Integrating Large Language Models Into Patient Health Education: Interview Study Among Nurses

Background: Large language models (LLMs) have shown potential to support patient education, improve information accessibility, and assist with repetitive clinical communication tasks. However, the clinical integration of LLMs depends not only on technological capabilities but also on how these tools fit within existing health care workflows. Existing studies have largely focused on technical performance of LLMs or the experiences of physicians and patients, and little is known about how frontline nurses, who play a central role in patient education, experience LLM-supported education workflows in clinical practice settings. Objective: This study aimed to explore frontline nurses' experiences with an LLM-assisted patient education workflow, including perceived benefits, changes, challenges, and considerations for clinical practice. Methods: Semistructured interviews were conducted with 16 frontline hematological nurses between December 2025 and March 2026 at the Institute of Hematology and Blood Diseases Hospital, Chinese Academy of Medical Sciences to explore their experiences. Data were analyzed using an inductive codebook thematic analysis, with codes and themes iteratively reviewed and refined through researcher discussions. Results: Nurses' experiences were characterized by 3 interconnected tensions. First, nurses perceived a balance between efficiency gains and information safety concerns, as the LLM-assisted workflow supported more efficient and standardized information delivery while requiring additional oversight. Second, nurses perceived changes in their roles and responsibilities, accompanied by increased demands for professional knowledge and competencies. Third, nurses perceived potential patient benefits of LLM use particularly in facilitating access to specialized health information, while identifying barriers related to limited health literacy and limited familiarity with LLM-based tools. Conclusions: From nurses' perspectives, LLM use was perceived to support more efficient delivery of patient health information while also requiring attention to information safety, professional responsibility, and patient-related challenges. These findings highlight that nurses' roles remain important in supporting the safe and appropriate use of LLM-assisted education. Future research and implementation efforts should explore workflow-oriented design strategies for integrating LLMs into clinical nursing practice while considering nurse oversight, support clinical workflow adaptation, and address patient needs to support safe and appropriate use.

Authors

Institutions

Publication Details

Journal
Journal of Medical Internet Research
Published
2026-11-12
DOI
https://doi.org/10.2196/102846
Primary Topic
Artificial Intelligence in Healthcare and Education
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Integrating Large Language Models Into Patient Health Education: Interview Study Among Nurses

Huijuan Zhang, Erlie Jiang, Wenjun Xie, Qianqian Zhang et al.
Journal of Medical Internet Research
Artificial Intelligence in Healthcare and Education
article

Integrating Large Language Models Into Patient Health Education: Interview Study Among Nurses

Huijuan Zhang, Erlie Jiang, Wenjun Xie, Qianqian Zhang, Qiyang Hong, Yiming Gao, Dan Xu, Jinying Zhao, Zuxing Kan, Zhen Song, Sulin Xu, Peixing Wan, Yujie Zhao, Yuebing Du, Xiaoqing Tang, Guiying Liu
article en

Abstract

Background: Large language models (LLMs) have shown potential to support patient education, improve information accessibility, and assist with repetitive clinical communication tasks. However, the clinical integration of LLMs depends not only on technological capabilities but also on how these tools fit within existing health care workflows. Existing studies have largely focused on technical performance of LLMs or the experiences of physicians and patients, and little is known about how frontline nurses, who play a central role in patient education, experience LLM-supported education workflows in clinical practice settings. Objective: This study aimed to explore frontline nurses' experiences with an LLM-assisted patient education workflow, including perceived benefits, changes, challenges, and considerations for clinical practice. Methods: Semistructured interviews were conducted with 16 frontline hematological nurses between December 2025 and March 2026 at the Institute of Hematology and Blood Diseases Hospital, Chinese Academy of Medical Sciences to explore their experiences. Data were analyzed using an inductive codebook thematic analysis, with codes and themes iteratively reviewed and refined through researcher discussions. Results: Nurses' experiences were characterized by 3 interconnected tensions. First, nurses perceived a balance between efficiency gains and information safety concerns, as the LLM-assisted workflow supported more efficient and standardized information delivery while requiring additional oversight. Second, nurses perceived changes in their roles and responsibilities, accompanied by increased demands for professional knowledge and competencies. Third, nurses perceived potential patient benefits of LLM use particularly in facilitating access to specialized health information, while identifying barriers related to limited health literacy and limited familiarity with LLM-based tools. Conclusions: From nurses' perspectives, LLM use was perceived to support more efficient delivery of patient health information while also requiring attention to information safety, professional responsibility, and patient-related challenges. These findings highlight that nurses' roles remain important in supporting the safe and appropriate use of LLM-assisted education. Future research and implementation efforts should explore workflow-oriented design strategies for integrating LLMs into clinical nursing practice while considering nurse oversight, support clinical workflow adaptation, and address patient needs to support safe and appropriate use.

Journal of Medical Internet ResearchVol. 28
Tianjin University of Traditional Chinese Medicine (CN), Chinese Academy of Medical Sciences & Peking Union Medical College (CN), Peking University (CN), Institute of Hematology & Blood Diseases Hospital (CN), Institute of Basic Medical Sciences of the Chinese Academy of Medical Sciences (CN)
Good health and well-being, Quality education
Artificial Intelligence in Healthcare and Education
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon