Designing and Evaluating a Conversational Agent for Early Detection of Alzheimer's Disease and Related Dementias

2025-09-14

AI Summary

Alzheimer’s disease and related dementias (ADRD) are frequently diagnosed too late to enable timely intervention, as existing screening tools primarily classify cognitive status without supporting structured clinical history collection. Method: We introduce the first large language model (LLM)-driven voice-based conversational agent for early ADRD detection. Designed to elicit detailed, empathetic, and systematic narratives from patients and informants about cognitive and behavioral changes, it transforms unstructured discourse into clinically relevant, structured data. Our approach integrates speech interaction, dialogue analysis, user-centered design, and blinded expert evaluation. Results: In a study with 30 suspected ADRD cases, the agent demonstrated high diagnostic agreement with specialist clinicians (Cohen’s κ = 0.82). Users rated it highly for patience, logical coherence, and effectiveness in facilitating disclosure of complex symptoms. This work establishes a novel paradigm for LMs in dementia diagnostics—balancing clinical validity with human-centered interaction.

Technology Category

• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Machine Learning: Large Multimodal Models (LMMs)
• Cognitive Modeling & Cognitive Systems: Agent Architectures

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Search and Retrieval-Augmented AI: Agentic search

Abstract

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.

Problem

• Early detection of Alzheimer's disease and related dementias
• Eliciting patient narratives for diagnostic assessment
• Developing conversational agents for dementia screening

Innovation

• Leveraging LLMs for conversational agents
• Eliciting ADRD narratives from patients
• Clinical validation through specialist interviews