Enhanced Handwriting Kinematic Modeling for Alzheimer's Disease Classification Using Machine Learning Models

Alzheimer's Disease (AD) is a neurodegenerative disorder that gradually deteriorates motor and cognitive abilities, including handwriting abilities. This study explores the effectiveness of handwriting analysis in detecting AD by leveraging Machine Learning (ML) techniques. A dataset containing handwriting samples was preprocessed using normalization and Synthetic Minority Over-Sampling Technique (SMOTE) to balance class distribution. Multiple ML models were trained and evaluated. Among the tested models, the highest classification accuracy, 99.26%, was attained by Multi-Layer Perceptron (MLP). The findings suggest that handwriting-based assessment, combined with advanced ML techniques, can serve as a promising non-intrusive tool for screening and evaluating the prognosis of AD.