{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T00:09:40Z","timestamp":1792714180863,"version":"4.5.0"},"reference-count":18,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T00:00:00Z","timestamp":1757376000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T00:00:00Z","timestamp":1757376000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Skeletal Radiol"],"published-print":{"date-parts":[[2026,2]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>To assess the ability of large language models (LLMs) to accurately simplify lumbar spine magnetic resonance imaging (MRI) reports.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Materials and methods<\/jats:title>\n                    <jats:p>Patients who underwent lumbar decompression and\/or fusion surgery in 2022 at one tertiary academic medical center were queried using appropriate CPT codes. We then identified all patients with a preoperative ICD diagnosis of lumbar spondylolisthesis and extracted the latest preoperative spine MRI radiology report text. The GPT-4 API was deployed on deidentified reports with a prompt to produce translations and evaluated for accuracy and readability. An enhanced GPT prompt was constructed using high-scoring reports and evaluated on low-scoring reports.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      Of 93 included reports, GPT effectively reduced the average reading level (11.47 versus 8.50,\n                      <jats:italic>p<\/jats:italic>\n                      \u2009&lt;\u20090.001). While most reports had no accuracy issues, 34% of translations omitted at least one clinically relevant piece of information, while 6% produced a clinically significant inaccuracy in the translation. An enhanced prompt model using high scoring reports-maintained reading level while significantly improving omission rate (\n                      <jats:italic>p<\/jats:italic>\n                      \u2009&lt;\u20090.0001). However, even in the enhanced prompt model, GPT made several errors regarding location of stenosis, description of prior spine surgery, and description of other spine pathologies.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>GPT-4 effectively simplifies the reading level of lumbar spine MRI reports. The model tends to omit key information in its translations, which can be mitigated with enhanced prompting. Further validation in the domain of spine radiology needs to be performed to facilitate clinical integration.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1007\/s00256-025-05027-9","type":"journal-article","created":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T02:36:21Z","timestamp":1757385381000},"page":"361-366","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Assessing the ability of large language models to simplify lumbar spine imaging reports into patient-facing text: a pilot study of GPT-4"],"prefix":"10.1007","volume":"55","author":[{"given":"Rushmin","family":"Khazanchi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Austin R.","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Parth","family":"Desai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniel","family":"Herrera","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jacob R.","family":"Staub","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matthew A.","family":"Follett","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mykhaylo","family":"Krushelnytskyy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hanna","family":"Kemeny","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wellington K.","family":"Hsu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alpesh A.","family":"Patel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Srikanth N.","family":"Divi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,9,9]]},"reference":[{"issue":"1","key":"5027_CR1","doi-asserted-by":"publisher","first-page":"120","DOI":"10.1038\/s41746-023-00873-0","volume":"6","author":"B Mesk\u00f3","year":"2023","unstructured":"Mesk\u00f3 B, Topol EJ. The imperative for regulatory oversight of large language models (or generative AI) in healthcare. NPJ Digit Med. 2023;6(1):120\u20136.","journal-title":"NPJ Digit Med"},{"issue":"1","key":"5027_CR2","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1186\/s42492-023-00136-5","volume":"6","author":"Q Lyu","year":"2023","unstructured":"Lyu Q, et al. Translating radiology reports into plain language using ChatGPT and GPT-4 with prompt learning: results, limitations, and potential. Vis Comput Ind Biomed Art. 2023;6(1):9\u201310.","journal-title":"Vis Comput Ind Biomed Art"},{"issue":"1","key":"5027_CR3","doi-asserted-by":"publisher","first-page":"e232714","DOI":"10.1148\/radiol.232714","volume":"311","author":"RJ Gertz","year":"2024","unstructured":"Gertz RJ, et al. Potential of GPT-4 for detecting errors in radiology reports: implications for reporting accuracy. Radiology. 2024;311(1):e232714.","journal-title":"Radiology"},{"issue":"1","key":"5027_CR4","doi-asserted-by":"publisher","first-page":"20159","DOI":"10.1038\/s41598-023-47500-2","volume":"13","author":"D Truhn","year":"2023","unstructured":"Truhn D, et al. A pilot study on the efficacy of GPT-4 in providing orthopedic treatment recommendations from MRI reports. Sci Rep. 2023;13(1):20159\u201320159.","journal-title":"Sci Rep"},{"issue":"1","key":"5027_CR5","doi-asserted-by":"publisher","first-page":"338","DOI":"10.1016\/j.acra.2023.08.020","volume":"31","author":"IJ Kuckelman","year":"2024","unstructured":"Kuckelman IJ, et al. Assessing AI-powered patient education: a case study in radiology. Acad Radiol. 