NeuroDx: a Novel Machine Learning Paradigm for Unveiling Parkinson’s Disease Patterns

EasyChair Preprint 11814

Abstract

This paper explores an innovative slant for detecting Parkinson's disease (PD) by analyzing voice data from patients. To extract meaningful features from the MDVP voice input, a machine learning technique, including a Support Vector Machine (SVM) is employed. The study emphasizes the importance of data collection, preprocessing, and feature engineering to improve model accuracy. Robustness is ensured by cross-validation and testing across diverse patient datasets. Integrating voice-based PD detection in clinical practice holds potential for early diagnosis and personalized care. This research highlights the efficacy of voice-based machine learning in enhancing PD detection, offering a non-invasive and patient-centric approach.

Keyphrases: Parkinson’s disease, Support Vector Machine, machine learning

@booklet{EasyChair:11814,
  author    = {Sharayu Garad and Pranoti Naiknaware and Anisha Shinde and Ashutosh Garad and Meenakshi Pawar},
  title     = {NeuroDx: a Novel Machine Learning Paradigm for Unveiling Parkinson’s Disease Patterns},
  howpublished = {EasyChair Preprint 11814},
  year      = {EasyChair, 2024}}