Supporting Radiology Resident Education and Clinical Decision-Making With Large Language Models: Comparative Study of Reasoning Models DeepSeek-R1 and ChatGPT-o1
JMIR AI · 2026-06-26 · 5 · e86974-e86974
DOI: 10.2196/86974 ↗At a glance
Journal article in JMIR AI, published online on 2026-06-26. Written by Semil Eminovic and 10 co-authors. Institution: Department of Radiology, Charité - Universitätsmedizin Berlin, Augustenburger Platz 1, Berlin, 13353, Germany. Cited 1 times so far (Crossref); 36 references. The full text is freely available in PubMed Central.
Abstract (original language)
Background
Radiology trainees require efficient, accurate, and accessible resources to master complex imaging techniques and identify findings that guide clinical decision-making. Large language models (LLMs) are emerging as promising tools for medical education and clinical workflows, offering the potential to enhance learning by providing instant feedback, aiding in diagnostic accuracy, and offering personalized learning experiences. However, systematic comparisons of LLMs for radiology education and clinical support remain limited, particularly regarding differences across subspecialties and resident experience levels.
Objective
This study aimed to evaluate and compare the response quality of 2 state-of-the-art reasoning-based LLMs, namely DeepSeek-R1 and ChatGPT-o1, as clinical and radiology residency support tools, comparing performance across clinical and didactic dimensions, including text- and image-based responses.
Methods
Overall, 27 radiology questions covering 9 radiological subspecialties were answered by both LLMs. Additionally, 6 image-based questions were presented only to ChatGPT-o1 due to its image processing capabilities. Responses were independently rated by 7 radiology residents (postgraduate years 2‐5) across 9 rating criteria grouped into 3 dimensions (factual accuracy, clinical practicality, and didactic value), using a 5-point Likert scale. Statistics compared LLMs, reader experience, and response types for text- as well as image-based for ChatGPT-o1 queries.
Results
DeepSeek-R1 consistently outperformed ChatGPT-o1 across all rating dimensions, with highly significant differences across all criteria (mean ratings: DeepSeek-R1 4.51, SD 0.73 vs ChatGPT-o1 3.73, SD 0.98; P
Subjects
Author keywords
Authors and institutions
- Department of Radiology, Charité - Universitätsmedizin Berlin, Augustenburger Platz 1, Berlin, 13353, Germany.
- Berlin Institute of Health, Charité - Universitätsmedizin Berlin, Berlin, Germany.
- Department of Neuroradiology, Charité - Universitätsmedizin Berlin, Berlin, Germany.
Cite
APA
Eminovic, S., Schmidt, R., Levita, B., Lindholz, M., Haack, A. M., Burdenski, A., Bui, M., Schobert, I. T., Dell'Orco, A., Nawabi, J., & Penzkofer, T. (2026). Supporting Radiology Resident Education and Clinical Decision-Making With Large Language Models: Comparative Study of Reasoning Models DeepSeek-R1 and ChatGPT-o1. JMIR AI, 5, e86974-e86974. https://doi.org/10.2196/86974
Vancouver
Eminovic S, Schmidt R, Levita B, Lindholz M, Haack AM, Burdenski A, et al. Supporting Radiology Resident Education and Clinical Decision-Making With Large Language Models: Comparative Study of Reasoning Models DeepSeek-R1 and ChatGPT-o1. JMIR AI. 2026;5:e86974-e86974. doi:10.2196/86974
BibTeX
@article{Eminovic2026,
author = {Eminovic, Semil and Schmidt, Robin and Levita, Bogdan and Lindholz, Maximilian and Haack, Anna-Maria and Burdenski, Alina and Bui, Maurice and Schobert, Isabel Theresa and Dell'Orco, Andrea and Nawabi, Jawed and Penzkofer, Tobias},
title = {Supporting Radiology Resident Education and Clinical Decision-Making With Large Language Models: Comparative Study of Reasoning Models DeepSeek-R1 and ChatGPT-o1},
journal = {JMIR AI},
year = {2026},
volume = {5},
pages = {e86974--e86974},
doi = {10.2196/86974}
}
EUVIMED