Utility of large language models for creating clinical assessment items
GPT-assistance can create CPSA items of comparable quality with significantly less cost when compared to standard methods. Future studies could evaluate GPT's ability to create CPSA material in other areas of clinical practice, aiming to validate the generalisability of these findings.
Authors
- Amir H. Sam (ORCID: https://orcid.org/0000-0002-9599-9069)
- George Lam (ORCID: https://orcid.org/0000-0001-6011-0154)
- Celia Brown (ORCID: https://orcid.org/0000-0002-7526-0793)
- Anjali Amin (ORCID: https://orcid.org/0000-0002-0416-6505)
- Felicity Lalloo (ORCID: https://orcid.org/0000-0002-5698-4120)
- Arti Maini (ORCID: https://orcid.org/0000-0002-0951-5604)
- Anna Coulson (ORCID: https://orcid.org/0009-0007-3451-579X)
- Yusra Shammoon (ORCID: https://orcid.org/0000-0003-2630-4443)
Institutions
- Imperial College London (GB)
Publication Details
- Journal
- Medical Teacher
- Published
- 2024-08-26
- DOI
- https://doi.org/10.1080/0142159x.2024.2382860
- Citations
- 12
- Primary Topic
- Innovations in Medical Education
- Type
- article
- Field-Weighted Citation Impact
- 6.52