Ting, Patrick W. K. and Wolffsohn, James S. (2025). Artificial intelligence-driven patient history and symptoms combined with slit-lamp eye simulation for enhancing the clinical training of students. Clinical and Experimental Optometry , pp. 1-10.
Abstract
CLINICAL RELEVANCE: Communication between eye care practitioners is essential to optimise health care. Traditionally, actors have been used prior to real patient exposure, but this is expensive and much training is needed to ensure a consistent student experience and assessment. Artificial intelligence using ChatBots is shown to provide a high-quality student experience, and due to their portability and cost, it has the potential to revolutionise communication training. BACKGROUND: Augmented reality ocular examination simulations have been shown to be effective in teaching ophthalmology and optometry. With large language models, ChatGPT has been shown to provide effective role-play simulation. This study examined whether a combination of augmented reality and role-play simulation can enhance self-assessed competency of optometry students. It also assessed, the learning experience of students with role play by a human actor compared to different artificial intelligence chatbots. METHOD: Sixteen final-year optometry students with limited experience of computer simulation completed three role-plays with each of a SimConverse artificial intelligence, ChatGPT artificial intelligence, and an actor patient, in randomised order. In each session, the scenario included a history and symptoms, related augmented reality slit-lamp biomicroscopy examination (EyeSi) of the 'patient's' eyes, followed by the student communicating their findings and intended actions with the 'patient'. Students completed pre- and post-questionnaires to rank their learning experiences. RESULTS: There were significant improvements ( p < 0.05) over all aspects of clinical competence expectations ranked by students except 'prioritising key signs and symptoms' ( p = 0.66). There was no significant difference between the role-play proved by an actor and SimConverse. However, students rated the ChatGTP simulation as providing a significantly poorer experience ( p < 0.001). CONCLUSION: Combining patient role-play with augmented reality simulation significantly enhances how students feel about their clinical competencies. Role-play by an artificial intelligence 'patient' can provide an equivalent learning experience as that provided by an actor.
Publication DOI: | https://doi.org/10.1080/08164622.2025.2544809 |
---|---|
Divisions: | College of Health & Life Sciences > School of Optometry > Optometry & Vision Science Research Group (OVSRG) College of Health & Life Sciences > School of Optometry > Optometry College of Health & Life Sciences Aston University (General) |
Funding Information: | The current study is supported by the HLS Teaching Research Fund 2023–24 from the College of Health and Life Science, Aston University. |
Additional Information: | Copyright © 2025 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group. This is an Open Access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/), which permitsunrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. The terms on which this article has been published allowthe posting of the Accepted Manuscript in a repository by the author(s) or with their consent. |
Uncontrolled Keywords: | Artificial intelligence,clinical training,patience history and symptoms,slit-lamp eye simulation,students |
Publication ISSN: | 1444-0938 |
Last Modified: | 07 Oct 2025 07:21 |
Date Deposited: | 24 Sep 2025 09:00 |
Full Text Link: | |
Related URLs: |
https://www.tan ... 22.2025.2544809
(Publisher URL) http://www.scop ... tnerID=8YFLogxK (Scopus URL) |
PURE Output Type: | Article |
Published Date: | 2025-09-21 |
Published Online Date: | 2025-09-21 |
Accepted Date: | 2025-08-03 |
Authors: |
Ting, Patrick W. K.
Wolffsohn, James S. ( ![]() |