Maintenance Notice

Due to necessary scheduled maintenance, the JMIR Publications website will be unavailable from Wednesday, July 01, 2020 at 8:00 PM to 10:00 PM EST. We apologize in advance for any inconvenience this may cause you.

Who will be affected?

Currently submitted to: JMIR Medical Education

Date Submitted: Jun 9, 2026
Open Peer Review Period: Jun 10, 2026 - Aug 5, 2026
(currently open for review)

Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.

Mapping Dementia Care Training Priorities through Multi-Source Topic Modeling: A Time-Course Latent Dirichlet Allocation Study

  • Xueqi Liu Liu; 
  • Bei Wu; 
  • An Huang; 
  • An Gu; 
  • Chuwen Dou; 
  • Jianlin Lou; 
  • Mei Chen; 
  • Hongchang Zhou; 
  • Lina Wang

ABSTRACT

Background:

Dementia care training plays an important role in improving care quality, yet its content is often fragmented and unevenly structured. Little is known about how training priorities have evolved over time, limiting efforts to keep curricula aligned with changing care needs.

Objective:

To identify the core thematic domains of dementia care training and examine their temporal evolution to inform curriculum review and development.

Methods:

A corpus of 261 texts, including academic literature, policy documents, and training materials, was analyzed using Latent Dirichlet Allocation (LDA) and expert-informed manual interpretation. Topic intensity was examined across five time periods from 2005 to 2025 using temporal analysis.

Results:

Five core topics and 15 subtopics were identified: (1) daily prevention and intervention; (2) palliative care and symptom management; (3) communication skills and caregiver role; (4) workflow and team-based training; and (5) individualized care and behavioral support. Temporal patterns suggested an earlier emphasis on communication- and team-related training, followed by increased prominence of palliative care, and more recently, individualized care approaches.

Conclusions:

This study provides a data-informed overview of dementia care training content and its temporal development across multiple source types. The findings suggest that training priorities have shifted over time in ways that are consistent with changing care demands, policy attention, and emerging technologies. These results may support more adaptive and context-sensitive approaches to curriculum review and training design. Future research should expand the geographic and linguistic scope of the corpus and further examine how thematic priorities identified in text are translated into real-world training practice.


 Citation

Please cite as:

Liu XL, Wu B, Huang A, Gu A, Dou C, Lou J, Chen M, Zhou H, Wang L

Mapping Dementia Care Training Priorities through Multi-Source Topic Modeling: A Time-Course Latent Dirichlet Allocation Study

JMIR Preprints. 09/06/2026:104180

DOI: 10.2196/preprints.104180

URL: https://preprints.jmir.org/preprint/104180

Download PDF


Request queued. Please wait while the file is being generated. It may take some time.

© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.