Artificial intelligence-assisted feedback in pharmacology education: a pilot evaluation of a custom generative model
Edward Stephenson, Katie Morrigan, Ayesha Irfan, Kate Bascombe, Michael Okorie · 2026
Read Artificial intelligence-assisted feedback in pharmacology education: a pilot evaluation of a custom generative model by Edward Stephenson, Katie Morrigan, Ayesha Irfan, Kate Bascombe, Michael Okorie (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13435439.txt.
Description
Edward Stephenson's team piloted AI feedback in 2026 for pharmacology short-answer work in a UK physician associate masters course. Timely, personal feedback is prized in medical training but costly when staff mark by hand, and proof on AI feedback quality was thin. Twenty students answered four formative questions each, a custom GPT model marked them against a rubric and references, and staff checked every output before release.
AI marking took about 34 seconds per quiz against 508 seconds by staff, and six in ten feedback files needed no change, though four needed major fixes. Just over half the students responded to the survey, with views mixed in ways the paper details. Educators get a realistic pilot: big time savings, real error risk, and a clear case for keeping staff in the loop.
Catalog record
| CREATOR | Edward Stephenson, Katie Morrigan, Ayesha Irfan, Kate Bascombe, Michael Okorie |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 30 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |