Deep learning vs. conventional methods for parkinson's disease diagnosis: a systematic review
DOI:
https://doi.org/10.56294/sctconf20251353Keywords:
Movement disorder, Transfer learning, End-to-end learning, Genetic information, Gait patterns, Class imbalance, Disease progression trackingAbstract
A neurological condition called Parkinson's disease (PD) primarily affects movement, but it can also have an impact on speaking, thinking, and a host of other bodily processes. Machine learning models can be trained by systems to examine clinical data, genetic information, speech patterns, and even speech patterns in order to identify early indicators of Parkinson's disease before symptoms manifest. One of the main issues with machine learning models is their inability to handle inconsistent, noisy, or missing input, which can have a negative effect on the model's performance. By building a system that supports both transfer learning techniques and multi-modal fusion, these shortcomings can be addressed. In order to determine the model's efficacy, this study examines many deep learning techniques based on speech, image, and handwritten patterns. In order to improve diagnosis accuracy, deep learning techniques can look at complex data patterns from a range of sources, such as speech, signals, images of medical conditions, and walking patterns. By using convolutional neural networks, recurrent neural networks, and transfer learning, deep learning models are able to identify Parkinson's disease early on, monitor its progression, and offer personalized treatment. Traditional Parkinson's disease diagnosis techniques rely on manually defined features extracted from a range of data sources, such as speech, gait, and medical images. These characteristics are subsequently incorporated into machine learning models. To automatically detect and extract aspects of Parkinson's disease, deep learning approaches make use of transfer learning and end-to-end learning.
References
[1] Gunduz, Hakan. "Deep learning-based Parkinson’s disease classification using vocal feature sets." Ieee access 7 (2019): 115540-115551. DOI: https://doi.org/10.1109/ACCESS.2019.2936564
[2] Caliskan, Abdullah, et al. "Diagnosis of the Parkinson disease by using deep neural network classifier." IU-Journal of Electrical & Electronics Engineering 17.2 (2017): 3311-3318.
[3] Sivaranjini, S., Sujatha, C.M. Deep learning based diagnosis of Parkinson’s disease using convolutional neural network. Multimed Tools Appl 79, 15467–15479 (2020). https://doi.org/10.1007/s11042-019-7469-8 DOI: https://doi.org/10.1007/s11042-019-7469-8
[4] Senturk, Zehra Karapinar. "Early diagnosis of Parkinson’s disease using machine learning algorithms." Medical hypotheses 138 (2020): 109603. DOI: https://doi.org/10.1016/j.mehy.2020.109603
[5] M. Wodzinski, A. Skalski, D. Hemmerling, J. R. Orozco-Arroyave and E. Nöth, "Deep Learning Approach to Parkinson’s Disease Detection Using Voice Recordings and Convolutional Neural Network Dedicated to Image Classification," 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Berlin, Germany, 2019, pp. 717-720, doi: 10.1109/EMBC.2019.8856972. DOI: https://doi.org/10.1109/EMBC.2019.8856972
[6] J. C. Vásquez-Correa, T. Arias-Vergara, J. R. Orozco-Arroyave, B. Eskofier, J. Klucken and E. Nöth, "Multimodal Assessment of Parkinson's Disease: A Deep Learning Approach," in IEEE Journal of Biomedical and Health Informatics, vol. 23, no. 4, pp. 1618-1630, July 2019, doi: 10.1109/JBHI.2018.2866873. DOI: https://doi.org/10.1109/JBHI.2018.2866873
[7] Sahu, L., Sharma, R., Sahu, I., Das, M., Sahu, B., & Kumar, R. (2022). Efficient detection of Parkinson's disease using deep learning techniques over medical data. Expert Systems, 39(3), e12787. https://doi.org/10.1111/exsy.12787 DOI: https://doi.org/10.1111/exsy.12787
[8] Oh, S.L., Hagiwara, Y., Raghavendra, U. et al. A deep learning approach for Parkinson’s disease diagnosis from EEG signals. Neural Comput & Applic 32, 10927–10933 (2020). https://doi.org/10.1007/s00521-018-3689-5 DOI: https://doi.org/10.1007/s00521-018-3689-5
