Translating musculoskeletal radiology reports into patient-friendly summaries using ChatGPT-4
Abstract
Objective To assess the feasibility of using large language models (LLMs), specifically ChatGPT-4, to generate concise and accurate layperson summaries of musculoskeletal radiology reports.Methods Sixty radiology reports, comprising 20 MR shoulder, 20 MR knee, and 20 MR lumbar spine reports, were obtained via PACS. The reports were deidentified and then submitted to ChatGPT-4, with the prompt "Produce an organized and concise layperson summary of the findings of the following radiology report. Target a reading level of 8-9th grade and word count <300 words." Three (two primary and one later added for validation) independent readers evaluated the summaries for completeness and accuracy compared to the original reports. Summaries were rated on a scale of 1 to 3: 1) summaries that were incorrect or incomplete, potentially providing harmful or confusing information; 2) summaries that were mostly correct and complete, unlikely to cause confusion or harm; and 3) summaries that were entirely correct and complete.Results All 60 responses met the criteria for word count and readability. Mean ratings for accuracy were 2.58 for reader 1, 2.71 for reader 2, and 2.77 for reader 3. Mean ratings for completeness were 2.87 for reader 1 and 2.73 for reader 2 and 2.87 for reader 3. For accuracy, reader 1 identified three summaries as a 1, reader 2 identified one, and reader 3 identified none. For the two primary readers, inter-reader agreement was low for accuracy (kappa 0.33) and completeness (kappa 0.29). There were no statistically significant changes in inter-reader agreement when the third reader's ratings were included in analysis.Conclusion Overall ratings for accuracy and completeness of the AI-generated layperson report summaries were high with only a small minority likely to be confusing or inaccurate. This study illustrates the potential for leveraging generative AI, such as ChatGPT-4, to automate the production of patient-friendly summaries for musculoskeletal MR imaging.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
LLMs can simplify complex medical information, improving patient understanding of diagnoses, treatments, and adverse effects.
“LLMs can simplify complex medical information, improving patient understanding of diagnoses, treatments, and adverse effects.38,39”
From Artificial Intelligence in Oncology: Practical Applications Across Clinical Care, Scholarship, and Translation. (2026) · cites this paper as [39]
Cites
Shanafelt, T. D., Dyrbye, L. N., Sinsky, C., Hasan, O., Satele, D., Sloan, J., & West, C. P. (2016) · Mayo Clinic Proceedings · doi:10.1016/j.mayocp.2016.05.007 · Cited by 1,086 · see citing works
Lyu, Q., Tan, J., Zapadka, M. E., Ponnatapura, J., Niu, C., Myers, K. J., Wang, G., & Whitlow, C. T. (2023) · Visual Computing for Industry, Biomedicine, and Art · doi:10.1186/s42492-023-00136-5 · Cited by 367 · see citing works
Appropriateness of breast cancer prevention and screening recommendations provided by ChatGPT
Haver, H. L., Ambinder, E. B., Bahl, M., Oluyemi, E. T., Jeudy, J., & Yi, P. H. (2023) · Radiology · doi:10.1148/radiol.230424 · Cited by 247 · see citing works
Self-citationHow to Create a Great Radiology Report
Hartung, M. P., Bickle, I. C., Gaillard, F., & Kanne, J. P. (2020) · Radiographics · doi:10.1148/rg.2020200020 · Cited by 118 · see citing works
Li, H., Moon, J. T., Iyer, D., Balthazar, P., Krupinski, E. A., Bercu, Z. L., Newsome, J. M., Banerjee, I., Gichoya, J. W., & Trivedi, H. M. (2023) · Clinical Imaging · doi:10.1016/j.clinimag.2023.06.008 · Cited by 118 · see citing works
Insight From Patients for Radiologists: Improving Our Reporting Systems
Johnson, A. J., Easterling, D. V., Williams, L. S., Glover, S., & Frankel, R. M. (2009) · Journal of the American College of Radiology · doi:10.1016/j.jacr.2009.07.010 · Cited by 69 · see citing works
US policy requires immediate release of records to patients
Salmi, L., Blease, C. R., Hägglund, M., Walker, J., & DesRoches, C. M. (2021) · BMJ · doi:10.1136/bmj.n426 · Cited by 68 · see citing works
Assessing AI-Powered Patient Education: A Case Study in Radiology
Kuckelman, I. J., Yi, P. H., Bui, M., Onuh, I., Anderson, J. A., & Ross, A. B. (2023) · Academic Radiology · doi:10.1016/j.acra.2023.08.020 · Cited by 46 · see citing works
Self-citationMusculoskeletal Applications of Magnetic Resonance Imaging
(1989) · JAMA · doi:10.1001/jama.262.17.2420 · Cited by 23 · see citing works
Physician Perception of the Role of the Patient Portal in Pediatric Health
Bush, R. A., Connelly, C. D., Pérez, A., Chan, N., Kuelbs, C. L., & Chiang, G. J. (2017) · Journal of Ambulatory Care Management · doi:10.1097/jac.0000000000000175 · Cited by 15 · see citing works
Deeds, S., Carr, S. A., Garrison, M. M., & Fainstad, T. L. (2018) · American Journal of Medical Quality · doi:10.1177/1062860618770043 · Cited by 9 · see citing works
Flagged first, then by citations
1 of the 12 references couldn’t be matched to a known paper.
Cited by
Sorted by citations
Large language models in patient education: a scoping review of applications in medicine
Aydin, S., Karabacak, M., Vlachos, V., & Margetis, K. D. (2024) · Frontiers in Medicine · doi:10.3389/fmed.2024.1477898 · Cited by 333 · see citing works
Du, X., Zhou, Z., Wang, Y., Chuang, Y.-W., Li, Y., Yang, R. C., Zhang, W., Wang, X., Chen, X., Guan, H., et al. (2025) · Journal of the American Medical Informatics Association · doi:10.1093/jamia/ocaf233 · Cited by 53 · see citing works
Large Language Models for Simplified Interventional Radiology Reports: A Comparative Analysis
Can, E., Uller, W., Vogt, K., Doppler, M. C., Busch, F., Bayerl, N., Ellmann, S., Kader, A., Elkilany, A., Makowski, M. R., et al. (2024) · Academic Radiology · doi:10.1016/j.acra.2024.09.041 · Cited by 36 · see citing works
ChatGPT and radiology report: potential applications and limitations
Parillo, M., Vaccarino, F., Zobel, B. B., & Mallio, C. A. (2024) · La radiologia medica · doi:10.1007/s11547-024-01915-7 · Cited by 29 · see citing works
Berigan, K., Short, R. G., Reisman, D., McCray, L. W., Skelly, J. M., Jones, K., Befera, N. T., & Ali, N. S. (2024) · Journal of the American College of Radiology · doi:10.1016/j.jacr.2024.06.018 · Cited by 28 · see citing works
Use of Large Language Models on Radiology Reports: A Scoping Review
Lee, R. C., Hadidchi, R., Coard, M. C., Rubinov, Y., Alamuri, T. T., Liaw, A., Chandrupatla, R. S., & Duong, T. Q. (2025) · Journal of the American College of Radiology · doi:10.1016/j.jacr.2025.10.005 · Cited by 26 · see citing works
Alabed, S., Anderson, A., Maiter, A., Hughes, A., McAnenly, N., Salehi, M., Sharkey, M. J., Dwivedi, K., Hokmabadi, A., Alahdab, F., et al. (2026) · The Lancet Digital Health · doi:10.1016/j.landig.2025.100960 · Cited by 25 · see citing works
Generative Artificial Intelligence: Enhancing Patient Education in Cardiovascular Imaging
Marey, A., Saad, A. M., Killeen, B. D., Gómez, C., Tregubova, M., Unberath, M., & Umair, M. (2023) · BJR|Open · doi:10.1093/bjro/tzae018 · Cited by 21 · see citing works
Prucker, P., Bressem, K. K., Peeken, J. C., Jukic, M., Marka, A. W., Strenzke, M., Kim, S. H., Mertens, C. J., Weller, D., Lemke, T., et al. (2025) · Radiology · doi:10.1148/radiol.251844 · Cited by 19 · see citing works
Khanna, P., Dhillon, G. S., Buddhavarapu, V. S., Verma, R., Kashyap, R., & Grewal, H. (2024) · Journal of Personalized Medicine · doi:10.3390/jpm14090923 · Cited by 19 · see citing works
Marey, A., Saad, A. M., Tanas, Y., Ghorab, H., Niemierko, J., Backer, H., & Umair, M. (2025) · Egyptian Journal of Radiology and Nuclear Medicine · doi:10.1186/s43055-025-01452-x · Cited by 16 · see citing works
Advancing spine care through AI and machine learning: overview and applications
Cina, A., & Galbusera, F. (2024) · EFORT Open Reviews · doi:10.1530/eor-24-0019 · Cited by 16 · see citing works
Berzolla, E., Gosnell, G. G., Chen, L., Vonck, C., Alaia, E. F., & Meislin, R. J. (2025) · Arthroscopy The Journal of Arthroscopic and Related Surgery · doi:10.1016/j.arthro.2025.04.033 · Cited by 14 · see citing works
