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?

Accepted for/Published in: Journal of Medical Internet Research

Date Submitted: Jul 8, 2025
Date Accepted: Oct 23, 2025

The final, peer-reviewed published version of this preprint can be found here:

Nurses’ Perspectives on Evidence Dissemination Barriers and Large Language Model–Based Support: Qualitative Study Using Focus Groups and Nominal Group Technique

Ruan J, Tang Y, Wei Z, Xing W, Hu Y

Nurses’ Perspectives on Evidence Dissemination Barriers and Large Language Model–Based Support: Qualitative Study Using Focus Groups and Nominal Group Technique

J Med Internet Res 2025;27:e80289

DOI: 10.2196/80289

PMID: 41202291

PMCID: 12639338

Nurses’ Perspectives on Evidence Dissemination Barriers and Large Language Model-Based Support: A Qualitative Study Using Focus Groups and the Nominal Group Technique

  • Junyi Ruan; 
  • Yimin Tang; 
  • Zhongyu Wei; 
  • Weijie Xing; 
  • Yan Hu

ABSTRACT

Background:

Current evidence dissemination methods fall short of meeting clinical nurses’ needs, hindering the implementation of evidence-based nursing practice. Although nurses have begun using LLMs to access evidence, existing tools are insufficient for supporting evidence dissemination and are not tailored to nursing practice. It is essential to develop AI tools tailored to nurses’ needs and preferences to enhance evidence dissemination.

Objective:

The objective of this study is to identify the challenges and barriers clinical nurses face in disseminating evidence, to examine their perspectives on the use of existing LLMs to support evidence dissemination, and to explore their needs and preferences regarding a large language model–based nursing evidence question-answering system.

Methods:

This qualitative study employed a combined method of focus group discussions and the nominal group technique. A total of 22 clinical nurses were recruited, all of whom participated in the entire study. Two focus groups were conducted to identify the challenges and barriers nurses face in disseminating evidence and examine their perspectives on the use of existing LLMs to support evidence dissemination. Following the focus group, the nominal group technique was used to explore nurses’ needs and preferences for the system to be developed. All sessions were held online to overcome geographical constraints and busy schedules. The study was conducted between November 2024 and April 2025.

Results:

The focus group yielded three main themes and seven sub-themes. Three main themes were identified: (1) pathways for evidence dissemination among nurses, (2) barriers that hinder the effective dissemination of evidence, and (3) advantages and limitations of using LLMs to support evidence dissemination. The NGT sessions ultimately identified nine desired functions. After prioritization, the top three ranked functions were evidence-based high-quality Q&A, evidence source provision, and personalized evidence recommendation.

Conclusions:

The current evidence dissemination process faces multiple barriers. LLMs hold promise as innovative tools to support evidence dissemination, but require further refinement. Clinical nurses have identified key functional needs, guiding the development of LLMs specifically tailored to clinical nursing practice.


 Citation

Please cite as:

Ruan J, Tang Y, Wei Z, Xing W, Hu Y

Nurses’ Perspectives on Evidence Dissemination Barriers and Large Language Model–Based Support: Qualitative Study Using Focus Groups and Nominal Group Technique

J Med Internet Res 2025;27:e80289

DOI: 10.2196/80289

PMID: 41202291

PMCID: 12639338

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.