Designing and Evaluating a Conversational Agent for Early Detection of Alzheimer's Disease and Related Dementias
This work addresses the challenge of delayed diagnosis in dementia care by providing a structured tool for assessment, though it is preliminary and incremental in applying existing LLM technology to a new healthcare context.
The researchers tackled the problem of early detection of Alzheimer's disease and related dementias by designing a conversational agent using large language models to elicit patient narratives, and found that symptoms detected by the agent aligned well with those identified by specialists in a study with 30 adults.
Early detection of Alzheimer's disease and related dementias (ADRD) is critical for timely intervention, yet most diagnoses are delayed until advanced stages. While comprehensive patient narratives are essential for accurate diagnosis, prior work has largely focused on screening studies that classify cognitive status from interactions rather than supporting the diagnostic process. We designed voice-interactive conversational agents, leveraging large language models (LLMs), to elicit narratives relevant to ADRD from patients and informants. We evaluated the agent with 30 adults with suspected ADRD through conversation analysis (n=30), user surveys (n=19), and clinical validation against blinded specialist interviews (n=24). Symptoms detected by the agent aligned well with those identified by specialists across symptoms. Users appreciated the agent's patience and systematic questioning, which supported engagement and expression of complex, hard-to-describe experiences. This preliminary work suggests conversational agents may serve as structured front-end tools for dementia assessment, highlighting interaction design considerations in sensitive healthcare contexts.