Maintenance Notice

Due to necessary scheduled maintenance, the JMIR Publications website will be unavailable from Wednesday, July 01, 2020 at 8:00 PM to 10:00 PM EST. We apologize in advance for any inconvenience this may cause you.

Who will be affected?

Accepted for/Published in: JMIR Medical Education

Date Submitted: Oct 28, 2023
Date Accepted: Mar 7, 2024

The final, peer-reviewed published version of this preprint can be found here:

Using ChatGPT in Psychiatry to Design Script Concordance Tests in Undergraduate Medical Education: Mixed Methods Study

Hudon A, Kiepura B, Pelletier M, Phan V

Using ChatGPT in Psychiatry to Design Script Concordance Tests in Undergraduate Medical Education: Mixed Methods Study

JMIR Med Educ 2024;10:e54067

DOI: 10.2196/54067

PMID: 38596832

PMCID: 11007379

Using ChatGPT in Psychiatry to design script-concordance tests in undergraduate medical education: a mixed-method study.

  • Alexandre Hudon; 
  • Barnabé Kiepura; 
  • Myriam Pelletier; 
  • Véronique Phan

ABSTRACT

Background:

Undergraduate medical studies represent a panoply of learning opportunities served in the form of various teaching-learning modalities for medical learners. A clinical scenario is frequently employed as a modality, followed by multiple choice and open-ended questions among other learning and teaching methods. As such, script-concordance tests (SCT) can be used to promote higher level of clinical reasoning. Recent technological developments have made generative artificial intelligence-based systems like ChatGPT available to assist clinician-educators in creating instructional materials.

Objective:

The main objective of this project is to explore how SCT generated by ChatGPT compared to SCT produced by clinical experts on three major elements: the scenario (stem), the clinical questions and the expert opinion.

Methods:

This mixed-method study evaluated three ChatGPT-generated SCT with three expert-created SCT using a predefined framework. Clinician-teachers as well as resident doctors in psychiatry involved in the undergraduate medical education in the area of Quebec (Canada) evaluated online the six SCT over three criteria: scenario, questions and expert opinion. They were also asked to describe the strengths and weaknesses of the SCT.

Results:

A total of 102 respondents assessed the SCT. Findings demonstrated no significant distinctions between the two SCT types concerning scenarios (P=0.68, clinical questions (P=0.27), and expert opinions, as interpretated by the respondents. Indeed, respondents struggled to differentiate between ChatGPT-generated and expert-generated SCTs. ChatGPT showcased promise in expediting SCT design, aligning well with DSM-5 criteria, albeit with a tendency towards caricatured scenarios and simplistic content.

Conclusions:

This study is the first to concentrate on the design of SCT supported by artificial intelligence in a period where medicine is changing swiftly and where technologies generated from AI are expanding much faster. This study suggests that ChatGPT can be a valuable tool in creating educational materials and further validation is essential to ensure educational efficacy and accuracy.


 Citation

Please cite as:

Hudon A, Kiepura B, Pelletier M, Phan V

Using ChatGPT in Psychiatry to Design Script Concordance Tests in Undergraduate Medical Education: Mixed Methods Study

JMIR Med Educ 2024;10:e54067

DOI: 10.2196/54067

PMID: 38596832

PMCID: 11007379

Download PDF


Request queued. Please wait while the file is being generated. It may take some time.

© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.