Sunshine, A., Honce, G. H., Callen, A. L., Zander, D. A., Tanabe, J., Petrucci, S. L. P., Lin, C., & Honce, J. M. (2025) · JMIR Formative Research · doi:10.2196/76097 · Cited by 14 · see citing works
Kottlors, J., Iuga, A.-I., Blüthgen, C., Bressem, K. K., Kather, J. N., Moy, L. P., Wald, C., Wang, W., Liu, T., Ranschaert, E. R., et al. (2026) · Radiology · doi:10.1148/radiol.250913 · Cited by 12 · see citing works
Reaver, C. N., Pereira, D. E., Carrillo, E. V., Marcos, C. R., & Goldfarb, C. A. (2025) · Journal of Bone and Joint Surgery · doi:10.2106/jbjs.24.01078 · Cited by 12 · see citing works
Saliba, T., Ferrari, J., Pozzessere, C., Rotzinger, D. C., & Fahrni, G. (2025) · European Journal of Radiology Artificial Intelligence · doi:10.1016/j.ejrai.2025.100024 · Cited by 9 · see citing works
Anand, E., Devi, J., Antoniou, A., Joshi, S., Stoker, J., Lung, P. F. C., Hart, A. L., Tozer, P. J., Ballard, D. H., & Deepak, P. (2025) · Crohn s & Colitis 360 · doi:10.1093/crocol/otaf015 · Cited by 9 · see citing works
Pandita, A., Keniston, A., & Madhuripan, N. (2025) · npj Digital Medicine · doi:10.1038/s41746-025-01658-3 · Cited by 8 · see citing works
Chen, A., Rudin, R. S., Levine, D. M., & Mehrotra, A. (2025) · Journal of the American Medical Informatics Association · doi:10.1093/jamia/ocaf187 · Cited by 8 · see citing works
Pisarcik, D., Kissling, M., Heimer, J., Farkas, M., Leo, C., Huch, R., & Euler, A. (2025) · Academic Radiology · doi:10.1016/j.acra.2025.05.065 · Cited by 7 · see citing works
The utility of artificial intelligence in plain language writing: A scoping review
Ugas, M. A., Huynh, J., Lenarcik-Packham, A., Kukan, A., Deol, A., Fazelzad, R., Fernando, S., Giannopoulos, E., Giuliani, M., Lawrie, K., et al. (2026) · Patient Education and Counseling · doi:10.1016/j.pec.2026.109483 · Cited by 7 · see citing works
Kaba, E., Beyazal, M., Çeliker, F. B., Yel, İ., & Vogl, T. J. (2024) · Academic Radiology · doi:10.1016/j.acra.2024.10.028 · Cited by 7 · see citing works
Large Language Models in Spine Surgery: A Promising Technology
Shah, R., & Schwab, J. H. (2025) · HSS Journal®: The Musculoskeletal Journal of Hospital for Special Surgery · doi:10.1177/15563316251340696 · Cited by 5 · see citing works
Dorigo, W., Giacomelli, E., Calvagna, C., Griselli, F., Speziali, S., Fargion, A. T., Lepidi, S., Pulli, R., & D’Oria, M. (2024) · JVS-Vascular Insights · doi:10.1016/j.jvsvi.2024.100107 · Cited by 6 · see citing works
Tsang, B., Gong, B., Probyn, L. J., & Patlas, M. N. (2026) · Diagnostic and Interventional Imaging · doi:10.1016/j.diii.2026.02.003 · Cited by 5 · see citing works
Prucker, P., Busch, F., Dorfner, F. J., Mertens, C. J., Bayerl, N., Makowski, M. R., Bressem, K. K., & Adams, L. C. (2025) · Clinical Imaging · doi:10.1016/j.clinimag.2025.110557 · Cited by 5 · see citing works
Blašković, L., Tanković, N., Lorencin, I., & Šegota, S. B. (2025) · Big Data and Cognitive Computing · doi:10.3390/bdcc9100256 · Cited by 4 · see citing works
Large Language Models in Radiologist–Patient Communication: A Narrative Review for Clinical Practice
Naidu, J. S., Muthyala, H., Naidu, S. S., Muralidharan, S., & Baskaradoss, V. K. (2026) · Cureus · doi:10.7759/cureus.101890 · Cited by 4 · see citing works
Simplifying Radiology Reports for Patients Using ChatGPT : A Systematic Review
Kwok, M., Franklin, A., & Wastney, T. (2026) · Journal of Medical Imaging and Radiation Oncology · doi:10.1111/1754-9485.70076 · Cited by 4 · see citing works
Lockwood, P., & Mitchell, M. (2025) · Radiography · doi:10.1016/j.radi.2025.102990 · Cited by 3 · see citing works
The clinical application potential assessment of the Deepseek-R1 large language model in lung cancer
Xu, X., Liu, Z., Zhou, S., Ji, B., Fan, D., Yang, Z., Chen, H., Yang, X., & Guan, M. (2025) · Frontiers in Oncology · doi:10.3389/fonc.2025.1601529 · Cited by 3 · see citing works
Anand, E., Ghersin, I., Lingam, G., Devlin, K., Pelly, T., Singer, D., Tomlinson, C., Munro, R. E. J., Capstick, R., Antoniou, A., et al. (2025) · Diagnostics · doi:10.3390/diagnostics16010072 · Cited by 3 · see citing works
Naidu, S. U., Li, H., Moon, J. T., Kim, R., Patel, E., Bercu, Z. L., Newsome, J. M., Gichoya, J. W., & Trivedi, H. (2026) · Academic Radiology · doi:10.1016/j.acra.2025.12.008 · Cited by 3 · see citing works
Arachchige, A. S. P. M. (2024) · Skeletal Radiology · doi:10.1007/s00256-024-04633-3 · Cited by 3 · see citing works
Ethics of artificial intelligence-assisted image interpretation in dermatopathology
Smith, H., Blalock, T. W., & Stoff, B. K. (2025) · JAAD International · doi:10.1016/j.jdin.2025.01.005 · Cited by 3 · see citing works
Sing, D. C., Shah, K. S., Pompliano, M. J., Yi, P. H., Velluto, C., Bagheri, A., Eastlack, R. K., Stephan, S. R., & Mundis, G. M. (2025) · JMIR AI · doi:10.2196/69654 · Cited by 2 · see citing works
Self-citationChang, J., Peng, R., Chen, X., Zhu, Y., Miao, R., Cao, Z., & Feng, H. (2026) · Journal of Medical Internet Research · doi:10.2196/84726 · Cited by 3 · see citing works
AI-Generated Patient-Friendly MRI Fistula Summaries: A Pilot Randomised Study
Anand, E., Ghersin, I., Lingam, G., Pelly, T., Singer, D., Tomlinson, C., Munro, R. E. J., Capstick, R., Antoniou, A., Hart, A. L., et al. (2025) · Journal of Imaging · doi:10.3390/jimaging11090302 · Cited by 2 · see citing works
Hundal, J., Veettil, A. A. V., Chung, C., & Hosseini, M. (2026) · American Society of Clinical Oncology Educational Book · doi:10.1200/edbk-26-517280 · Cited by 1 · see citing works
Role of ChatGPT in interventional cardiology
Sule, A. A., Poh, K. K., & Srinivasan, D. K. (2025) · Singapore Medical Journal · doi:10.4103/singaporemedj.smj-2024-139 · Cited by 1 · see citing works
Bahir, D., Rostov, A. T., Busool, Y., Azzam, S. H., Lockington, D., Teichman, J. C., Matsou, A., Chan, C. C., Shvartz, E., & Mimouni, M. (2025) · European Journal of Ophthalmology · doi:10.1177/11206721251350809 · Cited by 1 · see citing works
Doshi, R. H., Amin, K., Chan, S. M., Kaur, M., Bajaj, S. S., Khosla, P., Kothari, V. T., Mozayan, A., Tocino, I. M., & Chheang, S. (2025) · PLoS ONE · doi:10.1371/journal.pone.0331368 · Cited by 1 · see citing works
