An Intelligent Machine Learning Framework for Early Parkinsonian Symptom Identification
DOI:
https://doi.org/10.15662/IJEETR.2026.0802091Keywords:
Machine Learning, Parkinson’s Disease, Early Detection, Symptom Identification, Biomedical Signal Processing, Predictive Modeling, Healthcare AnalyticsAbstract
Currently, the ways to screen for Parkinson's Disease mainly involve one type of sensor. However, this is not enough because it affects different people in different ways. Neurodegeneration is not a simple phenomenon; it is complex. Therefore, there is a large gap that needs to be filled. What we are doing here is that we are building a "Multi-Modal Ensemble Framework. “So, it is linking "vocal dysarthria," which is problems with speech, to "kinematic micrography," which is related to the movement of handwriting. The "novelty" is that it combines "high-dimensional acoustic biomarkers." For instance, "Voice Onset Time" and "Vowel Variability Quotient" mix in with "pressure" from "handwriting kinematics
The other studies employ deep learning models, which are complete black boxes. They perform very well in the lab with very high accuracy. However, they don't perform very well in the clinics. Our method is different. Our method is designed to be more generalizable for the clinics. Our method employs a Tri-Algorithm Voting Classifier that employs Extra Trees, Random Forest, and Gradient Boosting Machines. These models work together to come to a conclusion, which is like a consensus
The single-sensor methods, like gyroscopes and accelerometers, are highly influenced by noise. This method does a better job of handling that. Our method has an accuracy of 85.4 percent. It's also interpretable and not a black box. This method compares to the single modality methods, which have an average accuracy of 80 percent. This method has a 5.4 percent improvement over the single modality methods. It kind of proves the point that the combination of the two methods does indeed have a synergy effect, although I'm not sure to what extent
References
1. K. P. Bhatia, P. Bain, N. Bajaj, R. J. Elble, M. Hallett, E. D. Louis, J. Raethjen, M. Stamelou, C. M. Testa, and G. Deuschl, ‘‘Consensus statement on the classification of tremors. From the task force on tremor of the international parkinson and movement disorder society,’’ Movement Disorders, vol. 33, no. 1, pp. 75–87, Jan. 2018, doi: 10.1002/mds. 27121.
2. C. Bhavana, J. Gopal, P. Raghavendra, K. M. Vanitha, and V. Talasila, ‘‘Techniques of measurement for Parkinson’s tremor highlighting advantages of embedded IMU over EMG,’’ in Proc. Int. Conf. Recent Trends Inf. Technol. (ICRTIT), Apr. 2016, pp. 1–5, doi: 10.1109/ICRTIT.2016. 7569560.
3. A. M. Woods, M. Nowostawski, E. A. Franz, and M. Purvis, ‘‘Parkinson’s disease and essential tremor classification on mobile device,’’ Pervas. Mobile Comput., vol. 13, pp. 1–12, Aug. 2014, doi: 10.1016/j.pmcj. 2013.10.002.
4. S. Barrantes, A. J. Sánchez Egea, H. A. González Rojas, M. J. Martí, Y. Compta, F. Valldeoriola, E. S. Mezquita, E. Tolosa, and J. Valls-Solè, ‘‘Differential diagnosis between Parkinson’s disease and essential tremor using the smartphone’s accelerometer,’’ PLoS ONE, vol. 12, no. 8, Aug. 2017, Art. no. e0183843, doi: 10.1371/journal.pone.0183843.
5. P. Locatelli and D. Alimonti, ‘‘Differentiating essential tremor and Parkinson’s disease using a wearable sensor—A pilot study,’’ in Proc. 7th IEEE Int. Workshop Adv. Sensors Interfaces (IWASI), Jun. 2017, pp. 213–218, doi: 10.1109/IWASI.2017.7974254.
6. D. B. Miller and J. P. O’Callaghan, ‘‘Biomarkers of Parkinson’s disease: Present and future,’’ Metabolism, vol. 64, no. 3, pp. S40–S46, Mar. 2015, doi: 10.1016/j.metabol.2014.10.030.
7. S. K. Nanda, W.-Y. Lin, M.-Y. Lee, and R.-S. Chen, ‘‘A quantitative classification of essential and Parkinson’s tremor using wavelet transform and artificial neural network on sEMG and accelerometer signals,’’ inProc. IEEE 12th Int. Conf. Netw., Sens. Control, Apr. 2015, pp. 399–404, doi:
10.1109/ICNSC.2015.7116070.
