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.

翻译：轻度认知障碍（MCI）因其进展为痴呆的高风险而成为一个重大的公共卫生问题。本研究探讨了在受控环境中，利用来自35名老年人的自发语音助手（VA）指令检测MCI的潜力。具体而言，我们设计了一项指令生成任务，其中包含预定义的意图，让参与者自由生成指令；与朗读指令相比，这些生成的指令与认知能力的关联更为密切。我们利用音频、文本、意图以及多模态融合特征，开发了MCI分类和回归模型。研究发现，指令生成任务的表现优于指令朗读任务，通过利用多模态融合特征，平均分类准确率达到82%。此外，与朗读指令相比，生成的指令与记忆和注意力子领域的相关性更强。我们的结果证实了指令生成任务的有效性，并暗示了利用纵向家庭指令进行MCI检测的前景。