Machine Learning-Driven Remote Monitoring of Parkinson’s Disease Severity Using At-Home Vocal Recordings
DOI:
https://doi.org/10.22399/ijcesen.4491Keywords:
Parkinson's disease, Machine learning, Telemonitoring, Disease severity prediction, Ensemble methodsAbstract
Parkinson’s disease is a progressive neurodegenerative disorder that severely impairs motor function and quality of life, creating a pressing need for objective, continuous monitoring to guide personalized therapy. This study develops a machine learning framework for the remote assessment of Parkinson’s disease severity using multimodal telemonitoring data, primarily from speech with supplementary handwriting and sensor inputs. We systematically benchmark a comprehensive suite of regression models—from linear baselines (Linear, Ridge, Lasso, ElasticNet) to advanced nonlinear ensembles (Random Forest, XGBoost, CatBoost, LightGBM)—on the public Parkinson’s Telemonitoring dataset. Results reveal a decisive performance gap: tree-based ensembles achieved superior predictive accuracy for total UPDRS scores, with R² values up to 0.97 and minimal error (MSE ~2.05), by effectively modeling complex, nonlinear patterns in vocal biomarkers. In stark contrast, linear models and simpler algorithms like AdaBoost significantly underperformed. These findings robustly demonstrate that advanced ensemble ML methods enable highly accurate, scalable, and non-invasive telemonitoring of Parkinson’s disease progression. The proposed approach provides a validated pathway for transforming real-world, continuous data into clinically actionable insights, with strong potential to enhance decision-making, optimize treatment plans, and improve long-term patient outcomes.
References
[1] Poewe, W., Seppi, K., Tanner, C. M., Halliday, G. M., Brundin, P., Volkmann, J., ... & Lang, A. E. (2017). Parkinson disease. Nature Reviews Disease Primers, 3(1), 1-21.
[2] Chaudhuri, K. R., Healy, D. G., & Schapira, A. H. (2006). Non-motor symptoms of Parkinson's disease: diagnosis and management. The Lancet Neurology, 5(3), 235-245.
[3] Schrag, A., Jahanshahi, M., & Quinn, N. (2000). What contributes to quality of life in patients with Parkinson's disease?. Journal of Neurology, Neurosurgery & Psychiatry, 69(3), 308-312.
[4] Espay, A. J., Bonato, P., Nahab, F. B., Maetzler, W., Dean, J. M., Klucken, J., ... & Merola, A. (2016). Technology in Parkinson's disease: challenges and opportunities. Movement Disorders, 31(9), 1272-1282.
[5] Goetz, C. G., Tilley, B. C., Shaftman, S. R., Stebbins, G. T., Fahn, S., Martinez‐Martin, P., ... & Dodel, R. (2007). Movement Disorder Society‐sponsored revision of the Unified Parkinson's Disease Rating Scale (MDS‐UPDRS): Scale presentation and clinimetric testing results. Movement Disorders, 23(15), 2129-2170.
[6] Heldman, D. A., Giuffrida, J. P., Chen, R., Payne, M., Mazzella, F., Duker, A. P., ... & Revilla, F. J. (2011). The modified Bradykinesia Rating Scale for Parkinson's disease: reliability and comparison with kinematic measures. Movement Disorders, 26(10), 1859-1863.
[7] Papapetropoulos, S., Mitsi, G., & Espay, A. J. (2017). Digital health and Parkinson’s disease: a new paradigm for continuous monitoring and management. Journal of Parkinson's Disease, 7(s1), S49-S53.
[8] Arora, S., Baig, F., Lo, C., Barber, T. R., Lawton, M. A., Zhan, A., ... & Foltynie, T. (2019). Smartphone motor testing to distinguish idiopathic REM sleep behavior disorder, controls, and PD. Neurology, 93(16), e1526-e1536.
[9] Tsanas, A., Little, M. A., McSharry, P. E., & Ramig, L. O. (2010). Accurate telemonitoring of Parkinson's disease progression by noninvasive speech tests. IEEE Transactions on Biomedical Engineering, 57(4), 884-893.
[10] Chen, T., & Guestrin, C. (2016, August). XGBoost: A scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 785-794).
