Actionable companion · Assessment and evidence of learning

From evidence to district action: Artificial Intelligence Enhanced Content Review for Curriculum Evaluation in Nursing Education: A Pilot Study

AI-assisted editorial implementation guide. The district actions are proposed applications, not findings or recommendations attributed to the original authors. No additional peer review is asserted.

Evidence and context

Health-professions education context: test transfer to K–12 rather than assuming it.

Original authors’ abstract, reproduced under the linked source license:

Background: Curricular evaluation is core to nursing education and can benefit from artificial intelligence-based automation. Large language models offer new opportunities for scalable, structured document analysis. Purpose: We developed a rubric to identify elements related to health equity, including whether the content addresses vulnerable groups, social factors in health, and clinical applications. Methods: A chatbot using retrieval-augmented generation (RAG) was configured with structured rubric-based instructions. The reliability of chatbot ratings of 9 lecture slide sets from one nurse-midwifery course was compared to ratings from 3 faculty reviewers. Results: The chatbot achieved reliability in repeated ratings of 84% to 91% across assessed topics. Chatbot alignment with faculty raters across topics was more variable and ranged from 56% to 89% agreement. Conclusions: An RAG-based large language model system demonstrates promising reliability for automated curriculum screening. This tool can be used to assist, but not replace, human insights and summative judgments.

A 90-day district pilot

1. Days 1–15 · Appraise. Have the curriculum lead and a teacher read the methods and limitations. Record the study design, sample, comparator, outcomes and evidence gaps. Define a local question that the study can help inform.
2. Days 16–30 · Design. Redesign one low-stakes assessment: require a first attempt, an AI-assisted revision, a source-check log and a short oral explanation. Use the same rubric for the comparison task. Name an accountable owner and set the baseline, success threshold and budget before implementation.
3. Days 31–60 · Test. Start with a small voluntary cohort, preserve an accessible non-AI route and require teacher review. Use synthetic or de-identified examples; approve data handling and tool terms through district processes.
4. Days 61–90 · Decide. Blind-score reasoning, factual accuracy and unaided transfer on a fresh task. Record suspected misconduct separately from demonstrated evidence. Compare with baseline, document uncertainty and stop or revise if learning worsens, access is unequal or critical errors persist.

The board decision brief

Report the learning problem, evidence quality, participating population, total cost including review time, measured benefit, errors, access differences and remaining uncertainties. Make a dated recommendation to stop, revise or expand. A positive perception survey alone does not establish learning improvement.

Attribution and reuse

Regina G. Russell; Md. Mashiur Rahman Khan; Lia Nagge; Hannah McGrew; Kendra Faucett; Xingchen Wei; Mary S. Dietrich; Julia Phillippi. Artificial Intelligence Enhanced Content Review for Curriculum Evaluation in Nursing Education: A Pilot Study. Nurse Educator (2026-07-09). https://doi.org/10.1097/nne.0000000000002243

Companion prepared 2026-10-30. Original authorship and DOI are preserved. The abstract is an attributed source extract; the implementation plan is new AI-assisted editorial material, offered under the same CC BY 4.0 license. This guide has not undergone independent peer review.