Evaluating a zero-shot GenAI assistant for clinical record writing in nursing education
Bibliographic record
Abstract
Objective: This study pilot-tested a zero-shot prompting approach for generating pedagogically appropriate AI feedback to support nursing students’ reflective record writing. A generative AI system was developed using GPT-4o, with prompts carefully designed to align with ethical, instructional, and contextual principles relevant to clinical practicum education. Following the ADDIE framework, this evaluation examined the feasibility and instructional applicability of the AI-generated feedback rather than aiming to establish generalizable effects. Methods: Three nursing faculty members independently reviewed 126 AI-generated responses using a 5-point scale based on clarity, relevance, and educational appropriateness. Items scoring less than 5 were revised, and a second round of evaluation was conducted. Results: The proportion of responses rated 5 increased from 69% to 96% after prompt refinement, confirming that even minor adjustments—such as clarifying vague instructions or reinforcing ethical boundaries—had a measurable impact. Inter-rater reliability was moderate, reflecting diverse faculty perspectives—a feature aligned with the contextual complexity of nursing education. The conservative scoring approach, in which the lowest score was adopted per item, ensured that potential pedagogical risks were not overlooked. Conclusions: These findings suggest that zero-shot prompting offers a practical and scalable method for aligning generative AI systems with educational goals, even without training data or programming expertise. Rather than positioning AI as a replacement for instructors, this study frames GenAI as a formative support tool shaped by educator input. The study is limited by its use of simulated student inputs and a small, single-institution faculty sample; therefore, future work should assess implementation with real students to examine usability, personalization, and effectiveness in authentic practicum environments.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.050 | 0.153 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.002 | 0.003 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.004 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".