Handwriting segments reveal risk signs for detecting Alzheimer disease
Segment-Level Risk Discovery in Online Handwriting for Alzheimer's Disease Detection
Computer Vision and Pattern RecognitionArtificial Intelligence
Summary
Detecting Alzheimer disease could be easier by analyzing how people write on paper. The authors designed a method that looks at small parts of handwriting instead of the whole writing at once, helping to spot subtle changes linked to Alzheimer’s. Their approach compares normal writing patterns to those showing unusual timing or pen movements. By finding these risky segments without needing detailed labels, the method helps highlight specific handwriting features related to Alzheimer’s. Tests showed their technique outperforms others at telling apart healthy and Alzheimer’s writing samples.
What this means in practice
- •For healthcare software developers: Develop tools that analyze online handwriting in segments to improve early Alzheimer detection accuracy.
- •For digital pen device makers: Incorporate segment-level risk models into smart pens to provide real-time feedback on cognitive health.$Commercial implications: This paper enables embedding interpretable Alzheimer risk assessment into pen devices for healthcare monitoring products.
Authors
Changqing Gong, Huafeng Qin, Mounîm A. El-Yacoubi
Abstract
Online handwriting provides a non-invasive and low-cost behavioral biomarker for Alzheimer's disease (AD) detection, as it reflects both cognitive planning and fine motor control. Existing handwriting-based AD detection methods usually rely on global trajectory features or whole-sample representations, which can be strongly affected by individual writing style, task-specific variation, and acquisition noise. In this paper, we propose NormPaST-Risk, a healthy-normative Paper-Air selective trajectory state-space risk network for interpretable AD detection from online handwriting. Instead of treating the entire trajectory as a single holistic representation, our method reformulates AD handwriting detection as local disease-relevant segment discovery. Specifically, a multi-scale temporal encoder captures stroke dynamics at different temporal resolutions, while a selective Paper-Air state-space encoder models long-range handwriting progression and distinguishes on-paper motor execution from in-air planning and transition behaviors. To explicitly characterize abnormal deviations, a healthy normative branch learns normal handwriting dynamics from healthy controls, and a task-aware multi-expert segment-risk module estimates segment-level AD risk calibrated by hidden-state changes and normative deviations. A weakly supervised segment-level objective further enables high-risk segment discovery without manual segment annotations. Experiments on the DARWIN benchmark demonstrate that the proposed framework achieves superior AD/HC classification performance compared with existing methods. Moreover, the discovered high-risk segments can be projected back to the original handwriting trajectory, providing interpretable evidence associated with AD-related handwriting variations.