Artificial intelligence-assisted feedback in pharmacology education: a pilot evaluation of a custom generative model.
Source check: Source checked. Not independent scientific confirmation.
Finding: Primary BMC Medical Education Methods/Results prospectively pilot a custom GPT-4-family model for pharmacology SAQ feedback. Among 20 students/80 answers, 12 outputs needed no edits, eight required amendments (four major); AI cut marking time 508 to 34 seconds per quiz. Human moderation was essential.
Technology: Custom GPT using a rubric and curated pharmacology references generates structured feedback; faculty review/moderation was part of intervention.
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
- AI contribution
- Custom GPT using a rubric and curated pharmacology references generates structured feedback; faculty review/moderation was part of intervention.
- Test and result
- Prospective pilot reports generation time, faculty correction rates, blinded scoring of only five submissions, and student views from 11 respondents.
- Limitation / still unknown
- Faculty moderation and a very small blinded comparison provide only pilot-level accuracy evidence; major safety-relevant omissions occurred, no learning outcomes assessed.
Evidence sources and annotation context
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
Evidence sources: https://link.springer.com/article/10.1186/s12909-026-09300-w · https://pubmed.ncbi.nlm.nih.gov/42218453/
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.
Review date: 22 Nov 2026. Review scope: Primary result-bearing material for the stated method, result and evaluation, with bibliographic version information..
No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.
Editorial assessment: Impact 2/5 · Validation 2/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.