Abstract
This study systematically investigated the influence of demographic characteristics on the readability of patient-centric radiology reports and compared the performance of different large language models (LLMs) in generating patient-centered reports. Adopting a sequential two-stage design, the research first conducted a retrospective evaluation involving 320 radiology reports followed by a clinical setting validation with 800 patients. Results suggested that all three LLMs significantly improved the readability of radiology reports (P < 0.05), with DeepSeek-R1 showing potentially superior performance within this specific cohort. Demographic analysis revealed significant interactive effects: higher education and older age (within consistent educational levels) were associated with better comprehension. Clinical setting validation further indicated that reading simplified reports suggesting the potential to significantly improved patients’ subjective and objective comprehension while significantly alleviating medical anxiety (P < 0.05). However, limitations persist, including inconsistent model outputs, missing anatomical details, and comprehension variances driven by demographic factors. Consequently, LLMs should be integrated as auxiliary communication tools for radiologists rather than standalone solutions, necessitating personalized interventions tailored to specific demographic profiles.
Similar content being viewed by others
Data availability
The datasets generated or analyzed during the study are available from the corresponding author on reasonable request.
References
Vijan, A., Bhagwanani, A., Calle, F. & Brun-Vergara, M. L. Optimizing patient communication in radiology. Radiographics 43, e230002 (2023).
Rockall, A. G., Justich, C., Helbich, T. & Vilgrain, V. Patient communication in radiology: moving up the agenda. Eur. J. Radiol. 155, 110464 (2022).
Cabarrus, M., Naeger, D. M., Rybkin, A. & Qayyum, A. Patients prefer results from the ordering provider and access to their radiology reports. J. Am. Coll. Radi. ol. 12, 556–562 (2015).
Gunn, A. J. et al. JOURNAL CLUB: structured feedback from patients on actual radiology reports: a novel approach to improve reporting practices. AJR Am. J. Roentgenol. 208, 1262–1270 (2017).
Martin-Carreras, T., Cook, T. S. & Kahn, C. E. Jr Readability of radiology reports: implications for patient-centered care. Clin. Imaging 54, 116–120 (2019).
Burns, J., Agarwal, V., Catanzano, T. M., Schaefer, P. W. & Jordan, S. G. Talking points: enhancing communication between radiologists and patients. Acad. Radiol. 29, 888–896 (2022).
Yin, S. et al. A survey on multimodal large language models. Natl. Sci. Rev. 11, nwae403 (2024).
Gulati, V. et al. Transcending language barriers: can ChatGPT Be the key to enhancing multilingual accessibility in health care? J. Am. Coll. Radiol. 21, 1888–1895 (2024).
Herwald, S. E. et al. RadGPT: a system based on a large language model that generates sets of patient-centered materials to explain radiology report information. J. Am. Coll. Radiol. 22, 1050–1059 (2025).
Leutz-Schmidt, P. et al. Performance of large language models ChatGPT and Gemini on workplace management questions in radiology. Diagnostics 15, 497 (2025).
Elhakim, T. et al. Enhanced PROcedural information READability for Patient-Centered Care in Interventional Radiology With Large Language Models (PRO-READ IR). J. Am. Coll. Radiol. 22, 84–97 (2025).
Kim, H. et al. Conversion of mixed-language free-text CT reports of pancreatic cancer to national comprehensive cancer network structured reporting templates by using GPT-4. Korean J. Radiol. 26, 557–568 (2025).
Çamur, E., Cesur, T. & Güneş, Y. C. A comparative study: performance of large language models in simplifying Turkish computed tomography reports. J. Infect. Public Health 87, 321–326 (2024).
Berzolla, E. et al. Artificial intelligence large language models improve patient comprehension of radiologist magnetic resonance imaging reports. Arthroscopy 41, 4607–4614.e4604 (2025).
Chen, A. H., Rudin, R. S., Levine, D. M. & Mehrotra, A. Improving patient understanding of radiology reports using generative artificial intelligence: a vignette study of 2000 US adults. J. Am. Med. Inform. Assoc. https://doi.org/10.1093/jamia/ocaf187 (2025).
Doyle, C., Lennox, L. & Bell, D. A systematic review of evidence on the links between patient experience and clinical safety and effectiveness. BMJ Open 3, e001570 (2013).
Jeblick, K. et al. ChatGPT makes medicine easy to swallow: an exploratory case study on simplified radiology reports. Eur. Radiol. 34, 2817–2825 (2024).
Doshi, R. et al. Quantitative evaluation of large language models to streamline radiology report impressions: a multimodal retrospective analysis. Radiology 310, e231593 (2024).
Rahsepar, A. A. Large language models for enhancing radiology report impressions: improve readability while decreasing burnout. Radiology 310, e240498 (2024).
Nakaura, T. et al. The impact of large language models on radiology: a guide for radiologists on the latest innovations in AI. Jpn. J. Radiol. 42, 685–696 (2024).
Prucker, P. et al. A prospective controlled trial of large language model-based simplification of oncologic CT reports for patients with cancer. Radiology 317, e251844 (2025).
Jebb, A. T., Ng, V. & Tay, L. A review of key likert scale development advances: 1995-2019. Front. Psychol. 12, 637547 (2021).
Acknowledgements
We gratefully acknowledge the Radiology Department of the Third Hospital of Jilin University for their support of this research, and Professor Mengchao Zhang on the research team.
Author information
Authors and Affiliations
Contributions
M.Z. conceptualized the study, performed formal analysis and investigation, and was responsible for project administration and supervision. Y.M. and C.W. (equal contributors) contributed to data curation, formal analysis, methodology, validation, visualization, and wrote the original draft and revised the manuscript. Y.L. contributed to data curation, methodology, and visualization. W.W. contributed to methodology and writing the original draft. All authors have read and approved the manuscript.
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests.
Additional information
Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary information
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.
About this article
Cite this article
Mao, Y., Wang, C., Li, Y. et al. Multidimensional evaluation of large language models in radiology report readability. npj Digit. Med. (2026). https://doi.org/10.1038/s41746-026-02589-3
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41746-026-02589-3
