Parkinson's Disease Detection through Vocal Biomarkers and Advanced Machine Learning Algorithms - Research Article

Aug 3, 2026

Upload by Hazel

Parkinson’s disease (PD) is a common neurodegenerative disorder affecting motor neurons, producing tremors, stiffness, and gait difficulties. The study investigates whether vocal feature alterations can enable earlier prediction of PD onset. A range of advanced machine-learning models—including XGBoost, LightGBM, Bagging, AdaBoost, and Support Vector Machine—are compared using accuracy, AUC, sensitivity, and specificity. Results identify LightGBM as the top performer, reaching 96% accuracy with 96% AUC, 100% sensitivity, and 94.43% specificity. The findings support vocal biomarkers combined with machine learning for timely PD detection.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages8

Reading Time20 min

AccessFree to download

Introduction

Vocal features for early PD prediction

Parkinson’s disease impact and diagnostic challenges

Role of machine learning in medical diagnosis

Journal of Computer Science and Technology Studies ISSN: 2709-104X DOI: 10. 32996/jcsts Journal [Homepage: www.al-kindipublisher.com/index.php/jcsts](Homepage: www.al-kindipublisher.com/index.php/jcsts) JCSTS AL-KINDI CENTER FOR RESEARCH AND DEVELOPMENT | RESEARCH ARTICLE
Parkinson's Disease Detection through Vocal Biomarkers and Advanced Machine Learning Algorithms
Md Abu Sayed1 ✉ Maliha Tayaba2, MD Tanvir Islam3, Md Eyasin Ul Islam Pavel4, Md Tuhin Mia5, Eftekhar Hossain Ayon6, Nur Nob7 and Bishnu Padh Ghosh8
1Department of Professional Security Studies, New Jersey City University, Jersey City, New Jersey, USA
2Department of Computer Science, University of South Dakota, Vermillion, South Dakota, USA
3Department of Computer Science, Monroe College, New Rochelle, New York, USA
4Department of Public and Nonprofit Management, University of Texas at Dallas, Dallas, TX, USA
5School of Business, International American University, Angeles, California, USA
6Department of Computer & Info Science, Gannon University, Erie, Pennsylvania, USA
7Department of Healthcare Management, Saint Francis College, Brooklyn, New York, USA.
8School of Business, International American University, Los Angeles, California, USA
Corresponding Author: Md Abu Sayed, [E-mail](E-mail: msayed@njcu.edu)[: msayed@njcu.edu](E-mail: msayed@njcu.edu) | | --- | | | ABSTRACT
Parkinson's disease (PD) is a prevalent neurodegenerative disorder known for its impact on motor neurons, causing symptoms like tremors, stiffness, and gait difficulties. This study explores the potential of vocal feature alterations in PD patients as a means of early disease prediction. This research aims to predict the onset of Parkinson's disease. Utilizing a variety of advanced machine-learning algorithms, including XGBoost, LightGBM, Bagging, AdaBoost, and Support Vector Machine, among others, the study evaluates the predictive performance of these models using metrics such as accuracy, area under the curve (AUC), sensitivity, and specificity. The findings of this comprehensive analysis highlight LightGBM as the most effective model, achieving an impressive accuracy rate of 96% alongside a matching AUC of 96% . LightGBM exhibited a remarkable sensitivity of 100% and specificity of 94.43%, surpassing other machine learning algorithms in accuracy and AUC scores. Given the complexities of Parkinson's disease and its challenges in early diagnosis, this study underscores the significance of leveraging vocal biomarkers coupled with advanced machine-learning techniques for precise and timely PD detection.
| KEYWORDS
RGB-D camera, Microsoft Kinect, Parkinson's disease assessment, gait analysis, skeleton data, deep brain stimulation, gait parameters, discrimination, PD ON and PD OFF states, center shoulder velocity, cost-effective, portable system, hospital environment
| ARTICLE INFORMATION
ACCEPTED: 05 November 2023 PUBLISHED: 02 December 2023 DOI: 10. 32996/jcsts.2023.5.4.14 | 1. Introduction Parkinson's disease (PD) is a significant neurodegenerative disorder that predominantly affects motor neurons, leading to distressing symptoms such as tremors, stiffness, and difficulties in controlling gait. PD stands out among neurodegenerative conditions due to its profound impact on motor functions and subsequent decline in quality of life. This study explores vocal feature alterations as potential indicators for early PD prediction in the pursuit of improved diagnosis and timely intervention. Leveraging the intricate connection between vocal characteristics and neurological disorders, particularly PD, offers a promising avenue for enhancing diagnostic accuracy and prognosis. Copyright: © 2023 the Author(s) . This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC-BY) 4.0 license ([https://creativecommons.org/licenses/by/4.0/](https://creativecommons.org/licenses/by/4.0/)) . Pub

FAQs

How does the study attempt to predict Parkinson’s disease onset?

It analyzes vocal feature alterations in PD patients as potential indicators for early prediction of disease onset.

Which machine learning model performed best in the evaluation?

LightGBM achieved the strongest results, with 96% accuracy and 96% AUC.

What metrics were used to compare the predictive models?

The study used accuracy, AUC, sensitivity, and specificity to measure and compare model performance.

Aug 3, 2026

Upload by Hazel