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

Area of Science:

• Neurology
• Computer Science
• Biomedical Engineering

Background:

• Alzheimer's Disease (AD) is a progressive neurodegenerative disorder impacting cognitive and motor functions.
• Handwriting impairment is a recognized symptom of AD, affecting fine motor control and cognitive processing.

Purpose of the Study:

• To investigate the efficacy of handwriting analysis for Alzheimer's Disease detection using Machine Learning (ML).
• To evaluate the performance of various ML models in classifying AD based on handwriting characteristics.

Main Methods:

• A dataset of handwriting samples was collected and preprocessed.
• Data balancing was achieved using normalization and Synthetic Minority Over-Sampling Technique (SMOTE).
• Multiple Machine Learning models, including Multi-Layer Perceptron (MLP), were trained and assessed.

Main Results:

• The Multi-Layer Perceptron (MLP) model achieved a classification accuracy of 99.26%.
• The study demonstrated the potential of ML in identifying AD through handwriting analysis.

Conclusions:

• Handwriting analysis, enhanced by ML, presents a highly accurate and non-intrusive method for AD screening.
• This approach can aid in the early detection and prognosis evaluation of Alzheimer's Disease.