ArticleJMIR medical education2026
Developing a Large Language Model-Based Feedback System for Case Report Writing in Rehabilitation Education: Tutorial.
Article in JMIR medical education, 2026. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Not yet cited in PubMed.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
0 citing papers in PubMed.
No citing paper in PubMed yet.
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
4 authors.
Funding
No grant is acknowledged in the PubMed record.
Abstract
backgroundNovice health care staff often write case reports during early clinical training. However, many institutions lack structured feedback systems because of time constraints and instructor shortages. Large language models, a form of artificial intelligence (AI), offer new opportunities to enhance educational feedback, yet their application in clinical training requires careful design to ensure pedagogically appropriate and ethically sound outputs.
objectiveThis tutorial provides a practical guide for educators without programming experience to develop an AI-based feedback system using 3 accessible tools: Dify (an AI workflow platform), Slack (a messaging app), and Google Apps Script. The system balances educational quality with operational efficiency while incorporating data privacy safeguards for clinical educational content.
methodsWe developed a feedback system comprising 4 AI chatbots with 2 distinct approaches: "loop-based" bots that promote clinical reasoning through iterative, comment-based feedback and "single-shot" bots for efficient proofreading and summarization tasks. The tutorial describes the system architecture; feedback design principles grounded in formative assessment theory; a step-by-step implementation guide; and data privacy safeguards, including a deidentification protocol and application programming interface-based data protection measures. To illustrate feasibility, we conducted a pilot implementation at a community care hospital from April to June 2024, involving 5 novice staff members and 5 instructors.
resultsA pilot implementation at a community care hospital demonstrated that the system was feasible to deploy and operate within routine clinical education workflows. Participant feedback indicated high usability and suggested that the iterative, comment-based feedback approach supported learner engagement while also identifying areas where feedback criteria required refinement to better match institutional educational goals.
conclusionsThis tutorial provides a reproducible framework for building a customized AI feedback system that combines comment-based iterative feedback with human-in-the-loop oversight and a multilayered data privacy framework. By following this guide, educators can implement an adaptive system tailored to their institutional context and clinical domain.
Indexed as
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.