LUMEN: Prototype Conversational AI to Streamline Dementia Assessments

Aims: Dementia assessments are time-intensive and often distressing for patients and caregivers. Underdiagnosis of non-Alzheimer’s disease subtypes remains prevalent. This study aimed to develop and evaluate LUMEN (Large Language Model for Understanding and Monitoring Elderly Neurocognition), a pro...

Full description

Saved in:
Bibliographic Details
Main Authors: Song Ling Tang, Alexander Robertson, Huizhi Liang, John-Paul Taylor, Judith Harrison
Format: Article
Language:English
Published: Cambridge University Press 2025-06-01
Series:BJPsych Open
Online Access:https://www.cambridge.org/core/product/identifier/S2056472425101853/type/journal_article
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849316455536918528
author Song Ling Tang
Alexander Robertson
Huizhi Liang
John-Paul Taylor
Judith Harrison
author_facet Song Ling Tang
Alexander Robertson
Huizhi Liang
John-Paul Taylor
Judith Harrison
author_sort Song Ling Tang
collection DOAJ
description Aims: Dementia assessments are time-intensive and often distressing for patients and caregivers. Underdiagnosis of non-Alzheimer’s disease subtypes remains prevalent. This study aimed to develop and evaluate LUMEN (Large Language Model for Understanding and Monitoring Elderly Neurocognition), a prototype conversational AI to automate caregiver-collateral data collection before clinical appointments. Our goals were to reduce clinician time per assessment, improve diagnostic accuracy across dementia subtypes, and standardise caregiver assessments.
format Article
id doaj-art-112e12b37ac947e5b4296645b7f38daf
institution Kabale University
issn 2056-4724
language English
publishDate 2025-06-01
publisher Cambridge University Press
record_format Article
series BJPsych Open
spelling doaj-art-112e12b37ac947e5b4296645b7f38daf2025-08-20T03:51:44ZengCambridge University PressBJPsych Open2056-47242025-06-0111S16S1610.1192/bjo.2025.10185LUMEN: Prototype Conversational AI to Streamline Dementia AssessmentsSong Ling Tang0Alexander Robertson1Huizhi Liang2John-Paul Taylor3Judith Harrison41Hertfordshire Partnership University NHS Foundation Trust, Hertfordshire, United Kingdom2Newcastle University, Newcastle, United Kingdom2Newcastle University, Newcastle, United Kingdom2Newcastle University, Newcastle, United Kingdom2Newcastle University, Newcastle, United KingdomAims: Dementia assessments are time-intensive and often distressing for patients and caregivers. Underdiagnosis of non-Alzheimer’s disease subtypes remains prevalent. This study aimed to develop and evaluate LUMEN (Large Language Model for Understanding and Monitoring Elderly Neurocognition), a prototype conversational AI to automate caregiver-collateral data collection before clinical appointments. Our goals were to reduce clinician time per assessment, improve diagnostic accuracy across dementia subtypes, and standardise caregiver assessments.https://www.cambridge.org/core/product/identifier/S2056472425101853/type/journal_article
spellingShingle Song Ling Tang
Alexander Robertson
Huizhi Liang
John-Paul Taylor
Judith Harrison
LUMEN: Prototype Conversational AI to Streamline Dementia Assessments
BJPsych Open
title LUMEN: Prototype Conversational AI to Streamline Dementia Assessments
title_full LUMEN: Prototype Conversational AI to Streamline Dementia Assessments
title_fullStr LUMEN: Prototype Conversational AI to Streamline Dementia Assessments
title_full_unstemmed LUMEN: Prototype Conversational AI to Streamline Dementia Assessments
title_short LUMEN: Prototype Conversational AI to Streamline Dementia Assessments
title_sort lumen prototype conversational ai to streamline dementia assessments
url https://www.cambridge.org/core/product/identifier/S2056472425101853/type/journal_article
work_keys_str_mv AT songlingtang lumenprototypeconversationalaitostreamlinedementiaassessments
AT alexanderrobertson lumenprototypeconversationalaitostreamlinedementiaassessments
AT huizhiliang lumenprototypeconversationalaitostreamlinedementiaassessments
AT johnpaultaylor lumenprototypeconversationalaitostreamlinedementiaassessments
AT judithharrison lumenprototypeconversationalaitostreamlinedementiaassessments