A-CONECT: Designing AI-based Conversational Chatbot for Early Dementia Intervention

Junyuan Hong, Wenqing Zheng, Han Meng, Siqi Liang, Anqing Chen, Hiroko H. Dodge, Jiayu Zhou, Zhangyang Wang

Keywords: Dementia Disease, Chatbot, AI, LLM

Abstract: Mild Cognitive Impairment (MCI) is a prodrome stage of Alzheimer's Disease and related dementias. Its detection is essential for early intervention and trial cohort enrichment. A recent clinical trial demonstrated that engaging in frequent cognitively stimulating conversations could be an effective strategy against social isolation and cognitive decline. However, the widespread deployment of such interventions faces challenges, particularly due to the need for trained human interviewers to conduct the conversations. In this paper, we study an innovative solution that uses an AI-based chatbot to replace human interviewers, thus greatly improving the accessibility of this therapeutic approach. We integrate the protocols used in the previous intervention trial into the automatic chatbot for stimulating cognitive functions through cognitively demanding, engaging, and user-friendly voice-based conversations. To evaluate the effectiveness, we create MCI digital twins--virtual replicas of MCI patients--offering a scalable and realistic assessment method. With the digital twins, we provide an end-to-end framework for evaluating and iterating the chatbot. Our experiments show the chatbot's proficiency in fostering natural conversations and its potential as a cost-effective, accessible tool in dementia intervention. A demonstration of our chatbot system is available at https://a-conect.github.io/.

Submission Number: 21