[11] Friedman, J. H. (2001). Greedy function approximation: a gradient boosting machine. Annals of Statistics, 1189-1232.
[12] Tsanas, A., Little, M. A., McSharry, P. E., Spielman, J., & Ramig, L. O. (2012). Novel speech signal processing algorithms for high-accuracy classification of Parkinson's disease. IEEE Transactions on Biomedical Engineering, 59(5), 1264-1271.
[13] Adams, J. L., Dinesh, K., Snyder, C. W., Xiong, M., Tarolli, C. G., Sharma, S., ... & Dorsey, E. R. (2020). A real-world study of wearable sensors in Parkinson’s disease. NPJ Parkinson's Disease, 6(1), 1-8.
[14] Motin, M. A., Karmakar, C. K., & Palaniswami, M. (2022). Speech-based estimation of Parkinson's disease severity using hierarchical neural networks. Computer Methods and Programs in Biomedicine, 220, 106810.
[15] Espay AJ, et al. Technology in Parkinson's disease: challenges and opportunities. Mov Disord. 2016.
[16] Hoff JI, et al. Accelerometric assessment of levodopa-induced dyskinesias in Parkinson's disease. Mov Disord. 2001.
[17] Salarian A, et al. Gait assessment in Parkinson's disease: toward an ambulatory system for long-term monitoring. IEEE Trans Biomed Eng. 2004.
[18] El-Gohary M, Pearson S, McNames J, Mancini M, Horak F, Mellone S, Chiari L. Continuous monitoring of turning in patients with movement disability. Sensors (Basel). 2013 Dec 27;14(1):356-69. doi: 10.3390/s140100356. PMID: 24379043; PMCID: PMC3926561.
[19] MA, Maetzler W, Aminian K, Chiari L. Technical and clinical view on ambulatory assessment in Parkinson's disease. Acta Neurol Scand. 2014 Sep;130(3):139-47. doi: 10.1111/ane.12248. Epub 2014 Apr 1. PMID: 24689772.
[20] Galna B, et al. Accuracy of the Microsoft Kinect sensor for measuring movement in people with Parkinson's disease. Gait Posture. 2014.
[21] Kidziński Ł, et al. Deep neural networks enable quantitative movement analysis using single-camera videos. Nat Commun. 2020.
[22] Xu, Zhaoyi et al. “Simultaneous Monitoring of Multiple People’s Vital Sign Leveraging a Single Phased-MIMO Radar.” IEEE Journal of Electromagnetics, RF and Microwaves in Medicine and Biology 6 (2021): 311-320.
[23] C. R. Dhivyaa, K. Nithya and S. Anbukkarasi, "Enhancing Parkinson’s Disease Detection and Diagnosis: A Survey of Integrative Approaches Across Diverse Modalities," in IEEE Access, vol. 12, pp. 158999-159024, 2024, doi: 10.1109/ACCESS.2024.3487001
[24] Rochester L, et al. A roadmap to inform development, validation and approval of digital mobility outcomes: the Mobilise-D approach. Digit Biomark. 2020.
[25] Brabenec L, Mekyska J, Galaz Z, Rektorova I. Speech disorders in Parkinson's disease: early diagnostics and effects of medication and brain stimulation. J Neural Transm (Vienna). 2017 Mar;124(3):303-334. doi: 10.1007/s00702-017-1676-0. Epub 2017 Jan 18. PMID: 28101650.
[26] Drotár P, et al. Evaluation of handwriting kinematics and pressure for differential diagnosis of Parkinson's disease. Artif Intell Med. 2016.
[27] Tsanas A, et al. Accurate telemonitoring of Parkinson's disease progression by non-invasive speech tests. IEEE Trans Biomed Eng. 2010.
[28] Alshammri R, Alharbi G, Alharbi E, Almubark I. Machine learning approaches to identify Parkinson's disease using voice signal features. Front Artif Intell. 2023 Mar 28;6:1084001. doi: 10.3389/frai.2023.1084001. PMID: 37056913; PMCID: PMC10086231.
[29] Hammerla NY, et al. Deep, convolutional, and recurrent models for human activity recognition using wearables. IJCAI. 2016.
