How word semantics and phonology affect handwriting of Alzheimer's patients: a machine learning based analysis

TL;DR

This study investigates how word semantics and phonology influence handwriting in Alzheimer's disease using six word-copy tasks spanning regular, non-regular, and non-words. A machine learning framework with four classifiers and recursive feature elimination analyzes kinematic features extracted from in-air, on-paper, and combined data, achieving up to about 89% accuracy in certain categories. Regular words tend to be more discriminant, while non-regular and non-words benefit most from feature selection, especially when using on-paper features. The results validate the approach against handwriting- and neuroimaging-based benchmarks, highlighting category-specific feature subsets and the potential utility of semantic/phonological handwriting analysis for early AD assessment.

Abstract

Using kinematic properties of handwriting to support the diagnosis of neurodegenerative disease is a real challenge: non-invasive detection techniques combined with machine learning approaches promise big steps forward in this research field. In literature, the tasks proposed focused on different cognitive skills to elicitate handwriting movements. In particular, the meaning and phonology of words to copy can compromise writing fluency. In this paper, we investigated how word semantics and phonology affect the handwriting of people affected by Alzheimer's disease. To this aim, we used the data from six handwriting tasks, each requiring copying a word belonging to one of the following categories: regular (have a predictable phoneme-grapheme correspondence, e.g., cat), non-regular (have atypical phoneme-grapheme correspondence, e.g., laugh), and non-word (non-meaningful pronounceable letter strings that conform to phoneme-grapheme conversion rules). We analyzed the data using a machine learning approach by implementing four well-known and widely-used classifiers and feature selection. The experimental results showed that the feature selection allowed us to derive a different set of highly distinctive features for each word type. Furthermore, non-regular words needed, on average, more features but achieved excellent classification performance: the best result was obtained on a non-regular, reaching an accuracy close to 90%.

Figures (3)

• Figure 1: Examples of the six tasks performed by a participant.
• Figure 2: Experimental methodology.
• Figure 3: Occurrence of features for the AL feature set.