Utility of large language models for creating clinical assessment items.

Journal: Medical teacher

PMID: 39186054

Abstract

PURPOSE: To compare student performance, examiner perceptions and cost of GPT-assisted (generative pretrained transformer-assisted) clinical and professional skills assessment (CPSAs) items against items created using standard methods.

Authors

George Lam

Imperial College School of Medicine, Imperial College London, London, UK.
Yusra Shammoon

Imperial College School of Medicine, Imperial College London, London, UK.
Anna Coulson

Imperial College School of Medicine, Imperial College London, London, UK.
Felicity Lalloo

Imperial College School of Medicine, Imperial College London, London, UK.
Arti Maini

Imperial College School of Medicine, Imperial College London, London, UK.
Anjali Amin

Imperial College School of Medicine, Imperial College London, London, UK.
Celia Brown

Imperial College School of Medicine, Imperial College London, London, UK.
Amir H Sam

Imperial College School of Medicine, Imperial College London, London, UK.

Keywords

Clinical Competence Double-Blind Method Education, Medical, Undergraduate Educational Measurement Humans Language Large Language Models Prospective Studies Students, Medical Surveys and Questionnaires

External Resources

View on PubMed Access via DOI PubMed (39186054)

Utility of large language models for creating clinical assessment items.

Abstract

Authors

Keywords

External Resources

Popular Topics

Recent Journals