EUVIMEDObjevte EUVIMED
Open access

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

Hunki Paek iD, Richard H Fortinsky iD, Kyeryoung Lee iD, Liang-Chin Huang iD, Yazeed S Maghaydah iD, George A Kuchel iD, Xiaoyan Wang iD

JMIR Aging · 2025

DOI: 10.2196/65221 ↗

At a glance

Journal article in JMIR Aging, 2025. Written by Hunki Paek and 6 co-authors. Institution: IMO Health, Rosemont, IL, United States. Major MEDLINE topics: Dementia, Natural Language Processing, Practice Patterns, Physicians', Memory Disorders. Cited 1 times so far (Crossref); 51 references. The full text is freely available in PubMed Central. Funded by: NIA NIH HHS.

AbstraktSubjectsBibliografické údajeCiteRelated studies

Abstract (original language)

Background

Understanding 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.

Objective

This 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.

Methods

This 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.

Results

The NLP pipeline showed precision, recall, and F 1 -scores of 0.97, 0.93, and 0.95, respectively. The median time from the first memory loss complaint to dementia diagnosis was 342 (IQR 200-675) days. Factors such as the location of initial complaints and diagnosis and primary caregiver relationships significantly affected this interval. Around 25.1% (146/581) of patients were prescribed cognition-enhancing medication before diagnosis, with the number of complaints influencing medication usage.

Conclusions

Our 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.

Subjects

MeSH terms (MEDLINE)

DementiaNatural Language ProcessingPractice Patterns, Physicians'Memory DisordersHumansDisease ProgressionRetrospective StudiesElectronic Health RecordsMaleFemaleAgedAged, 80 and over

Author keywords

Alzheimer diseaseEHRNLPagingcognitivecohortdeep learningdementiadiagnosisdiagnosticelectronic health recordsgeriatricmachine learningmemorymemory loss

Authors and institutions

  • IMO Health, Rosemont, IL, United States.
  • UConn Center on Aging, University of Connecticut School of Medicine, Farmington, CT, United States.
  • Center for Quantitative Medicine, University of Connecticut School of Medicine, 195 Farmington Ave, Farmington, CT, 06032, United States, 1 201-282-8098.
  • Department of Health Policy and Management, Tulane University, New Orleans, LA, United States.

ORCID profiles: Hunki Paek, Richard H Fortinsky, Kyeryoung Lee, Liang-Chin Huang, Yazeed S Maghaydah, George A Kuchel, Xiaoyan Wang

Funding

  • NIA NIH HHS

Cite

APA

Paek, H., Fortinsky, R. H., Lee, K., Huang, L. C., Maghaydah, Y. S., Kuchel, G. A., & Wang, X. (2025). Real-World Insights Into Dementia Diagnosis Trajectory and Clinical Practice Patterns Unveiled by Natural Language Processing: Development and Usability Study. JMIR Aging. https://doi.org/10.2196/65221

Vancouver

Paek H, Fortinsky RH, Lee K, Huang LC, Maghaydah YS, Kuchel GA, et al. Real-World Insights Into Dementia Diagnosis Trajectory and Clinical Practice Patterns Unveiled by Natural Language Processing: Development and Usability Study. JMIR Aging. 2025. doi:10.2196/65221

BibTeX
@article{Paek2025,
  author = {Paek, Hunki and Fortinsky, Richard H and Lee, Kyeryoung and Huang, Liang-Chin and Maghaydah, Yazeed S and Kuchel, George A and Wang, Xiaoyan},
  title = {Real-World Insights Into Dementia Diagnosis Trajectory and Clinical Practice Patterns Unveiled by Natural Language Processing: Development and Usability Study},
  journal = {JMIR Aging},
  year = {2025},
  doi = {10.2196/65221}
}
Start for free →