International Journal For Multidisciplinary Research

E-ISSN: 2582-2160   •   Impact Factor: 9.24

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

Call for Paper Volume 8, Issue 1 (January-February 2026) Submit your research before last 3 days of February to publish your research paper in the issue of January-February.
Submit Research Paper Join as a Reviewer

Plagiarism is checked by the leading plagiarism checker TurnItIn

Call for Paper

Volume 8 Issue 1
January-February 2026

Submit your research paper

Indexing Partners
Academia Advanced Sciences Index Bielefeld Academic Search Engine CiteSeer DRJI Google Scholar Independent Search Engine & Directory Network ISI (International Scientific Indexing) Issuu Mendeley Research Networks
RefSeek ResearcherId - Thomson Reuters ResearchGate Scirus Scribd Semantic Scholar UTeM - Universiti Teknikal Malaysia Melaka Wiki for Call for Papers WorldCat Zenodo

Advancing Voice-based Parkinson's Detection with Hybrid XGBoost-LightGBM Models

Author(s) Mr. Rajnish K Ranjan, Prof. Dr. Anupam Agrawal, Dr. Divyarth Rai
Country India
Abstract Parkinson’s disease (PD) affects millions of individuals across the world and is characterized by gradual degeneration of the nervous system, and leading to both motor and non-motor dysfunctions. Early and reliable identification of the disease is important, as it directly influences therapeutic strategies and long term patient outcomes. This research work presents a hybrid stacking ensemble technique that integrates Extreme Gradient Boosting (XGBoost) with Light Gradient Boosting Machine (LightGBM) to improve the predictive accuracy of PD diagnosis and disease progression assessment. By leveraging the complementary learning capabilities of both algorithms, the proposed framework aims to deliver strong generalization and high performance classification, particularly in the early stages of PD detection. The evaluation of proposed work is carried out using two publicly available UCI datasets: the Parkinson’s Disease Detection dataset for classification and the Parkinson’s Disease Telemonitoring dataset for regression-based prediction of UPDRS scores. On the detection dataset, the model achieved an accuracy of 96.7% with a perfect recall of 100%. On the Telemonitoring dataset, the framework produced an RMSE of 1.70 and an R² value of 0.973 for Total UPDRS, and an RMSE of 1.19 with an R² of 0.977 for Motor UPDRS. When the regression problem is reframed as binary classification, the model achieved a high accuracy range of 97-98%. Overall, the results show that ensemble-based learning techniques can significantly improve the reliability of predictive models and serve as effective decision support tools for the diagnosis and monitoring of Parkinson’s disease.
Keywords Parkinson’s disease, XGBoost, LightGBM, Machine Learning, Dementia
Field Computer > Artificial Intelligence / Simulation / Virtual Reality
Published In Volume 8, Issue 1, January-February 2026
Published On 2026-01-28
DOI https://doi.org/10.36948/ijfmr.2026.v08i01.67243
Short DOI https://doi.org/hbmrnp
View / Download PDF File

Share this



E-ISSN 2582-2160
CrossRef

CrossRef DOI is assigned to each research paper published in our journal.

IJFMR DOI prefix is
10.36948/ijfmr

Downloads
Research Paper Format Copyright Permission Form and Undertaking Form Cover Page Vol 8 Isu 1Cover Page Vol 7 Isu 6Cover Page Vol 7 Isu 5

All research papers published on this website are licensed under Creative Commons Attribution-ShareAlike 4.0 International License, and all rights belong to their respective authors/researchers.

CC-BY-SA Open Access

About IJFMR
Fees & Payment
Current Issue
Publication Archive 		Submit Research Paper
Track Submission Status
Publication Guidelines
Publication Ethics
Peer Review & Plagiarism 		Join as a Reviewer
Editors & Reviewers
Reviewer Referral Program
Get Reviewer Membership Certi. 		Website/Journal Policies
Usage Policy
Content Policies
Privacy Policy
Contact Us +91-9687-828-838 editor@ijfmr.com