Predicting UPDRS Scores in Parkinson’s Disease Based on Deep Learning

DOI

10.2991/978-94-6463-370-2_71How to use a DOI?

Keywords

Parkinson’s Disease; UPDRS Scores; Deep learning; Machine learning

Abstract

Parkinson’s disease is a progressive neurological disorder that has a significant impact on the quality of life of millions worldwide. Despite well-defined symptoms and known pathophysiological mechanisms, early diagnosis and effective treatment of Parkinson’s disease remain considerable challenges. At the same time, due to life pressure and unhealthy lifestyle, Parkinson’s and other diseases of the elderly have a trend of earlier onset. This study employed deep learning techniques to predict Unified Parkinson’s Disease Rating Scale (UPDRS) scores in Parkinson’s patients and investigated the relationships between various disease symptoms, offering insights into early prevention and intervention strategies. The research utilized the Parkinsons telemonitoring dataset sourced from the University of California, Irvine Machine Learning Repository, featuring data from 42 individuals with Parkinson’s disease. Motion characteristics and demographic factors, including age and gender, were analyzed to determine the feasibility of computational models in assessing UPDRS scores among Parkinson’s patients. Four distinct models including XGBRegressor, DecisionTreeRegressor, LinearRegression, and KNeighborsRegressor were employed, where XGBRegressor and DecisionTreeRegressor demonstrated superior performance across the three evaluation metrics. The proposed model offered the potential for early identification of disease severity in Parkinson’s patients, thereby facilitating the development of more precise treatment strategies. This research represented a significant step towards addressing the diagnostic and treatment challenges associated with Parkinson’s disease, ultimately aiming to enhance the overall quality of life for those affected by this debilitating condition.

Copyright

© 2024 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Yinan Li
PY  - 2024
DA  - 2024/02/14
TI  - Predicting UPDRS Scores in Parkinson’s Disease Based on Deep Learning
BT  - Proceedings of the 2023 International Conference on Data Science, Advanced Algorithm and Intelligent Computing (DAI 2023)
PB  - Atlantis Press
SP  - 705
EP  - 715
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6463-370-2_71
DO  - 10.2991/978-94-6463-370-2_71
ID  - Li2024
ER  -