Early diagnosis of Parkinson's disease using a hybrid method of least squares support vector regression and fuzzy clustering

Hossein Ahmadi*, Lin Huo, Goli Arji, Abbas Sheikhtaheri, Shang-Ming Zhou

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

Abstract

Parkinson's disease (PD) is a neurodegenerative disorder that influence brain's neurological, behavioral, and physiological functions and includes motor and nonmotor manifestations. Although there have been several PD diagnosis systems with supervised machine learning techniques, there are more efforts that need to enhance the accurate detection of PD in its early stage. The current paper developed a novel approach by integrating Least Squares Support Vector Regression (LS-SVR) and Fuzzy Clustering for Unified Parkinson's Disease Rating Scale (UPDRS) diagnosis. This paper used feature selection and Principal Component Analysis (PCA) to overcome the multicollinearity issues in data. This paper used a large medical dataset including Motor- and Total-UPDRS to demonstrate how the proposed method can improve prediction performance via extensive evaluations and comparisons with existing methods. Compared to other prediction methods, the experimental results demonstrate that the proposed method provided the best accuracy for Total-UPDRS (Root Mean Squared Error = 0.7348; R2 = 0.9169) and Motor-UPDRS (Root Mean Squared Error = 0.8321; R2 = 0.8756) predictions.

Original languageEnglish
Pages (from-to)569-585
Number of pages17
JournalBiocybernetics and Biomedical Engineering
Volume44
Issue number3
DOIs
Publication statusPublished - 26 Aug 2024

ASJC Scopus subject areas

  • Biomedical Engineering

Keywords

  • Early diagnosis
  • Fuzzy clustering
  • Machine learning
  • Parkinson disease
  • Support vector regression

Fingerprint

Dive into the research topics of 'Early diagnosis of Parkinson's disease using a hybrid method of least squares support vector regression and fuzzy clustering'. Together they form a unique fingerprint.

Cite this