LUMEN (Large Language Model for Understanding and Monitoring Elderly Neurocognition): A Clinical Feasibility Study With Nested Qualitative Evaluation for AI- Assisted Dementia Assessment
试验速览
- 阶段
- 不适用
- 状态
- 招募中
- 入组人数
- 60
- 试验地点
- 1
- 主要终点
- SUS (System Usability Scale)
研究概览
简要总结
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.
详细描述
- Background and Rationale Dementia diagnosis relies on clinical history, cognitive assessments, and collateral information from caregivers. However, obtaining structured and reliable collateral histories is challenging due to caregiver burden, recall bias, and time constraints in memory clinics. Large language models (LLMs) have the potential to improve this process by guiding structured history-taking, extracting clinically relevant details, and standardising information gathering.
LUMEN (Large Language Model for Understanding and Monitoring Elderly Neurocognition) is an AI-powered conversational tool designed to assist caregivers in providing structured collateral histories before clinical dementia assessments. Seed-funded by the Royal College of Psychiatrists, the Alzheimer's Research UK Northern Network and the Newcastle Biomedical Research Network, LUMEN was developed to enhance diagnostic accuracy, reduce caregiver burden, and improve workflow efficiency in memory clinics.
This study will evaluate the feasibility, usability, and acceptability of LUMEN in real-world clinical settings through a nested qualitative feasibility study. We will recruit caregivers and clinicians to interact with LUMEN and assess its effectiveness in gathering collateral histories. The study will also incorporate co-production workshops with community groups to explore issues around language, cultural inclusivity, and accessibility. Findings will inform future refinements and a larger validation study. 2. Research Objectives
This study aims to:
- Evaluate LUMEN's usability -Measure caregiver and clinician experiences using validated scales (System Usability Scale [SUS] and NASA Task Load Index [NASA-TLX]).
- Explore acceptability and implementation barriers and facilitators-Conduct qualitative interviews and coproduction workshops to refine LUMEN's design, ensuring accessibility across diverse user groups.
- Compare LUMEN's outputs to clinician assessments-Investigate the alignment between LUMEN-generated reports and clinician-elicited histories using Cohen's Kappa for inter-rater reliability.
研究设计
- 研究类型
- Observational
- 观察模型
- Other
- 时间视角
- Prospective
入排标准
- 年龄范围
- 65 Years 至 —（Older Adult）
- 性别
- All
- 接受健康志愿者
- 否
入选标准
- •Carers of patients attending Memory Clinic appointments; Aged 18 or over; Both patients and cares can provide informed consent; Basic English literacy
- •Clinicians must have at least 2 years of specialist dementia care experience and be personally responsible for dementia diagnosis; Must be provide informed consent
排除标准
- 未提供
研究组 & 干预措施
Patient-carer dyads
Carers (n=20-30 dyads): Recruited via Northumbria NHS Memory Clinics. Eligible carers will be adults (≥18 years) who know the patient well, have basic English literacy, and can provide informed consent.
• Patients (n=20-30): Individuals (≥65 years) attending a memory clinic for cognitive assessment.
- Baseline Data Collection:
- Demographics (age, gender, ethnicity, socioeconomic status).
- Clinical diagnosis (where available).
- Cognitive test scores (MoCA/ACE).
- LUMEN Interaction:
o Carers will use LUMEN on a laptop or tablet to provide structured collateral histories (~20-30 min). 3. Usability and Cognitive Load Assessment:
- SUS (System Usability Scale): 10-item Likert-scale questionnaire assessing ease of use (score ≥70 = good usability).
- NASA-TLX (Task Load Index): Evaluates perceived cognitive workload (scores 0-29 = low workload).
- Qualitative Evaluation:
- Semi-structured interviews (n=10 carers).
干预措施: LUMEN prototype software interaction (Other)
Clinicians
4.1. Participants and Recruitment
• Clinicians (n=8-10): Specialists in dementia care (neurologists, psychiatrists, geriatricians, advanced nurse practitioners) with ≥2 years of experience.
4.2. Study Procedures
- Baseline Data Collection:
o Demographics (age, gender, ethnicity, socioeconomic status). 2. LUMEN Interaction:
o Clinicians will review LUMEN-generated histories to assess completeness and clinical utility. 3. Usability and Cognitive Load Assessment:
- SUS (System Usability Scale): 10-item Likert-scale questionnaire assessing ease of use (score ≥70 = good usability).
- NASA-TLX (Task Load Index): Evaluates perceived cognitive workload (scores 0-29 = low workload).
- Qualitative Evaluation:
- Semi-structured interviews (n=4-5 clinicians).
干预措施: LUMEN prototype software interaction (Other)
结局指标
主要结局
SUS (System Usability Scale)
时间窗: Immediately after use of software
10-item Likert-scale questionnaire assessing ease of use (score ≥70 = good usability).
NASA-TLX (Task Load Index):
时间窗: Immediately after prototype interaction
Evaluates perceived cognitive workload (scores 0-29 = low workload).
次要结局
未报告次要终点