Analyzing Multimodal Features of Spontaneous Voice Assistant Commands for Mild Cognitive Impairment Detection
This addresses early detection of MCI in older adults, offering a potential non-invasive monitoring tool, though it is incremental as it builds on existing voice-based methods with a new task design.
This study tackled detecting mild cognitive impairment (MCI) by analyzing spontaneous voice assistant commands from 35 older adults, finding that a command-generation task achieved 82% classification accuracy using multimodal fusion features.
Mild cognitive impairment (MCI) is a major public health concern due to its high risk of progressing to dementia. This study investigates the potential of detecting MCI with spontaneous voice assistant (VA) commands from 35 older adults in a controlled setting. Specifically, a command-generation task is designed with pre-defined intents for participants to freely generate commands that are more associated with cognitive ability than read commands. We develop MCI classification and regression models with audio, textual, intent, and multimodal fusion features. We find the command-generation task outperforms the command-reading task with an average classification accuracy of 82%, achieved by leveraging multimodal fusion features. In addition, generated commands correlate more strongly with memory and attention subdomains than read commands. Our results confirm the effectiveness of the command-generation task and imply the promise of using longitudinal in-home commands for MCI detection.