Predictive Modelling of Parkinson's Disease Progression Using LightGBM Classifier
Abstract
Parkinson's disease is a progressive neurological disorder that affects millions worldwide, causing a variety of motor and non-motor symptoms, such as the condition known as freezing of gait (FOG). The overall health of people with Parkinson's disease can be significantly enhanced by early identification and treatment of freezing of gait (FOG). Using LightGBM (Gradient Boosting Machine), a well-liked gradient boosting ensemble method that is trained using the AutoML tool and is based on decision trees, we present a prediction model for freezing of gait in this work. Leveraging a comprehensive dataset of Parkinson's disease patient’s clinical profiles, gait patterns, and demographic information, we employed feature engineering techniques to extract meaningful predictors associated with FOG. Our results demonstrate the effectiveness of the LightGBM model in accurately predicting FOG episodes in Parkinson's patients. The model evaluation shown that LightGBM offers the best results with an accuracy of 92.31% when compared to other models like Support Vector Classifier and Logistic Regression.
Downloads
Metrics
References
Esfahani, A. H., Dyka, Z., Ortmann, S., & Langendörfer, P. (2021). Impact of data preparation in freezing of gait detection using feature-less recurrent neural network. IEEE Access, 9, 138120-138131.
Noor, M. H. M., Nazir, A., Ab Wahab, M. N., & Ling, J. O. Y. (2021). Detection of freezing of gait using unsupervised convolutional denoising autoencoder. IEEE Access, 9, 115700-115709.
Lin, C. H., Wang, F. C., Kuo, T. Y., Huang, P. W., Chen, S. F., & Fu, L. C. (2022). Early detection of Parkinson’s disease by neural network models. IEEE Access, 10, 19033-19044.
Wang, W., Lee, J., Harrou, F., & Sun, Y. (2020). Early detection of Parkinson’s disease using deep learning and machine learning. IEEE Access, 8, 147635-147646.
Kwon, H., Clifford, G. D., Genias, I., Bernhard, D., Esper, C. D., Factor, S. A., & McKay, J. L. (2023). An explainable spatial-temporal graphical convolutional network to score freezing of gait in parkinsonian patients. Sensors, 23(4), 1766.
Borzì, L., Sigcha, L., & Olmo, G. (2023). Context Recognition Algorithms for Energy-Efficient Freezing-of-Gait Detection in Parkinson’s Disease. Sensors, 23(9), 4426.
Nagasubramanian, G., Sankayya, M., Al-Turjman, F., & Tsaramirsis, G. (2020). Parkinson data analysis and prediction system using multi-variant stacked auto encoder. IEEE Access, 8, 127004-127013.
Zhang, J., Lim, J., Kim, M. H., Hur, S., & Chung, T. M. (2023). WM–STGCN: A Novel Spatiotemporal Modeling Method for Parkinsonian Gait Recognition. Sensors, 23(10), 4980.
Cai, Z., Gu, J., & Chen, H. L. (2017). A new hybrid intelligent framework for predicting Parkinson’s disease. IEEE Access, 5, 17188-17200.
Kour, N., & Arora, S. (2019). Computer-vision based diagnosis of Parkinson’s disease via gait: A survey. IEEE Access, 7, 156620-156645..
..
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Jyotsnarani Tripathy, D. Sowjanya, Chunduru Anilkumar, Subramanyam Kunisetti, Chandramouli
This work is licensed under a Creative Commons Attribution 4.0 International License.
You are free to:
- Share — copy and redistribute the material in any medium or format
- Adapt — remix, transform, and build upon the material for any purpose, even commercially.
Terms:
- Attribution — You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
- No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.