Alarifi, M., Luo, J., Jabour, A. M., Alashban, Y. I., Alahmad, H. N., Alshedi, A. F., & Almanaa, M. A. (2026) · Journal of Clinical Medicine · doi:10.3390/jcm15114158 · Cited by 1 · see citing works
Utility of ChatGPT-4 in Musculoskeletal Imaging: A Narrative ReviewPreprint
Albahkali, S. M., & Alawad, S. H. (2024) · Preprints.org · doi:10.20944/preprints202403.1342.v2 · Cited by 1 · see citing works
Translating musculoskeletal radiology reports using ChatGPT-4: comment
Daungsupawong, H., & Wiwanitkit, V. (2024) · Skeletal Radiology · doi:10.1007/s00256-024-04651-1
Xu, M., & Wang, Y. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-4001-0_28
Bahir, D., Hartstein, M. E., Burkat, C. N., Ezra, D. G., Wulc, A. E., Zloto, O., Holds, J. B., & Azzam, S. H. (2025) · Ophthalmic Plastic and Reconstructive Surgery · doi:10.1097/iop.0000000000003046
Beyond readability: Toward empathetic patient-friendly radiology reports
Rattanapitoon, S. K., Thitimahatthanakusol, P., Choenklang, C., & Rattanapitoon, N. K. (2025) · Clinical Imaging · doi:10.1016/j.clinimag.2025.110652
Sun, Y., Huang, C., Kang, H., Wu, K., Jin, Z., Chen, C., Liao, M., Ou, W., Wang, B., Chen, X., et al. (2026) · Journal of Medical Internet Research · doi:10.2196/97136
Responsible Use of GenAI Technologies in Health Communication: Translating the Covid-19 Pandemic
Çetin, Ö., Eser, O., & Durán, A. (2026) · Öğretim Teknolojisi ve Hayat Boyu Öğrenme Dergisi - Instructional Technology and Lifelong Learning · doi:10.52911/itall.1870352
Zhou, S., & Wang, Y. (2026) · Applied Artificial Intelligence Research · doi:10.65455/2c4jes43
van der Mee, F. A. M., Broos, R., Ottenheijm, R. P. G., Puts, S., Zijta, F. M., Jansen, J., Cals, J., Nobel, J. M., & Leijenaar, R. T. H. (2026) · European Radiology · doi:10.1007/s00330-026-12971-0
Erdem, T. E., Kırılmaz, A., Dogan, F., Tahak, F., Küçükşen, M. F., Yıldız, M., Yılmaz, S., Yapar, D., & Yapar, A. (2026) · Diagnostics · doi:10.3390/diagnostics16213609
- Authors
- Kuckelman, I. J., Wetley, K., Yi, P. H., & Ross, A. B.
- Affiliations
- University of Wisconsin–Madison (US)
- University of Maryland, Baltimore (US)
- Corresponding author
- Kuckelman, Ian J.
- Venue
- Skeletal Radiology
- Published
- 2024-01-25
- Volume
- 53
- Issue
- 8
- Pages
- 1621-1624
- ISSN
- 0364-2348 (ISSN-L)
- 1432-2161
- OpenAlex
- W4391227238
- Cited by
- 58
- References
- 12
- Citations by year
- 2026: 15 · 2025: 29 · 2024: 13 · 2023: 1
- FWCI
- 5.30
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Locations
- Skeletal Radiology (publishedVersion)
- PubMed (publishedVersion)
- Topics
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › Radiology practices and education
- Health Sciences › Health Professions › General Health Professions › Health Literacy and Information Accessibility
- Keywords
- ChatGPT-4, large language models, generative AI, radiology report summarization, patient-friendly summary, musculoskeletal MRI, shoulder MRI, knee MRI, lumbar spine MRI, interobserver agreement
- MeSH terms
- Feasibility Studies, Humans, Musculoskeletal Diseases, Radiology Information Systems, Translating, Comprehension
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
