Efficient Parkinson Diagnosis Method Using Handwriting and Firefly Feature Selection Algorithm

Abstract

Handwriting analysis is useful in a wide range of applications such as medical diagnostics. Artificial Intelligence (AI) methods have a vital role in assessing abnormalities using handwriting. This paper presents and evaluates an efficient handwriting-based Computer-Aided Diagnosis (CAD) system for Parkinson’s diagnosis as one of the most common neurodegenerative diseases. The research objective is to improve the performance of the CAD system in Parkinson’s diagnosis. The research strategy is using efficient AI methods. In the developed CAD system, the Gray-Level Co-occurrence Matrix (GLCM) is employed as a feature extraction method. The Firefly Algorithm (FA) is then applied to extracted features to select the most relevant features. The Support Vector Machine (SVM), k-Nearest Neighbor (kNN), and Ensemble algorithms are used to classify the results. The performance of the proposed CAD system is evaluated using MATLAB R2021b and a templated handwritten dataset collected at Botucatu Medical School, São Paulo State University, Brazil. The evaluation's findings show that the suggested method works well. The suggested CAD system performs best when the Meander handwritten exam, GLCM feature extraction method, FA feature selection algorithm, and SVM classification algorithm are used attaining an accuracy of 96%. The accuracy results in this study show that the proposed method can be considered a noninvasive accessible diagnostic method.