Modares Mechanical Engineering

Modares Mechanical Engineering

Parkinson's Diagnosis Based on Gait Patterns Using Artificial Intelligence

Authors
Farzin Zeinaddini Meymand
Mahkame Sharbatdar
Mechanical Engineering Department, K. N. Toosi University of Technology
10.48311/mme.2025.24037
Abstract
Parkinson’s disease is recognized as a progressive neurological disorder that leads to motor impairments. Due to the necessity of early and accurate diagnosis for effective disease management, a novel approach has been proposed for detecting and predicting the progression stages of Parkinson’s disease. In this study, gait signals were processed using Empirical Mode Decomposition (EMD), and temporal features were extracted by employing a hybrid CNN-LSTM deep neural network architecture. The gait data were collected using sixteen force sensors placed beneath the left and right feet of 93 individuals with Parkinson’s disease and 73 healthy controls. The signals were then preprocessed, and their intrinsic frequency components were extracted.

To evaluate model performance, two training strategies were applied: a conventional train-test split, and K-Fold cross-validation. Temporal dynamics associated with disease progression were effectively extracted through the CNN-LSTM model.

According to the results, the cross-validation-based model demonstrated superior accuracy of 96.44%, compared to 84.27% achieved by the simple split approach. These findings indicate that the proposed method can be reliably utilized as an intelligent, non-invasive clinical decision-support tool for the diagnosis and staging of Parkinson’s disease
Keywords
Parkinson
Gait Signal
Neural Network
Disease Diagnosis

Subjects

1 - W. Poewe, K. Seppi, C. M. Tanner, G. M. Halliday, P. Brundin, J. Volkmann, A. Eleonore Schrag and A. E. Lang, "Parkinson disease," Nature Reviews Disease Primers, vol. 3, no. 1, pp. 1-21, 2017.
doi: 10.1038/nrdp.2017.13
2 - Y. Wu and S. Krishnan, "Statistical Analysis of Gait Rhythm in Patients With Parkinson's Disease," IEEE Xplore, vol. 18, no. 2, pp. 150-158, 2010. doi: 10.1109/TNSRE.2009.2033062
3 - W. Ferdous, K. B. Rezaul, J. H. Chris, S. Halgamuge and C. A. David, "Classification of Parkinson's Disease Gait Using Spatial-Temporal Gait Features," IEEE Xplore, vol. 23, no. 6, pp. 973-982, 2015. doi: 10.1109/TNSRE.2015.2404812
4 - I. E. Maachi, G.-A. B. and W. B. , "Deep 1D-Convnet for accurate Parkinson disease detection and severity prediction from gait," ELSEVIER, vol. 143, p. 113075, 2020.
doi: 10.1016/j.eswa.2019.113075
5 - P. P. A. K. H. A. and N. P. , "Classification of gait signals into different neurodegenerative diseases using statistical analysis and recurrence quantification analysis," ELSEVIER, vol. 117, pp. 1-7, 2018.
doi: 10.1016/j.patrec.2018.04.005
6 - N. Khoury, F. Attal, Y. Amirat, L. Oukhellou and S. Mohammed, "Data-Driven Based Approach to Aid Parkinson’s," Sensors, vol. 19, no. 2, p. 242, 2019. doi: 10.3390/s19020242
7 - B. E. B. D and B. R. , "Supervised machine learning based gait classification system for early detection and stage classification of Parkinson’s disease," ELSEVIER, vol. 49, p. 106494, 2020.
doi: 10.1016/j.asoc.2020.106494
8 - A. B. Oktay and A. Kocer, "Differential diagnosis of Parkinson and essential tremor with convolutional LSTM networks," ELSEVIER, vol. 56, p. 6, 2020. doi: 10.1016/j.bspc.2019.101683
9 - B. Vidya and S. P. , "Parkinson’s disease diagnosis and stage prediction based on gait signal analysis using EMD and CNN–LSTM network," ELSEVIER, vol. 114, p. 16, 2022.
doi: 10.1016/j.engappai.2022.105099
10 - G. Yogev, N. Giladi, C. Peretz, S. Springer, E. S. Simon and J. M. Hausdorff, "Dual tasking, gait rhythmicity, and Parkinson’s disease:," European Journal of Neuroscience, vol. 22, no. 5, pp. 1248-1256, 2005. doi: 10.1111/j.1460-9568.2005.04298.x
11- J. M. Hausdorff, J. Lowenthal, T. Herman, L. Gruendlinger, C. Peretz and N. Giladi, "Rhythmic auditory stimulation modulates gait variability," European Journal of Neuroscience, vol. 26, no. 8, pp. 2369-2375, 2007.
doi: 10.1111/j.1460-9568.2007.05810.x
12 - S. F. Toledo, N. Giladi, C. Peretz, T. Herman, L. Gruendlinger and J. M. Hausdorff, "Treadmill Walking as an External Pacemaker to Improve Gait," Movement Disorders, vol. 20, no. 9, pp. 1109-1114, 2005. doi: 10.1002/mds.20507
13 - N. Giladi, C. Peretz, T. Herman, L. Gruendlinger, J. M. Hausdorff and S. F. Toledo, "Effect of gait speed on gait rhythmicity in Parkinson's disease: variability of stride time and swing time respond differently," NeuroEngineering and Rehabilitation, vol. 2, no. 23, p. 7, 2005.
doi: 10.1186/1743-0003-2-23
14 - C. G. Goetz, W. Poewe, O. Rascol and G. T. Stebbins, "Movement Disorder Society Task Force report on the Hoehn and Yahr staging scale: Status and recommendations The Movement Disorder Society Task Force on rating scales for Parkinson's disease," Movement Disorders, vol. 19, no. 9, pp. 1020-1028, 2014.
doi: 10.1002/mds.20115
15 - L. J. Evers, J. H. Krijthe, M. J. Meinders, B. R. Bloem and T. M. Heskes, "Measuring Parkinson's disease over time: The real-world within-subject reliability of the MDS-UPDRS," Movement Disorders, vol. 36, no. 10, pp. 2444-2451, 2019.
doi: 10.1002/mds.27790
16 - D. Joshi, A. Khajuria and P. Joshi, "An automatic non-invasive method for Parkinson's disease classification," ELSEVIER, vol. 145, pp. 135-145, 2017. doi: 10.1016/j.cmpb.2017.04.007
17 - Vahid Mehdipour, "Mahsa Memarianfard," Modares Civil Engineering, vol. 18, no. 5, pp. 217-226, 2019.
doi: 20.1001.1.24766763.1397.18.5.3.3
18 - M. S. T. R. J. G. M. S. Mahsa Vaghefi, "Polymer Gear Fault Detection Based on Audio Signal and Wavelet Packet," Modares Mechanical Engineering, vol. 24, no. 6, pp. 351-362, 2024.
doi: 10.48311/MME.24.6.351
Modares Mechanical Engineering
Volume 25, Issue 6
June 2025
Pages 359-371