Large Language Model for Understanding and Monitoring Elderly Neurocognition

Dementia affects millions of people worldwide, and early diagnosis is essential for getting the right care and support. Doctors rely on collateral histories (accounts from family members or caregivers) to understand changes in a person's memory and thinking. However, these histories can be incomplete, unstructured, or difficult to obtain, making diagnosis more challenging. This study will test LUMEN (Large Language Model for Understanding and Monitoring Elderly Neurocognition), an AI-powered conversation tool designed to help caregivers describe their loved one's symptoms more effectively. By asking structured questions and guiding the conversation, LUMEN can create clear, well-organised reports for memory clinic doctors. This could make assessments quicker, more accurate, and less stressful for families. We will test LUMEN in real-world clinics by asking caregivers and doctors to use it and provide feedback. We want to understand how easy it is to use, whether it could improve the quality of information shared, and how it fits into existing NHS memory clinic processes. We will also run co-production workshops with community groups to ensure the tool is accessible to people from diverse cultural and language backgrounds. This research is exciting because it explores how artificial intelligence can improve dementia care. If successful, LUMEN could enhance the diagnostic process, reduce carer burden, and help more people access dementia support sooner. In the future, this tool could be used nationwide in memory clinics, improving care for thousands of families.