37/100

Emerging evidence

Trace: a gain and a problemPublished recordHealthThe Trace

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

Truvace record
TRV-2026-2888raw data (JSON)
Version
v1Published
First published
Evidence type
Interviews or qualitative study
Sources
1 sourcePeer-reviewed
sha256
e3f1a3fff9fa…check it

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.

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

Cite this record

v1

Truvace Impact Record TRV-2026-2888, v1: “Integrating Large Language Models Into Patient Health Education: Interview Study Among Nurses.” Truvace, 2026-11-13. /record/TRV-2026-2888 (accessed on the day you copy it). sha256 e3f1a3fff9fad886…

Change history

1 version

Every change made to this record since it was first published, and why. Nothing has changed since it went up.

  1. Publishedv1e3f1a3fff9fa…

    Certified into the record

Check this record hasn’t been altered

Check this record hasn’t been altered
How to check it yourself, without trusting this page

Download any version from /api/record/TRV-2026-2888 and hash its canonical field yourself, for example with shasum -a 256. You should get its content_hash. Each version’s text also ends with prev:and the hash of the version before it (version 1 points to 64 zeros). If anyone had changed a single character of any version after it was saved, those hashes wouldn’t line up.