[9] Taleb, C., Likforman-Sulem, L., Mokbel, C. et al. Detection of Parkinson’s disease from handwriting using deep learning: a comparative study. Evol. Intel. 16, 1813–1824 (2023). DOI: https://doi.org/10.1007/s12065-020-00470-0
[10] Aşuroğlu, T., Oğul, H. A deep learning approach for parkinson’s disease severity assessment. Health Technol. 12, 943–953 (2022) DOI: https://doi.org/10.1007/s12553-022-00698-z
[11] Yadav, S., Singh, M.K. & Pal, S. Artificial Intelligence Model for Parkinson Disease Detection Using Machine Learning Algorithms. Biomedical Materials & Devices 1, 899–911 (2023). https://doi.org/10.1007/s44174-023-00068-x DOI: https://doi.org/10.1007/s44174-023-00068-x
[12] Agrawal, S., Sahu, S.P. Image-based Parkinson disease detection using deep transfer learning and optimization algorithm. Int. j. inf. tecnol. 16, 871–879 (2024). https://doi.org/10.1007/s41870-023-01601-3 DOI: https://doi.org/10.1007/s41870-023-01601-3
[13] Islam, Md. A., Hasan Majumder, Md. Z., Hussein, Md. A., Hossain, K. M., & Miah, Md. S. (2024). A review of machine learning and deep learning algorithms for Parkinson’s disease detection using handwriting and voice datasets. In Heliyon (Vol. 10, Issue 3, p. e25469). Elsevier BV. https://doi.org/10.1016/j.heliyon.2024.e25469 DOI: https://doi.org/10.1016/j.heliyon.2024.e25469
[14] Erdaş ÇB, Sümer E. 2023. A fully automated approach involving neuroimaging and deep learning for Parkinson’s disease detection and severity prediction. PeerJ Computer Science 9:e1485 https://doi.org/10.7717/peerj-cs.1485 DOI: https://doi.org/10.7717/peerj-cs.1485
[15] Khaskhoussy, R., & Ayed, Y. B. (2023). Improving Parkinson’s disease recognition through voice analysis using deep learning. In Pattern Recognition Letters (Vol. 168, pp. 64–70). Elsevier BV. https://doi.org/10.1016/j.patrec.2023.03.011 DOI: https://doi.org/10.1016/j.patrec.2023.03.011
[16] Nilashi, M., Abumalloh, R. A., Yusuf, S. Y. M., Thi, H. H., Alsulami, M., Abosaq, H., Alyami, S., & Alghamdi, A. (2023). Early diagnosis of Parkinson’s disease: A combined method using deep learning and neuro-fuzzy techniques. In Computational Biology and Chemistry (Vol. 102, p. 107788). Elsevier BV. https://doi.org/10.1016/j.compbiolchem.2022.107788 DOI: https://doi.org/10.1016/j.compbiolchem.2022.107788
[17] Md Abu Sayed, Duc Minh Cao, Islam, M. T., Tayaba, M., Md Eyasin Ul Islam Pavel, Md Tuhin Mia, Eftekhar Hossain Ayon, Nur Nobe, Bishnu Padh Ghosh, & Sarkar, M. (2023). Parkinson’s Disease Detection through Vocal Biomarkers and Advanced Machine Learning Algorithms. Journal of Computer Science and Technology Studies, 5(4), 142–149. https://doi.org/10.32996/jcsts.2023.5.4.14 DOI: https://doi.org/10.32996/jcsts.2023.5.4.14
[18] Balnarsaiah, B., Nayak, B. A., Sujeetha, G. S., Babu, B. S., & Vallabhaneni, R. B. (2023). RETRACTED ARTICLE: Parkinson’s disease detection using modified ResNeXt deep learning model from brain MRI images. In Soft Computing (Vol. 27, Issue 16, pp. 11905–11914). Springer Science and Business Media LLC. https://doi.org/10.1007/s00500-023-08535-9 DOI: https://doi.org/10.1007/s00500-023-08535-9
[19] Saleh, S., Cherradi, B., El Gannour, O. et al. Predicting patients with Parkinson's disease using Machine Learning and ensemble voting technique. Multimed Tools Appl 83, 33207–33234 (2024). https://doi.org/10.1007/s11042-023-16881-x DOI: https://doi.org/10.1007/s11042-023-16881-x
[20] Rahman, S., Hasan, M., Sarkar, A.K. and Khan, F. 2023. Classification of Parkinson’s Disease using Speech Signal with Machine Learning and Deep Learning Approaches. European Journal of Electrical Engineering and Computer Science. 7, 2 (Mar. 2023), 20–27. DOI:https://doi.org/10.24018/ejece.2023.7.2.488. DOI: https://doi.org/10.24018/ejece.2023.7.2.488
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Sowjanya Vuddanti, A.Srinagesh (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
The article is distributed under the Creative Commons Attribution 4.0 License. Unless otherwise stated, associated published material is distributed under the same licence.
