119 posters, 6 topics, 524 authors, 243 institutions
ePostersLive by SciGen Technologies S.A. All rights reserved.
RCR Global AI Conference 2026
29-30 June, 2026 | QEII Centre, Westminster
142
AI- assisted question generation for FRCR Part 1 Physics: Evaluating the role of Multi model LLMs in High-stake Radiology Assessment Design
Poster Presenter
Authors
Ebinesh Arulnathan, Shirou Masoodi, Zobia Hussain, Rayya Naffa', Srikrishna Harave, Sivakumar Manickam
Affiliations
Mid & South Essex NHS trust , Mid and South Essex NHS Foundation Trust, Alder Hey Children's NHS Foundation Trust , East and North Hertfordshire Teaching NHS Trust, Alder Hey Children's NHS Foundation Trust
Part of Topic
AI Education and research: examples of proof of concept or AI in development, technical advances, teaching approaches or pre-clinical testing
AI- assisted question generation for FRCR Part 1 Physics: Evaluating the role of Multi model LLMs in High-stake Radiology Assessment Design
Across 105 FRCR Part 1 physics questions rated independently by 5 reviewers, source had a large effect on overall score, with ChatGPT outperforming Gemini and Perplexity, and Gemini outperforming Perplexity. The clearest between-source differences were in adequacy of explanation, reliability of rationale, technical accuracy, and difficulty calibration, whereas clarity differed little. Domain-level effects were small, suggesting that model-related rather than topic-related factors primarily determined quality.