Abstract
Objective structured clinical examinations (OSCEs) are a standardized examination for assessing medical and dental students. OSCEs involve a medical interview task in which examinees are evaluated based on their interactions with standardized patients (SPs), who are trained to respond according to specific clinical scenarios. However, preparing well-trained SPs incurs substantial costs. To overcome this limitation, the use of virtual SPs employing artificial intelligence has attracted considerable attention. In this study, we propose using ChatGPT to create virtual SPs capable of reacting to arbitrary clinical scenarios. However, the direct application of ChatGPT has drawbacks in that it tends to generate overly detailed responses, sometimes mentioning clinical information irrelevant to the examinees’ questions. Such behavior is unsuitable for the purpose of OSCEs. To address this limitation, we propose a mechanism that identifies and amends overly detailed responses from ChatGPT and integrates this mechanism into the ChatGPT-based virtual SP.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Ban, N., Suzuki, T., Aomatsu, M., Saiki, T., Abe, K., Kuwabata, A.: An Easy-to-Understand Guide to Medical Interviews and Simulated Patients[In Japanese]. The University of Nagoya Press (2015)
Dickerson, R., et al.: Evaluating a script-based approach for simulating patient-doctor interaction. In: International Conference of Human-Computer Interface Advances for Modeling and Simulation, vol. 1, pp. 79–84 (2005)
Fareez, F., et al.: A dataset of simulated patient-physician medical interviews with a focus on respiratory cases. Sci. Data 9(1), 313 (2022)
Maicher, K.R., et al.: Artificial intelligence in virtual standardized patients: combining natural language understanding and rule based dialogue management to improve conversational fidelity. In: Medical Teacher, pp. 279–285 (2022)
Pereira, D.S.M., Falcão, F., Nunes, A., Santos, N., Costa, P., Pêgo, J.M.: Designing and building OSCEBot® for virtual OSCE - performance evaluation. Med. Educ. Online 28(1), 16 (2023)
Rau, T., Fegert, J.L.H.: How high are the personnel costs for OSCE? A financial report on management aspects. GMS J. Med. Educ. 28(1), 16 (2011)
Uto, M.: Accuracy of performance-test linking based on a many-facet Rasch model. Behav. Res. Methods 53(4), 1440–1454 (2021)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Shindo, N., Uto, M. (2024). ChatGPT-Based Virtual Standardized Patient that Amends Overly Detailed Responses in Objective Structured Clinical Examinations. In: Olney, A.M., Chounta, IA., Liu, Z., Santos, O.C., Bittencourt, I.I. (eds) Artificial Intelligence in Education. Posters and Late Breaking Results, Workshops and Tutorials, Industry and Innovation Tracks, Practitioners, Doctoral Consortium and Blue Sky. AIED 2024. Communications in Computer and Information Science, vol 2150. Springer, Cham. https://doi.org/10.1007/978-3-031-64315-6_22
Download citation
DOI: https://doi.org/10.1007/978-3-031-64315-6_22
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-64314-9
Online ISBN: 978-3-031-64315-6
eBook Packages: Computer ScienceComputer Science (R0)