Classification and Assessment of Hand Arthritis Stage using Support Vector Machine

Area of Science:

• Medical imaging and machine learning applications.
• Biomedical engineering and data analysis.

Background:

• Arthritis is a prevalent global health issue, significantly impacting individuals worldwide.
• Hand arthritis affects numerous patients, necessitating accurate staging for effective management.

Purpose of the Study:

• To develop and evaluate a machine learning model for classifying hand arthritis stages.
• To categorize the progression of hand arthritis in patients using automated analysis.

Main Methods:

• Utilized finger border detection and curvature analysis for feature extraction.
• Applied principal components analysis (PCA), support vector machine (SVM), and K-nearest neighbor (KNN) algorithms for classification.
• Focused on analyzing proximal interphalangeal (PIP) and distal interphalangeal (DIP) joints.

Main Results:

• The proposed machine learning approach demonstrated promising accuracy in classifying hand arthritis stages.
• Achieved notable performance in binary classification tasks for PIP and DIP joint involvement.
• The method provides a quantitative approach to assessing arthritis severity in hand joints.

Conclusions:

• Machine learning offers a viable tool for objective hand arthritis staging.
• The developed method shows potential for early detection and management of hand arthritis.
• Further research can refine the model for multi-class classification and broader clinical application.