# Exploring Handwriting-Based Biomarkers for Alzheimer’s Disease: Identifying Discriminative Features and Tasks to Enhance Diagnostic Accuracy

## TL;DR

This paper explores using handwriting analysis to detect Alzheimer's disease, combining many features and machine learning techniques to improve accuracy and efficiency.

## Contribution

The novel contribution is a dynamic ensemble learning framework with task reduction and enriched features for Alzheimer's detection using handwriting.

## Key findings

- Reducing handwriting tasks improved accuracy from 79.47% to 81.03% while saving 40% training time and 35% memory.
- Hard Ensemble with L1-based feature selection achieved the highest accuracy of 94.20%.
- Dynamic ensemble learning combined with task reduction provides an efficient solution for Alzheimer's detection.

## Abstract

Background/Objectives: This study proposes a comprehensive classification framework for the automatic detection of Alzheimer’s disease using handwriting data. An enriched feature space is constructed by combining 18 baseline features extracted from raw handwriting signals with 30 additional features derived from established handwriting analysis studies, resulting in a total of 48 features. To enhance clinical practicality, a task reduction analysis is conducted by comparing the full dataset containing 25 handwriting tasks with a reduced dataset comprising 14 selected tasks. Methods: The proposed framework employs a two-stage evaluation strategy involving four feature selection methods (Random Forest Feature Importance, Extreme Gradient Boosting Feature Importance, L1 Regularization and Recursive Feature Elimination), three normalization techniques (Unnormalized, Min–Max and Z-Score), and five baseline machine learning classifiers (Random Forest, Logistic Regression, Multilayer Perceptron, XGBoost and Support Vector Machines). In the second stage, a dynamic ensemble learning strategy is introduced, where the most effective classifiers are adaptively selected for each cross-validation fold and integrated using soft and hard voting schemes. Results: The experimental results demonstrate that reducing the number of tasks leads to an improvement in average classification accuracy from 79.47% to 81.03%, while simultaneously decreasing training time and memory consumption by approximately 40% and 35%, respectively. The highest classification performance, achieving an accuracy of 94.20%, is obtained using the Hard Ensemble combined with L1-based feature selection. Conclusions: These findings highlight that the joint use of enriched feature representations, task reduction, and dynamic ensemble learning provides an effective and computationally efficient solution for handwriting-based Alzheimer’s disease detection.