Abstract :

Parkinson’s Disease (PD) Is A Long-term Brain Disorder That Gets Worse Over Time And Makes It Harder For A Person To Move Their Body And Speak Clearly. Early Detection And Proper Diagnosis Remain Important Elements In Enhancing The Living Standards Of Infected People. In This Endeavor, It Is Proposed That This Paper Introduces A Hybrid Diag- Nostic Framework That Uses The Biomedical Voice Features In Order To Determine The Parkinson’s Disease Effectively. The Method Combines The Clas- Sical Models Of Machine Learning Classifiers, Such As Support Vector Machine, Logistic Regression, Ran- Dom Forest, And K-Nearest Neighbors With A Deep Learning Architecture Based On The Convolutional Neural Network Model (one-dimensional; Conv1D), Long Short-Term Memory (LSTM) And Attention Mechanisms. The Deep Model Extracts Useful Voice Patterns Out A Pre-processed And Normalized Voice Features And Then Classify Them In A Final Decision- Making Process With The SVM. The Experimental Findings Indicate That The Hybrid Model Could Achieve Very High Accuracy And Recall That Individ- Ual Algorithms Could Not Achieve, And Hence It Can Be Effectively Deployed In A Scalable Mode Within Clinical And Remote Healthcare Environments. Keywords: Parkinson’s Disease, Voice Fea- Ture Analysis, Hybrid Classification, CNN-LSTM- Attention, Machine Learning, Deep Learning, SVM, Non-invasive Diagnosis, Medical Data Clas- Sification

Published:

17-7-2025

Issue:

Vol. 25 No. 7 (2025)

Page Nos:

515 - 524

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite