Research on Prediction of Parkinson’s Disease Based on Speech Features

DOI

10.2991/978-94-6463-823-3_55How to use a DOI?

Keywords

Parkinson’s Disease; Machine Learning; Speech Analysis; Xgboost; KNN Imputer

Abstract

Early signs of Parkinson’s disease (PD), a common neurological illness, include hoarseness, unusual speech rhythms, and decreased voice volume. These speech impairments significantly impact communication abilities, making speech analysis a crucial tool for early PD diagnosis and intervention. However, existing speech classification models for PD face challenges with class imbalance, so this study employs a KNN Imputer to fill in missing features based on similar samples and integrates XGBoost to capture complex nonlinear relationships among features like speech rate, pitch and volume. XGBoost, by employing gradient boosting trees, effectively handles outliers and noise, making it a robust method for speech classification in Parkinson’s disease. The experimental results indicate that this approach achieves an average accuracy and test accuracy of 90% irresponsible of class imbalance. These results indicate that PD speech classification performance can be considerably enhanced by combining KNN Imputer with XGBoost, providing a novel approach for early PD detection.

Copyright

© 2025 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  - Bowen Tian
PY  - 2025
DA  - 2025/08/31
TI  - Research on Prediction of Parkinson’s Disease Based on Speech Features
BT  - Proceedings of the 2025 3rd International Conference on Image, Algorithms, and Artificial Intelligence (ICIAAI 2025)
PB  - Atlantis Press
SP  - 548
EP  - 555
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-823-3_55
DO  - 10.2991/978-94-6463-823-3_55
ID  - Tian2025
ER  -