[30] Bot BM, et al. The mPower study, Parkinson disease mobile data collected using ResearchKit. Sci Data. 2016.
[31] Lipsmeier F, et al. Evaluation of smartphone-based testing to generate exploratory outcome measures in a phase 1 Parkinson's disease clinical trial. Mov Disord. 2018.
[32] Faheem MSB, Haroon-Ul-Rasheed M, Aftab R, Faheem Q, Feroze F, Ain HQU, Samadi S. The Next Frontier in Parkinson's Disease Treatment: A Narrative Review of Innovative Neurosurgical and Gene Therapy Approaches. Health Sci Rep. 2025 Aug 27;8(9):e71197. doi: 10.1002/hsr2.71197. PMID: 40895248; PMCID: PMC12391019.
[33] Coravos A, et al. Digital Medicine: A Primer on Measurement. Digit Biomark. 2019.
[34] Hall AM, Allgar V, Carroll CB, Meinert E. Digital health technologies and self-efficacy in Parkinson's: a scoping review. BMJ Open. 2025 Jan 21;15(1):e088616. doi: 10.1136/bmjopen-2024-088616. PMID: 39842912; PMCID: PMC11784209.
[35] Dobkin RD, Amondikar N, Kopil C, Caspell-Garcia C, Brown E, Chahine LM, Marras C, Dahodwala N, Mantri S, Standaert DG, Dean M, Shoulson I, Marek K, Katz A, Korell M, Riley L, Tanner CM; Fox Insight Study. Innovative Recruitment Strategies to Increase Diversity of Participation in Parkinson's Disease Research: The Fox Insight Cohort Experience. J Parkinsons Dis. 2020;10(2):665-675. doi: 10.3233/JPD-191901. PMID: 32250321; PMCID: PMC7242847.
[36] L. Breiman, “Random forests,” Machine Learning, vol. 45, no. 1, pp. 5–32, 2001. doi: 10.1023/A:1010933404324
[37] T. Chen and C. Guestrin, “XGBoost: A scalable tree boosting system,” in Proc. 22nd ACM SIGKDD Int. Conf. Knowledge Discovery and Data Mining, 2016, pp. 785–794. doi: 10.1145/2939672.2939785
[38] L. Prokhorenkova, G. Gusev, A. Vorobev, A. V. Dorogush, and A. Gulin, “CatBoost: unbiased boosting with categorical features,” in Advances in Neural Information Processing Systems (NeurIPS), 2018, vol. 31. [Online]. Available: https://github.com/catboost/catboost
[39] G. Ke et al., “LightGBM: A highly efficient gradient boosting decision tree,” in Advances in Neural Information Processing Systems (NeurIPS), 2017, vol. 30. Available: https://github.com/Microsoft/LightGBM
[40] J. R. Quinlan, “Induction of decision trees,” Machine Learning, vol. 1, no. 1, pp. 81–106, 1986. doi: 10.1007/BF00116251
[41] T. G. Dietterich, “Ensemble methods in machine learning,” in Proc. Int. Workshop Multiple Classifier Systems, 2000, pp. 1–15, Springer. doi: 10.1007/3-540-45014-9_1
[42] R. Polikar, “Ensemble based systems in decision making,” IEEE Circuits and Systems Magazine, vol. 6, no. 3, pp. 21–45, 2006. doi: 10.1109/MCAS.2006.1688199
[43] Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner, “Gradient-based learning applied to document recognition,” Proceedings of the IEEE, vol. 86, no. 11, pp. 2278–2324, 2002. doi: 10.1109/5.726791
[44] D. E. Rumelhart, G. E. Hinton, and R. J. Williams, “Learning representations by back-propagating errors,” Nature, vol. 323, no. 6088, pp. 533–536, 1986. doi: 10.1038/323533a0
[45] A.Tsanas, & M.Little, Parkinsons Telemonitoring Dataset. UCI Machine Learning Repository, 2009. doi: 10.24432/C5ZS3N
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 International Journal of Computational and Experimental Science and Engineering
This work is licensed under a Creative Commons Attribution 4.0 International License.
