Abstract
Early detection of Mild Cognitive Impairment (MCI) offers a critical window for intervention before progression to dementia. This study presents a novel approach to MCI screening through multimodal behavioral analysis during the Clock Drawing Test (CDT), implementing a comprehensive data collection system using standard tablet devices. Our approach analyzes three behavioral dimensions: drawing trajectories, facial expressions, and hand motion patterns. We developed an integrated framework combining Convolutional Neural Networks with multi-head attention mechanisms for drawing analysis, alongside specialized feature extraction methods for facial and motion data. To effectively integrate these behavioral markers, we proposed a Higher-order Canonical Correlation Analysis (HCCA) algorithm that models complex relationships between modalities. In our primary study with 69 MCI participants and 133 age-matched controls, we identified distinct behavioral patterns: temporal drawing anomalies, altered facial behaviors including increased gaze variability, and distinctive motion patterns reflecting changes in movement stability. Our multimodal approach achieved an AUC of 0.92 (accuracy: 92.68%, sensitivity: 90.91%), with HCCA further improving performance to an AUC of 0.97. External validation with 76 additional participants demonstrated good generalizability (AUC: 0.86). These findings reveal how cognitive impairment manifests across multiple behavioral channels offer clinicians precise, interpretable quantification of cognitive function for more accurate MCI screening.
Funding Information
  • National Science and Technology Innovation 2030, Noncommunicable Chronic Diseases-National Science and Technology Major Project (2024ZD0524300, 2024ZD0524302)

This publication has 48 references indexed in Scilit: