MemoryChat: Leveraging Large Language Models as Conversational Agents to Transform the Cognitive Assessment in Dementia Care

With the increasing prevalence of dementia, timely access to assessments, diagnosis, and support is vital. However, the shortage of dementia specialists often leads to significant delays in a patient accessing time-sensitive treatments. To address this challenge, we proposed MemoryChat, a conversational dementia assessment tool designed to collect crucial information on the patient's condition before the first clinical consultation. The Large Language Model-powered pipeline interacts with an informant to conduct a dynamic, multi-turn dialogue, collecting details. This interaction is transformed into a clinical summary and a preliminary diagnosis, serving as a reference for the clinician. %Additionally, we introduce a novel clinical question dataset, MemoryChatQ, which provides content to facilitate a comprehensive and standardised assessment of a person with suspected dementia.%Our evaluation framework systematically assesses the clinical viability of MemoryChat by measuring the conversational, summarisation, and diagnostic capabilities. We compared different strong-performing Large Language Models, including Mistral:7b, LLaMA3.1:8b, and Qwen3:14b. We found that the configuration of LLaMA3.1-8b for interactivity and summarisation, alongside Qwen3-14b for diagnostic prediction, would formulate a potential option for MemoryChat to be used in a clinical setting.