Detecting Cognitive Decline Through Handwriting: The Role of Task Complexity and Feature Selection
摘要
The present pilot study aims to analyze the characteristics of combined handwriting and drawing data by evaluating a wide range of kinematic and dynamic parameters across different graphomotor tasks, with the intention of supporting the implementation of online and remote systems for the early detection of cognitive decline markers. To this end, a total of 36 participants were included in the study, consisting of 8 individuals diagnosed with Alzheimer's disease (AD), 9 with mild cognitive impairment (MCI) and 19 healthy controls (HC). Results show, on the one hand, that the combination of specific tasks and parameters enhances the discriminative power of handwriting analysis and, on the other hand, that performance declines progressively across groups, with individuals with MCI exhibiting an intermediate and a more variable profile bridging AD and HC. Although further investigations are needed, these findings suggest that multiple and combined writing and drawing tasks have the potential to serve as valuable tools for the early diagnosis of dementia.