'Bill': an artificial intelligence (AI) clinical scenario coach for medical radiation science education
Files
Date
2025
Authors
Chau, M.
Higgins, G.
Arruzza, E.
Singh, C.L.
Editors
Advisors
Journal Title
Journal ISSN
Volume Title
Type:
Journal article
Citation
Radiography, 2025; 31(5, article no. 103002):1-4
Statement of Responsibility
Conference Name
Abstract
Introduction: The integration of artificial intelligence (AI) into medical radiation science (MRS) education offers significant potential to enhance student training and bridge gaps in traditional pedagogical methods. This technical note describes the development of “Bill,” an AI-driven Clinical Scenario Coach, designed as a prototype to simulate realistic clinical challenges for undergraduate radiography students. Bill utilizes OpenAI's GPT-4o model to create structured, interactive learning environments aligned with the Medical Radiation Practice Board of Australia (MRPBA) professional standards
Methods: Bill was developed as a collaborative effort between academics and clinical practitioners. Scenarios were designed to simulate tasks ranging from basic technical skills to advanced clinical decision-making in radiography. The prototype incorporates real-time feedback and reflective prompts to align with evidence-based educational practices. The development process focused on ensuring authenticity, relevance, and compliance with MRS-specific standards while optimizing the functionality of the AI framework.
Results: The prototype demonstrated the feasibility of using AI to simulate clinical scenarios in radiography education. Scenarios included tasks such as performing mobile X-rays on critically ill patients and managing fluoroscopy near-miss incidents. Bill provided structured, adaptive guidance and feedback tailored to the complexity of each scenario. The framework was found to effectively simulate real-world challenges, offering a dynamic environment for prototype testing and future refinements.
Conclusions: The development of Bill marks a step forward in exploring AI applications within MRS education. The prototype successfully illustrates the potential for AI to augment traditional teaching methods and create engaging, adaptive learning environments.
Implications for practice: While still in its experimental phase, Bill provides a replicable model for AI-driven clinical coaching, with potential applications across various healthcare disciplines.
School/Discipline
Dissertation Note
Provenance
Description
Access Status
Rights
Copyright 2025 The Authors Published by Elsevier Ltd on behalf of The College of Radiographers (https://creativecommons.org/licenses/by/4.0/)
Access Condition Notes: This is an open access article