37/100

Emerging evidence

Cite
More
EmailLinkedInX

Nurses in a 16-person interview study said AI sped up patient education but needed checking

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

Evidence type
Interviews or qualitative study
Sample
n = 16
Sources
1 sourcePeer-reviewed
Published
2 min read

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

Researchers interviewed 16 frontline hematology nurses at the Institute of Hematology and Blood Diseases Hospital, Chinese Academy of Medical Sciences, between December 2025 and March 2026. The nurses had used an AI chatbot-assisted workflow to educate patients, and the interviews explored what changed in their work.

Read the study 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 pla…

50Gain side

How the two sides scoreClose call

51Problem side

The gain

In interviews with 16 hematology nurses at a Chinese Academy of Medical Sciences hospital, nurses said an AI chatbot-assisted workflow made patient education delivery more efficient and standardized.

The problem

In interviews with 16 hematology nurses at a Chinese Academy of Medical Sciences hospital, nurses said the AI chatbot-assisted education workflow raised information safety concerns and required additional oversight from them.

A fixed formula sets both scores from the evidence and its sources. Reader votes don’t move them.

What the scores mean

G is the gain side, out of 100. It goes up when the gain is specific, when it measurably helped people and when the sources behind it are strong.

P is the problem side, out of 100. It goes up when the problem is specific, when it measurably hurt people and when the sources behind it are strong.

In brief

Nurses described efficiency gains alongside information safety concerns. They said the workflow delivered information more efficiently and in a more standardized way, but it required them to check what the tool produced.

Nurses also said their roles and responsibilities shifted, with greater demands for professional knowledge. They saw potential patient benefits in access to specialized health information, but pointed to patients' limited health literacy and unfamiliarity with such tools as barriers.

Main points

  1. The study used semistructured interviews with 16 frontline hematology nurses at one hospital in China.
  2. Interviews took place between December 2025 and March 2026 and were analyzed with inductive codebook thematic analysis.
  3. Nurses described a tension between efficiency gains and information safety concerns.
  4. The workflow supported more efficient and standardized delivery of patient information but required additional oversight.
  5. Nurses perceived changes in their roles, with increased demands for professional knowledge and competencies.
  6. Nurses saw possible patient benefits in access to specialized information, but cited limited health literacy and limited familiarity with LLM tools as barriers.

The full story

The work addresses a gap: earlier studies mostly looked at the technical performance of language models or at physicians' and patients' experiences, while little was known about nurses, who play a central role in patient education.

Results were organized around three interconnected tensions: efficiency versus information safety, changing roles and responsibilities, and patient benefits versus patient-related barriers. Nurses reported these as perceptions, not measured outcomes.

The authors conclude that nurses' roles remain important in supporting safe and appropriate use of LLM-assisted education. They call for workflow-oriented design that builds in nurse oversight, supports workflow adaptation and addresses patient needs.

What this doesn’t fix

The findings come from interviews with 16 nurses at a single hematology hospital and reflect their perceptions, not measured patient or efficiency outcomes.

Sources

1 on file
  1. Peer-reviewed2026-11-12

Talk it over

Three questions to start on, two more if you have time
Hematology nurses said the chatbot workflow made patient education more efficient and standardized, but they had to check what it produced. How would you weigh that efficiency against the extra oversight?

Start with a question

Nurses in a 16-person interview study said AI sped up patient education but needed checkinghttps://truvace.com/item/integrating-large-language-models-into-patient-health-education-interview-study-

  1. Hematology nurses said the chatbot workflow made patient education more efficient and standardized, but they had to check what it produced. How would you weigh that efficiency against the extra oversight?

    Answer in the thread
  2. The 16 nurses were interviewed at one hospital, and they described perceptions rather than measured outcomes. Which measurements would you want to see to test what they said about efficiency and information safety?

    Answer in the thread
  3. Nurses pointed to patients' limited health literacy and unfamiliarity with such tools as barriers. If you were a patient receiving this education, what would help you decide whether to trust or question what the chatbot produced?

    Answer in the thread
If you have more time
  • Nurses said their roles shifted, with greater demands for professional knowledge. What training or support would you ask a hospital to provide, and who should decide?

    Answer in the thread
  • The study interviewed nurses only, not patients or physicians. Which of their views would you collect first, and what would you ask them?

    Answer in the thread

What readers say