Abstract
A progressive neurodegenerative ailment called Parkinson's disease (PD) is marked by the death of dopamine-producing cells in the substantia nigra area of the brain. The exact etiology of PD remains elusive, but it is believed to involve the presence of Lewy bodies, abnormal protein aggregates, in affected brain regions, leading to the mobile symptoms of PD. Hence, as the management of PD continues to evolve, there is a growing demand for the establishment of a descriptive system that enables the early detection of PD. In this study, we conducted an extensive analysis using machine learning, ensemble learning, and deep learning models with different hyperparameters to develop accurate classification models for PD prediction. To enhance classifier performance and address overfitting, we employed principal component analysis (PCA) for feature selection along with various preprocessing techniques. The dataset used consisted of voice samples, comprising 188 PD patients and 64 normal individuals. Our results demonstrated that the Random Forest (RF) model with accuracy of 82.37% outperformed the other base classifiers Among the ensemble classifiers, the LGBM model exhibited the highest accuracy of 85.90% when compared to both base and ensemble classifiers. Notably, the deep learning model has 91.33% training accuracy and 85.02% testing accuracy, suggesting that deep learning models perform comparably equivalent on small datasets compared to machine learning classifiers. Overall, our findings underscore the effectiveness of machine learning, ensemble techniques and deep learning models in accurately predicting PD.
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs42979-023-02368-x/MediaObjects/42979_2023_2368_Fig1_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs42979-023-02368-x/MediaObjects/42979_2023_2368_Fig2_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs42979-023-02368-x/MediaObjects/42979_2023_2368_Fig3_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs42979-023-02368-x/MediaObjects/42979_2023_2368_Fig4_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs42979-023-02368-x/MediaObjects/42979_2023_2368_Fig5_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs42979-023-02368-x/MediaObjects/42979_2023_2368_Fig6_HTML.png)
Similar content being viewed by others
Data availability
The data used to support the findings of the study is made available from UCI Repository at https://archive.ics.uci.edu/ml/datasets/Parkinson%27s+Disease+Classification#.
References
Aarsland D, Batzu L, Halliday GM, et al. Parkinson disease-associated cognitive impairment. Nat Rev Dis Primers. 2021;7(1):1–21.
Kochanek KD, Xu J, Murphy SL, et al. Deaths: preliminary data for 2009. Natl Vital Stat Rep. 2011;59(4):1–51.
Rojas-Valenzuela I, Valenzuela O, Delgado-Marquez E, et al. Multi-class classifier in Parkinson’s disease using an evolutionary multi-objective optimization algorithm. Appl Sci. 2022;12(6):3048.
Fox SH, Katzenschlager R, Lim SY, et al. The movement disorder society evidence-based medicine review update: treatments for the motor symptoms of Parkinson’s disease. Mov Disord. 2011;26(S3):S2–41.
Chaudhuri KR, Schapira AH. Non-motor symptoms of Parkinson’s disease: dopaminergic pathophysiology and treatment. The Lancet Neurology. 2009;8(5):464–74.
Kalia LV, Lang AE. Parkinson’s disease. Lancet. 2015;386(9996):896–912.
Guerreiro R, Ross OA, Kun-Rodrigues C, et al. Investigating the genetic architecture of Parkinson’s disease in ethnic Chinese. J Neurol Neurosurg Psychiatry. 2018;89(5):553–8.
Wirdefeldt K, Adami HO, Cole P, et al. Epidemiology and etiology of Parkinson’s disease: a review of the evidence. Eur J Epidemiol. 2011;26:S1-58.
Jankovic J. Parkinson’s disease: clinical features and diagnosis. J Neurol Neurosurg Psychiatry. 2008;79(4):368–76.
Brooks DJ. Imaging approaches to Parkinson disease. J Nucl Med. 2010;51(4):596–609.
Pereira CR, Pereira DR, Papa JP, et al. Convolutional neural networks applied for parkinson’s disease identification. In: Holzinger A, editor. Machine learning for health informatics, vol. 9605. Lecture notes in computer science. Springer, Cham; 2016. p. 377–90.
Xu J, Zhang M. Use of magnetic resonance imaging and artificial intelligence in studies of diagnosis of Parkinson’s disease. ACS Chem Neurosci. 2019;10(6):2658–67.
Kaur S, Aggarwal H, Rani R. Diagnosis of Parkinson’s disease using deep CNN with transfer learning and data augmentation. Multimedia Tools Appl. 2021;80(7):10113–39.
Ricciardi L, Visco-Comandini F, Erro R, et al. Facial emotion recognition and expression in Parkinson’s disease: an emotional mirror mechanism? PLoS ONE. 2017;12(1): e0169110.
Kaur S, Aggarwal H, Rani R. Hyper-parameter optimization of deep learning model for prediction of Parkinson’s disease. Mach Vis Appl. 2020;31(5):1–15.
Rovini E, Maremmani C, Cavallo F. How wearable sensors can support Parkinson’s disease diagnosis and treatment: a systematic review. Front Neurosci. 2017;11:555.
Gomez-Rodellar A, Alvarez-Marquina A, Mekyska J, et al. Performance of Articulation Kinetic Distributions Vs MFCCs in Parkinson’s Detection from Vowel Utterances. Singapore: In Neural Approaches to Dynamics of Signal Exchanges Springer; 2020. p. 431–41.
Fleyeh H, Westin J Extracting Body Landmarks from Videos for Parkinson Gait Analysis, In: 2019 IEEE 32nd International Symposium on Computer-Based Medical Systems (CBMS), IEEE, pp. 379–384, 2019.
Vasquez-Correa JC, Arias-Vergara T, et al. Multimodal assessment of Parkinson’s disease: a deep learning approach. IEEE J Biomed Health Inform. 2018;23(4):1618–30.
Joshi A, Ghosh S, Gunnery S et al. Context-Sensitive Prediction of Facial Expressivity using Multimodal Hierarchical Bayesian Neural Networks, In: 2018 13th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2018), IEEE, pp. 278–285, 2018.
Sonawane B, Sharma P. Review of automated emotion-based quantification of facial expression in Parkinson’s patients. Vis Comput. 2021;37(5):1151–67.
Bowers D, Miller K, Bosch W, et al. Faces of emotion in Parkinson’s disease: micro-expressivity and bradykinesia during voluntary facial expressions. J Int Neuropsychol Soc. 2006;12(6):765–73.
Wu P, Gonzalez I, Patsis G, et al. Objectifying facial expressivity assessment of parkinson’s patients: preliminary study. Comput Math Methods Med. 2014;2014:427826.
Vinokurov N, Arkadir D, Linetsky E, et al. Quantifying hypomimia in parkinson patients using a depth camera. Cham: In International Symposium on Pervasive Computing Paradigms for Mental Health Springer; 2015. p. 63–71.
Agrawal A, Mittal N. Using CNN for facial expression recognition: a study of the effects of kernel size and number of filters on accuracy. Vis Comput. 2020;36(2):405–12.
Gan Y, Chen J, Xu L. Facial expression recognition boosted by soft label with a diverse ensemble. Pattern Recogn Lett. 2019;125:105–12.
Tsipouras MG, et al. A deep learning approach for Parkinson’s disease detection based on vocal parameters. Neural Comput Appl. 2018;29(10):743–53.
Gupta R, et al. Deep learning-based early detection of Parkinson’s disease using gait analysis. J Med Syst. 2019;43(12):348.
Hirschauer TJ, et al. Deep learning for individualized Parkinson’s disease diagnosis using handwritten digit tasks. Front Neurol. 2019;10:777.
Barukab O, et al. Analysis of Parkinson’s disease using an imbalanced-speech dataset by employing decision tree ensemble methods. Diagnostics. 2022;12(12):3000.
Sharma S, Guleria K. A systematic literature review on deep learning approaches for pneumonia detection using chest X-ray images. Multimed Tools Appl. 2023;1–51.
Sharma S, Guleria K. A Deep Learning based model for the Detection of Pneumonia from Chest X-Ray Images using VGG-16 and Neural Networks. Proc Comput Sci. 2023;218:357–66.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors have no conflicting interests.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
This article is part of the topical collection “Diverse Applications in Computing, Analytics and Networks” guest edited by Archana Mantri and Sagar Juneja.
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
Goyal, P., Rani, R. Comparative Analysis of Machine Learning, Ensemble Learning and Deep Learning Classifiers for Parkinson’s Disease Detection. SN COMPUT. SCI. 5, 66 (2024). https://doi.org/10.1007/s42979-023-02368-x
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s42979-023-02368-x