8. D. Surangsrirat, C. Thanawattano, R. Pongthornseri, S. Dumnin, C. Anan, and R. Bhidayasiri, ‘‘Support vector machine classification of Parkinson’s disease and essential tremor subjects based on temporal fluctuation,’’ in Proc. 38th Annu. Int. Conf. IEEE Eng. Med. Biol. Soc. (EMBC), Aug. 2016, pp. 6389–6392, doi: 10.1109/EMBC.2016.7592190.
9. F. Papengut, J. Raethjen, A. Binder, and G. Deuschl, ‘‘Rest tremor suppression may separate essential from parkinsonian rest tremor,’’ Parkinsonism Rel. Disorders, vol. 19, no. 7, pp. 693–697, Jul. 2013, doi:
10.1016/j.parkreldis.2013.03.013.
10. K. Uchida, M. Hirayama, F. Yamashita, N. Hori, T. Nakamura, and G. Sobue, ‘‘Tremor is attenuated during walking in essential tremor with resting tremor but not parkinsonian tremor,’’ J. Clin. Neurosci., vol. 18, no. 9, pp. 1224–1228, Sep. 2011, doi: 10.1016/j.jocn.2010.12.053.
11. M. Algarni and A. Fasano, ‘‘The overlap between essential tremor and parkinson disease,’’ Parkinsonism Rel. Disorders, vol. 46, pp. S101–S104, Jan. 2018, doi: 10.1016/j.parkreldis.2017.07.006.
12. E. Nikfekr, K. Kerr, S. Attfield, and E. D. Playford, ‘‘Trunk movement in Parkinson’s disease during rising from seated position,’’ Movement Disorders, vol. 17, no. 2, pp. 274–282, Mar. 2002, doi: 10.1002/mds.10073.
13. G. Serrancolí, J. M. Font-Llagunes, and A. Barjau, ‘‘A weighted cost function to deal with the muscle force sharing problem in injured subjects: A single case study,’’ Proc. Inst. Mech. Eng., K, J. Multi-body Dyn., vol. 228, no. 3, pp. 241–251, Sep. 2014, doi: 10.1177/1464419314530110.
14. F. P. Bernhard, J. Sartor, K. Bettecken, M. A. Hobert, C. Arnold,
15. Y. G. Weber, S. Poli, N. G. Margraf, C. Schlenstedt, C. Hansen, and W. Maetzler, ‘‘Wearables for gait and balance assessment in the neurological ward–study design and first results of a prospective cross-sectional feasibility study with 384 inpatients,’’ BMC Neurol., vol. 18, no. 1, p. 114, Dec. 2018, doi: 10.1186/s12883-018-1111-7.
16. D. J. Wile, R. Ranawaya, and Z. H. T. Kiss, ‘‘Smart watch accelerometry for analysis and diagnosis of tremor,’’ J. Neurosci. Methods, vol. 230, pp. 1–4, Jun. 2014, doi: 10.1016/j.jneumeth.2014.04.021.
17. G. Kramer, A. M. M. Van der Stouwe, N. M. Maurits, M. A. J. Tijssen, and J.W.J.Elting,‘‘Waveletcoherenceanalysis:Anewapproachtodistinguish organic and functional tremor types,’’ Clin. Neurophysiol., vol. 129, no. 1, pp. 13–20, Jan. 2018, doi: 10.1016/j.clinph.2017.10.002.
