Real-World Insights Into Dementia Diagnosis Trajectory and Clinical Practice Patterns Unveiled by Natural Language Processing: Development and Usability Study

Abstract BackgroundUnderstanding the dementia disease trajectory and clinical practice patterns in outpatient settings is vital for effective management. Knowledge about the path from initial memory loss complaints to dementia diagnosis remains limited. ObjectiveTh...

Full description

Saved in:
Bibliographic Details
Main Authors: Hunki Paek, Richard H Fortinsky, Kyeryoung Lee, Liang-Chin Huang, Yazeed S Maghaydah, George A Kuchel, Xiaoyan Wang
Format: Article
Language:English
Published: JMIR Publications 2025-02-01
Series:JMIR Aging
Online Access:https://aging.jmir.org/2025/1/e65221
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850027082881433600
author Hunki Paek
Richard H Fortinsky
Kyeryoung Lee
Liang-Chin Huang
Yazeed S Maghaydah
George A Kuchel
Xiaoyan Wang
author_facet Hunki Paek
Richard H Fortinsky
Kyeryoung Lee
Liang-Chin Huang
Yazeed S Maghaydah
George A Kuchel
Xiaoyan Wang
author_sort Hunki Paek
collection DOAJ
description Abstract BackgroundUnderstanding the dementia disease trajectory and clinical practice patterns in outpatient settings is vital for effective management. Knowledge about the path from initial memory loss complaints to dementia diagnosis remains limited. ObjectiveThis study aims to (1) determine the time intervals between initial memory loss complaints and dementia diagnosis in outpatient care, (2) assess the proportion of patients receiving cognition-enhancing medication prior to dementia diagnosis, and (3) identify patient and provider characteristics that influence the time between memory complaints and diagnosis and the prescription of cognition-enhancing medication. MethodsThis retrospective cohort study used a large outpatient electronic health record (EHR) database from the University of Connecticut Health Center, covering 2010‐2018, with a cohort of 581 outpatients. We used a customized deep learning–based natural language processing (NLP) pipeline to extract clinical information from EHR data, focusing on cognition-related symptoms, primary caregiver relation, and medication usage. We applied descriptive statistics, linear, and logistic regression for analysis. ResultsThe NLP pipeline showed precision, recall, and F1 ConclusionsOur NLP-guided analysis provided insights into the clinical pathways from memory complaints to dementia diagnosis and medication practices, which can enhance patient care and decision-making in outpatient settings.
format Article
id doaj-art-0d8e75fa9c7d4626b72eb082b231a1f9
institution DOAJ
issn 2561-7605
language English
publishDate 2025-02-01
publisher JMIR Publications
record_format Article
series JMIR Aging
spelling doaj-art-0d8e75fa9c7d4626b72eb082b231a1f92025-08-20T03:00:21ZengJMIR PublicationsJMIR Aging2561-76052025-02-018e65221e6522110.2196/65221Real-World Insights Into Dementia Diagnosis Trajectory and Clinical Practice Patterns Unveiled by Natural Language Processing: Development and Usability StudyHunki Paekhttp://orcid.org/0009-0000-9916-5654Richard H Fortinskyhttp://orcid.org/0000-0002-2013-719XKyeryoung Leehttp://orcid.org/0000-0002-6937-9931Liang-Chin Huanghttp://orcid.org/0000-0001-5661-8940Yazeed S Maghaydahhttp://orcid.org/0000-0002-0842-3265George A Kuchelhttp://orcid.org/0000-0001-8387-7040Xiaoyan Wanghttp://orcid.org/0000-0002-4193-4120 Abstract BackgroundUnderstanding the dementia disease trajectory and clinical practice patterns in outpatient settings is vital for effective management. Knowledge about the path from initial memory loss complaints to dementia diagnosis remains limited. ObjectiveThis study aims to (1) determine the time intervals between initial memory loss complaints and dementia diagnosis in outpatient care, (2) assess the proportion of patients receiving cognition-enhancing medication prior to dementia diagnosis, and (3) identify patient and provider characteristics that influence the time between memory complaints and diagnosis and the prescription of cognition-enhancing medication. MethodsThis retrospective cohort study used a large outpatient electronic health record (EHR) database from the University of Connecticut Health Center, covering 2010‐2018, with a cohort of 581 outpatients. We used a customized deep learning–based natural language processing (NLP) pipeline to extract clinical information from EHR data, focusing on cognition-related symptoms, primary caregiver relation, and medication usage. We applied descriptive statistics, linear, and logistic regression for analysis. ResultsThe NLP pipeline showed precision, recall, and F1 ConclusionsOur NLP-guided analysis provided insights into the clinical pathways from memory complaints to dementia diagnosis and medication practices, which can enhance patient care and decision-making in outpatient settings.https://aging.jmir.org/2025/1/e65221
spellingShingle Hunki Paek
Richard H Fortinsky
Kyeryoung Lee
Liang-Chin Huang
Yazeed S Maghaydah
George A Kuchel
Xiaoyan Wang
Real-World Insights Into Dementia Diagnosis Trajectory and Clinical Practice Patterns Unveiled by Natural Language Processing: Development and Usability Study
JMIR Aging
title Real-World Insights Into Dementia Diagnosis Trajectory and Clinical Practice Patterns Unveiled by Natural Language Processing: Development and Usability Study
title_full Real-World Insights Into Dementia Diagnosis Trajectory and Clinical Practice Patterns Unveiled by Natural Language Processing: Development and Usability Study
title_fullStr Real-World Insights Into Dementia Diagnosis Trajectory and Clinical Practice Patterns Unveiled by Natural Language Processing: Development and Usability Study
title_full_unstemmed Real-World Insights Into Dementia Diagnosis Trajectory and Clinical Practice Patterns Unveiled by Natural Language Processing: Development and Usability Study
title_short Real-World Insights Into Dementia Diagnosis Trajectory and Clinical Practice Patterns Unveiled by Natural Language Processing: Development and Usability Study
title_sort real world insights into dementia diagnosis trajectory and clinical practice patterns unveiled by natural language processing development and usability study
url https://aging.jmir.org/2025/1/e65221
work_keys_str_mv AT hunkipaek realworldinsightsintodementiadiagnosistrajectoryandclinicalpracticepatternsunveiledbynaturallanguageprocessingdevelopmentandusabilitystudy
AT richardhfortinsky realworldinsightsintodementiadiagnosistrajectoryandclinicalpracticepatternsunveiledbynaturallanguageprocessingdevelopmentandusabilitystudy
AT kyeryounglee realworldinsightsintodementiadiagnosistrajectoryandclinicalpracticepatternsunveiledbynaturallanguageprocessingdevelopmentandusabilitystudy
AT liangchinhuang realworldinsightsintodementiadiagnosistrajectoryandclinicalpracticepatternsunveiledbynaturallanguageprocessingdevelopmentandusabilitystudy
AT yazeedsmaghaydah realworldinsightsintodementiadiagnosistrajectoryandclinicalpracticepatternsunveiledbynaturallanguageprocessingdevelopmentandusabilitystudy
AT georgeakuchel realworldinsightsintodementiadiagnosistrajectoryandclinicalpracticepatternsunveiledbynaturallanguageprocessingdevelopmentandusabilitystudy
AT xiaoyanwang realworldinsightsintodementiadiagnosistrajectoryandclinicalpracticepatternsunveiledbynaturallanguageprocessingdevelopmentandusabilitystudy