Machine learning based Parkinson's disease Prediction
DOI:
https://doi.org/10.48001/978-81-966500-2-5-6Keywords:
Parkinson's Disease, Fundamental Frequency Curve, Long-Short Term Memory, Articulation TransitionsAbstract
Early detection of vocal alterations in people with Parkinson's disease (PD) allows for preemptive care before the emergence of more severe physical symptoms. This study examines both static and dynamic aspects of communication that are relevant to identifying PD. A comparison between articulation transition features in PD patients and healthy control (HC) speakers shows differences in articulation transitions and trends in the fundamental frequency curve. We suggest collecting time-series data utilizing an unidirectional long-short-term memory (LSTM) model, with an emphasis on the dynamic features of speech signals to identify Parkinson's disease (PD). The study evaluates speech capabilities by analyzing the strength of transitions from voiced to mute segments (offset) and voiced-to-voiced segments. Two assessment techniques are employed, using 10-fold partitioning of the dataset while ensuring no overlap of data from the same individual in the validation process. We recommend using the bidirectional LSTM framework to capture dynamic elements of speech in this investigation, which may provide new insights into PD detection.
Downloads
References
Alshammri, R., Alharbi, G., Alharbi, E., & Almubark, I. (2023). Machine learning approaches to identify Parkinson’s disease using voice signal features. Frontiers in Artificial Intelligence, 6. https://doi.org/10.3389/frai.2023.1084001
Athanasios Tsanas, Max A. Little, Patrick E. McSharry, Jennifer Spielman, & Lorraine O. Ramig. (2012). Novel speech signal processing algorithms for high-accuracy classification of Parkinsons disease. IEEE Transactions on Biomedical Engineering, 59, 1264–1271. http://www.maxlittle.net/publications/TBME-00887-2011.pdf
Bhattacharya, I., & Bhatia, M. P. (2010). SVM classification to distinguish Parkinson disease patients. Proceedings of the 1st Amrita ACM-W Celebration of Women in Computing in India, A2CWiC’10. https://doi.org/10.1145/1858378.1858392
Das, R. (2010). A comparison of multiple classification methods for diagnosis of Parkinson disease. Expert Systems with Applications, 37(2), 1568–1572. https://doi.org/10.1016/j.eswa.2009.06.040
Goubault, E., Nguyen, H. P., Ayachi, F. S., Bogard, S., & Duval, C. (2017). Do bradykinesia and tremor interfere in voluntary movement of essential tremor patients? Preliminary findings. Tremor and Other Hyperkinetic Movements, 7. https://doi. org/10.7916/D822319X
Nissar, I., Mir, W. A., Izharuddin, & Shaikh, T. A. (2021). Machine Learning Approaches for Detection and Diagnosis of Parkinson’s Disease- A Review. 2021 7th International Conference on Advanced Computing and Communication Systems, ICACCS 2021, 898–905. https://doi.org/10.1109/ICACCS51430.2021.9441885
Office of Communications and Public Liaison. (2023). Parkinson’s Disease: Challenges, Progress, and Promise. National Institute of Neurological Disorders and Stroke. https://www.ninds.nih.gov/current-research/focus-disorders/parkinsons-disease research/parkinsons disease-challenges-progress-and-promise#toc-resources
Ramage, A. E., Greenslade, K. J., Cote, K., Lee, J. N., Fox, C. M., Halpern, A., & Ramig, L. O. (2024). Narrative analysis in individuals with Parkinson’s disease following intensive voice treatment: secondary outcome variables from a randomized controlled trial. Frontiers in Human Neuroscience, 18. https://doi.org/10.3389/fnhum.2024.1394948
Ramani, R. G., & Sivagami, G. (2011). Parkinson Disease classification using data mining algorithms. International Journal of Computer Applications, 32(9), 17–22.
Ramesh, S., & Arachchige, A. S. M. (2023). Depletion of dopamine in Parkinson’s disease and relevant therapeutic options: A review of the literature. AIMS Neuroscience, 10(3), 200–231. https://doi.org/10.3934/NEUROSCIENCE.2023017
