Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

A Machine Learning Approach to Analyze the Effects of Alzheimer's Disease on Handwriting through Lognormal Features

Tiziana D'Alessandro, Cristina Carmona-Duarte, Claudio De Stefano, Moises Diaz, Miguel A. Ferrer, Francesco Fontanella

TL;DR

The paper addresses the challenge of early Alzheimer’s disease detection by analyzing handwriting through features derived from the Sigma-Lognormal model. It proposes a three-stage ML framework—classification, stacking, and ranking/majority voting—to classify AD versus healthy controls using 25 tasks collected from 174 participants. Key contributions include a rich feature set from lognormal parameters, an extensive ML evaluation with multiple classifiers and aggregation strategies, and insights into how handwriting dynamics relate to age and education. While results show promising discriminative power (up to 82.5% accuracy via majority vote), the authors acknowledge limitations and outline avenues to improve diagnostic utility and generalization to other conditions.

Abstract

Alzheimer's disease is one of the most incisive illnesses among the neurodegenerative ones, and it causes a progressive decline in cognitive abilities that, in the worst cases, becomes severe enough to interfere with daily life. Currently, there is no cure, so an early diagnosis is strongly needed to try and slow its progression through medical treatments. Handwriting analysis is considered a potential tool for detecting and understanding certain neurological conditions, including Alzheimer's disease. While handwriting analysis alone cannot provide a definitive diagnosis of Alzheimer's, it may offer some insights and be used for a comprehensive assessment. The Sigma-lognormal model is conceived for movement analysis and can also be applied to handwriting. This model returns a set of lognormal parameters as output, which forms the basis for the computation of novel and significant features. This paper presents a machine learning approach applied to handwriting features extracted through the sigma-lognormal model. The aim is to develop a support system to help doctors in the diagnosis and study of Alzheimer, evaluate the effectiveness of the extracted features and finally study the relation among them.

A Machine Learning Approach to Analyze the Effects of Alzheimer's Disease on Handwriting through Lognormal Features

TL;DR

The paper addresses the challenge of early Alzheimer’s disease detection by analyzing handwriting through features derived from the Sigma-Lognormal model. It proposes a three-stage ML framework—classification, stacking, and ranking/majority voting—to classify AD versus healthy controls using 25 tasks collected from 174 participants. Key contributions include a rich feature set from lognormal parameters, an extensive ML evaluation with multiple classifiers and aggregation strategies, and insights into how handwriting dynamics relate to age and education. While results show promising discriminative power (up to 82.5% accuracy via majority vote), the authors acknowledge limitations and outline avenues to improve diagnostic utility and generalization to other conditions.

Abstract

Alzheimer's disease is one of the most incisive illnesses among the neurodegenerative ones, and it causes a progressive decline in cognitive abilities that, in the worst cases, becomes severe enough to interfere with daily life. Currently, there is no cure, so an early diagnosis is strongly needed to try and slow its progression through medical treatments. Handwriting analysis is considered a potential tool for detecting and understanding certain neurological conditions, including Alzheimer's disease. While handwriting analysis alone cannot provide a definitive diagnosis of Alzheimer's, it may offer some insights and be used for a comprehensive assessment. The Sigma-lognormal model is conceived for movement analysis and can also be applied to handwriting. This model returns a set of lognormal parameters as output, which forms the basis for the computation of novel and significant features. This paper presents a machine learning approach applied to handwriting features extracted through the sigma-lognormal model. The aim is to develop a support system to help doctors in the diagnosis and study of Alzheimer, evaluate the effectiveness of the extracted features and finally study the relation among them.
Paper Structure (19 sections, 3 equations, 6 figures, 6 tables)

This paper contains 19 sections, 3 equations, 6 figures, 6 tables.

Table of Contents

  1. Introduction
  2. The Sigma-Lognormal Model
  3. Description
  4. Data collection
  5. Tasks
  6. Feature Engineering
  7. Experimental phase
  8. Workflow
  9. First Step: ML Classification
  10. Second Step: Stacking
  11. Third Step: Ranking and Majority vote
  12. Results
  13. First Step Results
  14. Second Step Results
  15. Third Step Results
  16. ...and 4 more sections

Figures (6)

  • Figure 1: Comparison between the original (green) and the reconstructed (blue) velocity profile. Dotted blue lines show the lognormal functions that generated the reconstructed profile.
  • Figure 2: Workflow Representation.
  • Figure 3: Average Accuracy achieved on 30 runs for every ML algorithm on lognormal features
  • Figure 4: Comparison between average Accuracy achieved on 30 runs for every task with the best-performing ML algorithm for Dynamic and Lognormal features
  • Figure 5: Distribution of people according to Education level and Age.
  • ...and 1 more figures