2313–2317 (2013)
Rosen, K.M., Kent, R.D., Delaney, A.L., Duffy, J.R.: Parametric quantitative acoustic analysis of conversation produced by speakers with dysarthria and healthy speakers. J. Speech Lang. Hear Res. 49(2), 395–411 (2006)
Rout, R.K., Hassan, S.S., Sheikh, S., Umer, S., Sahoo, K.S., Gandomi, A.H.: Feature-extraction and analysis based on spatial distribution of amino acids for SARS-CoV-2 protein sequences. Comput. Biol. Med. 141, 105024 (2022)
Rout, R.K., Hassan, S.S., Sindhwani, S., Pandey, H.M., Umer, S.: Intelligent classification and analysis of essential genes using quantitative methods. ACM Trans. Multimed. Comput. Commun. Appl. (TOMM) 16(1), 1–21 (2020)
Rout, R.K., Umer, S., Sheikh, S., Sindhwani, S., Pati, S.: Eightydvec: a method for protein sequence similarity analysis using physicochemical properties of amino acids. Comput. Methods Biomech. Biomed. Eng: Imag. Visual. 10(1), 3–13 (2022)
Ruggiero, C., Sacile, R., Giacomini, M.: Home telecare. J. Telemed. Telecare 5(1), 11–17 (1999)
Shalev-Shwartz, S., Ben-David, S.: Understanding machine learning: From theory to algorithms. Cambridge University Press, Cambridge (2014)
Solana-Lavalle, G., Rosas-Romero, R.: Analysis of voice as an assisting tool for detection of Parkinson’s disease and its subsequent clinical interpretation. Biomed. Signal Process. Control 66, 102415 (2021)
Tsoulos, I.G., Mitsi, G., Stavrakoudis, A., Papapetropoulos, S.: Application of machine learning in a Parkinson’s disease digital biomarker dataset using neural network construction (nnc) methodology discriminates patient motor status. Front. ICT 6, 10 (2019)
Umapathy, K., Krishnan, S.: Feature analysis of pathological speech signals using local discriminant bases technique. Med. Biol. Eng. Comput. 43(4), 457–464 (2005)
Umer, S., Mohanta, P.P., Rout, R.K., Pandey, H.M.: Machine learning method for cosmetic product recognition: a visual searching approach. Multimed. Tools Appl. 80, 1–27 (2020)
Wilcox, R.R.: Statistics for the social sciences. Academic Press, USA (1996)
Wroge, T.J., Özkanca, Y., Demiroglu, C., Si, D., Atkins, D.C., Ghomi, R.H.: Parkinsons disease diagnosis using machine learning and voice. In 2018 IEEE Signal Processing in Medicine and Biology Symposium (SPMB), IEEE, pp 1–7, (2018)
Yang, S., Zheng, F., Luo, X., Cai, S., Yunfeng, W., Liu, K., Meihong, W., Chen, J., Krishnan, S.: Effective dysphonia detection using feature dimension reduction and kernel density estimation for patients with parkinson’s disease. PLoS ONE 9(2), e88825 (2014)
Zhang, Y., Yang, M., Wang, F., Chen, Y., Liu, R., Zhang, Z., Jiang, Z.: Histogram analysis of quantitative susceptibility mapping for the diagnosis of Parkinson’s disease. Acad. Radiol. 29, S71-9 (2020)
Zou, H., Hastie, T., Tibshirani, R.: Sparse principal component analysis. J. Comput. Graph. Stat. 15(2), 265–286 (2006)
Funding
The authors received no financial support for the research, authorship, and/or publication of this article.
Author information
Authors and Affiliations
Contributions
Original Draft Preparation, Methodology, Investigation SU; Formal Analysis, Conceptualization, Validation, RKR. All authors have read and agreed to the published version of the manuscript.
Corresponding author
Ethics declarations
Conflicts of Interest
The authors declare no conflict of interest.
Ethical approval
This manuscript is not required for the ethics committee or institutional review board approval.
Human and animal rights
This research respects all the sentiments, dignity, and intrinsic values of animals or humans.
Informed consent
Not applicable.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Umer, S., Rout, R.K. Descriptive and inferential analysis of features for Dysphonia and Dysarthria Parkinson’s disease symptoms. Health Serv Outcomes Res Method (2023). https://doi.org/10.1007/s10742-023-00316-z
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s10742-023-00316-z