18. C.Nagarajan and M.Madheswaran - ‘Stability Analysis of Series Parallel Resonant Converter with Fuzzy Logic Controller Using State Space Techniques’- Taylor &Francis, Electric Power Components and Systems, Vol.39 (8), pp.780-793, May 2011. DOI: 10.1080/15325008.2010.541746
19. C.Nagarajan and M.Madheswaran - ‘Experimental verification and stability state space analysis of CLL-T Series Parallel Resonant Converter’ - Journal of Electrical Engineering, Vol.63 (6), pp.365-372, Dec.2012. DOI: 10.2478/v10187-012-0054-2
20. C.Nagarajan and M.Madheswaran - ‘Performance Analysis of LCL-T Resonant Converter with Fuzzy/PID Using State Space Analysis’- Springer, Electrical Engineering, Vol.93 (3), pp.167-178, September 2011. DOI 10.1007/s00202-011-0203-9
21. S.Tamilselvi, R.Prakash, C.Nagarajan,“Solar System Integrated Smart Grid Utilizing Hybrid Coot-Genetic Algorithm Optimized ANN Controller” Iranian Journal Of Science And Technology-Transactions Of Electrical Engineering, DOI10.1007/s40998-025-00917-z,2025
22. S.Tamilselvi, R.Prakash, C.Nagarajan,“ Adaptive sliding mode control of multilevel grid-connected inverters using reinforcement learning for enhanced LVRT performance” Electric Power Systems Research 253 (2026) 112428, doi.org/10.1016/j.epsr.2025.112428
23. S.Thirunavukkarasu, C. Nagarajan, 2024, “Performance Investigation on OCF and SCF study in BLDC machine using FTANN Controller," Journal of Electrical Engineering And Technology, Volume 20, pages 2675–2688, (2025), doi.org/10.1007/s42835-024-02126-w
24. C. Nagarajan, M.Madheswaran and D.Ramasubramanian- ‘Development of DSP based Robust Control Method for General Resonant Converter Topologies using Transfer Function Model’- Acta Electrotechnica et Informatica Journal , Vol.13 (2), pp.18-31,April-June.2013, DOI: 10.2478/aeei-2013-0025.
25. C.Nagarajan and M.Madheswaran - ‘DSP Based Fuzzy Controller for Series Parallel Resonant converter’- Springer, Frontiers of Electrical and Electronic Engineering, Vol. 7(4), pp. 438-446, Dec.12. DOI 10.1007/s11460-012-0212-0.
26. C.Nagarajan and M.Madheswaran - ‘Experimental Study and steady state stability analysis of CLL-T Series Parallel Resonant Converter with Fuzzy controller using State Space Analysis’- Iranian Journal of Electrical & Electronic Engineering, Vol.8 (3), pp.259-267, September 2012.
27. C.Nagarajan and M.Madheswaran, “Analysis and Simulation of LCL Series Resonant Full Bridge Converter Using PWM Technique with Load Independent Operation” has been presented in ICTES’08, a IEEE / IET International Conference organized by M.G.R.University, Chennai.Vol.no.1, pp.190-195, Dec.2007
28. Suganthi Mullainathan, Ramesh Natarajan, “An SPSS and CNN modelling based quality assessment using ceramic materials and membrane filtration techniques”, Revista Materia (Rio J.) Vol. 30, 2025, DOI: https://doi.org/10.1590/1517-7076-RMAT-2024-0721
29. M Suganthi, N Ramesh, “Treatment of water using natural zeolite as membrane filter”, Journal of Environmental Protection and Ecology, Volume 23, Issue 2, pp: 520-530,2022
30. M. A. Raza, Q. Chaudry, S. M. T. Zaidi, and M. B. Khan, ‘‘Clinical decision support system for Parkinson’s disease and related movement disorders,’’ in Proc. IEEE Int. Conf. Acoust., Speech Signal Process. (ICASSP), Mar. 2017, pp. 1108–1112, doi: 10.1109/ICASSP.2017.7952328.
31. H. A. González Rojas, P. C. Cuevas, E. E. Zayas Figueras, S. C. Foix, and A. J. Sánchez Egea, ‘‘Time measurement characterization of standto-sit and sit-to-stand transitions by using a smartphone,’’ Med. Biol. Eng. Comput., vol. 56, no. 5, pp. 879–888, May 2018, doi: 10.1007/s11517-0171728-5.
32. J. D. Loaiza Duque, A. M. González-Vargas, A. J. Sánchez Egea, and H. A. González Rojas, ‘‘Using machine learning and accelerometry data for differential diagnosis of parkinson’s disease and essential tremor,’’ in Applied Computer Sciences in Engineering (Communications in Computer and Information Science), vol. 1052. Springer, 2019, pp. 368–378.
33. Sensorlog (Version 1.9.4) Mobile Application Software. Accessed: 2017. [Online]. Available: http://itunes.apple.com
34. S. Padma G, S. Umesh, U. Asokan, and T. Srinivas, ‘‘Parkinsonian hand tremor measurement device based on fiber Bragg grating sensor,’’ in Proc. Int. Conf. Smart Sensors Syst. (IC-SSS), Dec. 2015, pp. 3–5, doi: 10.1109/ SMARTSENS.2015.7873611.
35. F. Hopfner and R. C. Helmich, ‘‘The etiology of essential tremor: Genes versus environment,’’ Parkinsonism Rel. Disorders, vol. 46, pp. S92–S96, Jan. 2018, doi: 10.1016/j.parkreldis.2017.07.014.
