An Electronic Assessment System of Inflammatory Demyelinating Diseases Based on Digital Drawing Test

This study developed an electronic cognitive assessment system for patients with Inflammatory Demyelinating Diseases (IDD), aiming to explore the application of digital drawing in assisting cognitive assessment. The system includes the Montreal Cognitive Assessment (MoCA), Symbol Digit Modalities Test (SDMT), and a series of neuropsychological assessment scales. Additionally, it incorporates digital drawing tasks such as Sentence Writing, Pentagon Copying, Cube Copying, Trail Making Test, and Clock Drawing Test. Dynamic drawing data of digital drawing were collected using a digitizing tablet, and features were extracted. A cognitive state classification model was constructed using machine learning methods. Support vector machines (SVM) showed superior classification performance across multiple task datasets, with the best performance observed in the classification of cube drawing tasks. Significance analysis revealed that features such as total time in the Cube Copying, air stroke length in the Cube Copying, and mean of stroke length in the Trail Making Test effectively distinguished the cognitive impairment group (CI) from the cognitive preservation group (CP) and showed significant correlations with neuropsychological assessment scores. This study provides a novel automated assessment tool for detecting cognitive impairment in patients with IDD and offers empirical evidence for future research.