Abstract
Parkinson's Disease (PD) is a progressive neurodegenerative disorder that impacts motor skills, including tremors, bradykinesia, and rigidity, affecting millions globally. Early diagnosis is essential for effective treatment yet remains challenging as the symptoms overlap with other conditions and the limitations of conventional diagnostic methods. This study presents a diagnostic tool utilizing machine learning that employs a Support Vector Machine (SVM) classifier for precise PD prediction through biomedical voice data. The system uses the UCI Parkinson’s dataset, where pre-processing tasks like feature standardization, train-test split (80-20 ratio), and Recursive Feature Elimination (RFE)enhance model accuracy by identifying significant features. An easy-to-use Streamlit web application was developed to enable real-time predictions, permitting users to input voice parameters and receive instant diagnostic results. The SVM classifier achieved a precision rate of 92%, showcasing its capability and effectiveness in distinguishing PD from non-affected cases. By providing a scalable, cost-effective, and non-invasive approach, this tool bridges advanced computational techniques with real-world healthcare needs. Future enhancements will focus on integrating multimodal data, such as neuroimaging and wearable sensor data, as well as employing deep learning models to improve diagnostic accuracy and expand clinical applicability.
References
Mohammed Al-Sarem, F., Saeed, F., Al-Mohaimeed, M., & Ghabban, D. (2022). Enhancing Parkinson's Disease Prediction Using Machine Learning and Feature Selection Methods. Computers, Materials & Continua, 71(3), 5639–5658.
R. Das, (2010) “A Comparison of multiple classification methods for diagnosis of Parkinson disease.” Expert Systems with Applications, vol. 37, no. 2, pp. 1568-1572.
Tsanas, M. A. Little, P. E. McSharry, and L. O. Ramig, (2010) “Accurate telemonitoring of Parkinson's disease progression by noninvasive speech tests.” Biomedical Engineering, IEEE Transactions, vol. 57, no. 4, pp. 884-893.
S. Amit, M. Ashutosh, A. Bhattacharya and F. Revilla, (2014) "Understanding Postural Response of Parkinson's Subjects Using Nonlinear Dynamics and Support Vector Machines", Austin J. Biomed Eng., vol. 1, no. 1, pp. id1005.
D. T. Dexter and P. Jenner, (2013)"Parkinson disease: from pathology to molecular disease mechanisms", Free Radical Biology and Medicine, vol. 62, pp. 132-144.
Liaqat Ali, Ashir Javeed, Adeeb Noor, Hafiz Tayyab Rauf, Seifedine Kadry, Amir H. Gandomi,(2024) "Parkinson’s disease detection based on features refinement through L1 regularized SVM and deep neural network", Scientific Reports, vol.14, no.1, 2024.
Arti Rana, Ankur Dumka, Rajesh Singh, Mamoon Rashid, Nazir Ahmad, Manoj Kumar Panda,(2022) "An Efficient Machine Learning Approach for Diagnosing Parkinson’s Disease by Utilizing Voice Features", Electronics, vol.11, no.22, 3782.
Ajay Sankar Gullapalli, Vinay Kumar Mittal, (2022)"Early Detection of Parkinson’s Disease Through Speech Features and Machine Learning: A Review", ICT with Intelligent Applications, vol.248, 203.
Yongming Li, Xinyue Zhang, Pin Wang, Xiaoheng Zhang, Yuchuan Liu, (2021) "Insight into an unsupervised two-step sparse transfer learning algorithm for speech diagnosis of Parkinson’s disease", Neural Computing and Applications, vol.33, no.15, 9733.
Liaqat Ali, Chinmay Chakraborty, Zhiquan He, Wenming Cao, Yakubu Imrana, Joel J. P. C. Rodrigues,(2022) "A novel sample and feature dependent ensemble approach for Parkinson?s disease detection", Neural Computing and Applications, 2022.
Cnockaert, Laurence, Jean Schoentgen, Pascal Auzou, Canan Ozsancak, L. Defebvre, and Francis Grenez. "Low-frequency vocal modulations in vowels produced by Parkinsonian subjects." Speech communication 50, no. 4 (2008): 288-300.
Giovanni Rizzo, Massimiliano Copetti, Simona Arcuti, Davide Martino, Andrea Fontana and Giancarlo Logroscino,(2016) "Accuracy of clinical diagnosis of parkinson disease: a systematic review and meta-analysis", Neurology, vol. 86, no. 6, pp. 566-576.
Giovanni Paragliola and Antonio Coronato, (2018) "Gait anomaly detection of subjects with parkinson’s disease using a deep time series-based approach", IEEE Access, vol. 6, 73280-73292.
Cosmin Stamate, George D Magoulas, Stefan Küppers, Effrosyni Nomikou, Ioannis Daskalopoulos, Marco U Luchini, et al., (2017) "Deep learning parkinson’s from smartphone data", 2017 IEEE International Conference on Pervasive Computing and Communications.,Kona, HI, USA 31-40.
Tabashum, T., Snyder, R. C., O'Brien, M. K., & Albert, M. V. (2024). Machine Learning Models for Parkinson Disease: Systematic Review. Journal of Medical Internet Research, 12.