36. T. Novak and K. M. Newell, ‘‘Physiological tremor (8–12 Hz component) in isometric force control,’’ Neurosci. Lett., vol. 641, pp. 87–93, Feb. 2017, doi: 10.1016/j.neulet.2017.01.034.
37. E. D. Louis, ‘‘Essential tremor then and now: How views of the most common tremor diathesis have changed over time,’’ Parkinsonism Rel. Disorders, vol. 46, pp. S70–S74, Jan. 2018, doi: 10.1016/j.parkreldis.2017. 07.010.
38. O. Martinez Manzanera, J. W. Elting, J. H. van der Hoeven, and N. M. Maurits, ‘‘Tremor detection using parametric and non-parametric spectral estimation methods: A comparison with clinical assessment,’’ PLoS ONE, vol. 11, no. 6, Jun. 2016, Art. no. e0156822, doi: 10.1371/journal.pone.0156822.
39. Guyon and A. Elisseeff, ‘‘An introduction to variable and feature selection,’’ J. Mach. Learn. Res., vol. 3, pp. 1157–1182, Jan. 2003, doi:10.1162/153244303322753616.
40. N. Kostikis, D. Hristu-Varsakelis, M. Arnaoutoglou, and
C. Kotsavasiloglou, ‘‘A smartphone-based tool for assessing parkinsonian hand tremor,’’ IEEE J. Biomed. Health Informat., vol. 19, no. 6, pp. 1835–1842, Nov. 2015, doi: 10.1109/JBHI.2015.2471093.
41. S. Thaseen and C. A. Kumar, ‘‘Intrusion detection model using fusion of chi-square feature selection and multi class SVM,’’ J. King Saud
42. Univ. Comput. Inf. Sci., vol. 29, no. 4, pp. 462–472, Oct. 2017, doi:
10.1016/j.jksuci.2015.12.004.
43. L. M. Gil, T. P. Nunes, F. H. S. Silva, A. C. D. Faria, and P. L. Melo, ‘‘Analysis of human tremor in patients with parkinson disease using entropy measures of signal complexity,’’ in Proc. Annu. Int. Conf. IEEE Eng. Med. Biol., Aug. 2010, pp. 2786–2789, doi: 10.1109/IEMBS.2010. 5626365.
44. B. Zhang, F. Huang, J. Liu, and D. Zhang, ‘‘A novel posture for better differentiationbetweenParkinson’stremorandessentialtremor,’’Frontiers Neurosci., vol. 12, p. 317, May 2018, doi: 10.3389/fnins.2018.00317.
45. Marjama-Lyons and W. Koller, ‘‘Tremor-predominant parkinson’s disease,’’ Drugs Aging, vol. 16, no. 4, pp. 273–278, Apr. 2000, doi: 10.2165/ 00002512-200016040-00003.
46. A. P. Duker and A. J. Espay, ‘‘Surgical treatment of parkinson disease,’’ Neurologic Clinics, vol. 31, no. 3, pp. 799–808, Aug. 2013, doi: 10.1016/
47. Sugumar, R. (2025). Designing Resilient and Scalable Cloud-Native Frameworks for Generative AI Content Production. International Journal of Research Publications in Engineering, Technology and Management (IJRPETM), 8(6), 13268-13279.
48. Soundappan, S. J. (2020). Big Data Analytics in Healthcare: Applications for Pandemic Forecastin. International Journal of Advanced Research in Computer Science & Technology (IJARCST), 3(1), 2248-2253.
49. Aarthi, K., Thirumoorthy, P., Tamizharasu, K., Manoja, R., Kalyanasundaram, P., & Rajasekar, M. (2025, September). Improved Network lifetime using Cluster based Power-Aware Balanced Routing Protocol for Device to Device Communication. In 2025 6th International Conference on Electronics and Sustainable Communication Systems (ICESC) (pp. 1005-1010). IEEE.
50. Mathew, A. Cybersecurity 5.0: From Firewalls to Fully Autonomous Digital Protection.
51. Rengarajan, A. (2025). Cloud-Based AI-Driven Threat Detection Framework for Smart Grid Cybersecurity. International Journal of Future Innovative Science and Technology (IJFIST), 8(6), 16065.
52. Anbazhagan, K. (2025). Next-Generation Enterprise Cloud AI for Healthcare: Secure CNN Pipelines and Privacy Controls. International Journal of Future Innovative Science and Technology (IJFIST), 8(6), 15980.