2024;31(1):338\u201342.","journal-title":"Acad Radiol"},{"issue":"5","key":"5027_CR6","doi-asserted-by":"publisher","first-page":"269","DOI":"10.4174\/astr.2023.104.5.269","volume":"104","author":"N Oh","year":"2023","unstructured":"Oh N, Choi G-S, Lee WY. ChatGPT goes to the operating room: evaluating GPT-4 performance and its potential in surgical education and training in the era of large language models. Ann Surg Treat Res. 2023;104(5):269\u201373.","journal-title":"Ann Surg Treat Res"},{"issue":"5","key":"5027_CR7","doi-asserted-by":"publisher","first-page":"e231259","DOI":"10.1148\/radiol.231259","volume":"307","author":"Z Sun","year":"2023","unstructured":"Sun Z, et al. Evaluating GPT-4 on impressions generation in radiology reports. Radiology. 2023;307(5):e231259\u2013e231259.","journal-title":"Radiology"},{"issue":"2","key":"5027_CR8","doi-asserted-by":"publisher","first-page":"e232561","DOI":"10.1148\/radiol.232561","volume":"309","author":"KS Amin","year":"2023","unstructured":"Amin KS, et al. Accuracy of chatGPT, Google Bard, and Microsoft Bing for simplifying radiology reports. Radiology. 2023;309(2):e232561\u2013e232561.","journal-title":"Radiology"},{"issue":"1","key":"5027_CR9","doi-asserted-by":"publisher","first-page":"128","DOI":"10.14245\/ns.2347310.655","volume":"21","author":"B Zaidat","year":"2024","unstructured":"Zaidat B, et al. Performance of a large language model in the generation of clinical guidelines for antibiotic prophylaxis in spine surgery. Neurospine. 2024;21(1):128\u201346.","journal-title":"Neurospine"},{"issue":"2","key":"5027_CR10","doi-asserted-by":"publisher","first-page":"190","DOI":"10.1007\/s11604-023-01487-y","volume":"42","author":"T Nakaura","year":"2024","unstructured":"Nakaura T, et al. Preliminary assessment of automated radiology report generation with generative pre-trained transformers: comparing results to radiologist-generated reports. Jpn J Radiol. 2024;42(2):190\u2013200.","journal-title":"Jpn J Radiol"},{"issue":"1","key":"5027_CR11","doi-asserted-by":"publisher","first-page":"13218","DOI":"10.1038\/s41598-024-63824-z","volume":"14","author":"J Park","year":"2024","unstructured":"Park J, et al. Patient-centered radiology reports with generative artificial intelligence: adding value to radiology reporting. Sci Rep. 2024;14(1):13218\u20139.","journal-title":"Sci Rep"},{"issue":"2","key":"5027_CR12","doi-asserted-by":"publisher","first-page":"245","DOI":"10.1007\/s00270-023-03563-2","volume":"47","author":"M Scheschenja","year":"2024","unstructured":"Scheschenja M, et al. Feasibility of GPT-3 and GPT-4 for in-depth patient education prior to interventional radiological procedures: a comparative analysis. Cardiovasc Intervent Radiol. 2024;47(2):245\u201350.","journal-title":"Cardiovasc Intervent Radiol"},{"key":"5027_CR13","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1016\/j.clinimag.2023.06.008","volume":"101","author":"H Li","year":"2023","unstructured":"Li H, et al. Decoding radiology reports: potential application of OpenAI ChatGPT to enhance patient understanding of diagnostic reports. Clin Imaging. 2023;101:137\u201341.","journal-title":"Clin Imaging"},{"issue":"1","key":"5027_CR14","doi-asserted-by":"publisher","first-page":"101035","DOI":"10.1016\/j.jocmr.2024.101035","volume":"26","author":"B Salam","year":"2024","unstructured":"Salam B, et al. Generative pre-trained transformer 4 makes cardiovascular magnetic resonance reports easy to understand. J Cardiovasc Magn Reson. 2024;26(1):101035\u2013101035.","journal-title":"J Cardiovasc Magn Reson"},{"issue":"3","key":"5027_CR15","doi-asserted-by":"publisher","first-page":"e231593","DOI":"10.1148\/radiol.231593","volume":"310","author":"R Doshi","year":"2024","unstructured":"Doshi R, et al. Quantitative evaluation of large language models to streamline radiology report impressions: a multimodal retrospective analysis. Radiology. 2024;310(3):e231593.","journal-title":"Radiology"},{"issue":"5","key":"5027_CR16","doi-asserted-by":"publisher","first-page":"2817","DOI":"10.1007\/s00330-023-10213-1","volume":"34","author":"K Jeblick","year":"2024","unstructured":"Jeblick K, et al. ChatGPT makes medicine easy to swallow: an exploratory case study on simplified radiology reports. Eur Radiol. 2024;34(5):2817\u201325.","journal-title":"Eur Radiol"},{"issue":"2","key":"5027_CR17","doi-asserted-by":"publisher","first-page":"611","DOI":"10.1007\/s00402-023-05113-4","volume":"144","author":"S Schmidt","year":"2024","unstructured":"Schmidt S, et al. Simplifying radiologic reports with natural language processing: a novel approach using ChatGPT in enhancing patient understanding of MRI results. Arch Orthop Trauma Surg. 2024;144(2):611\u20138.","journal-title":"Arch Orthop Trauma Surg"},{"key":"5027_CR18","doi-asserted-by":"publisher","DOI":"10.1016\/j.jacr.2024.05.009","author":"V Gulati","year":"2024","unstructured":"Gulati V, et al. Transcending language barriers: can ChatGPT be the key to enhancing multilingual accessibility in health care? J Am Coll Radiol. 2024. https:\/\/doi.org\/10.1016\/j.jacr.2024.05.009.","journal-title":"J Am Coll Radiol"}],"container-title":["Skeletal Radiology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00256-025-05027-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00256-025-05027-9","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00256-025-05027-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,26]],"date-time":"2025-12-26T05:16:37Z","timestamp":1766726197000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00256-025-05027-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,9]]},"references-count":18,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,2]]}},"alternative-id":["5027"],"URL":"https:\/\/doi.org\/10.1007\/s00256-025-05027-9","relation":{},"ISSN":["0364-2348","1432-2161"],"issn-type":[{"value":"0364-2348","type":"print"},{"value":"1432-2161","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,9]]},"assertion":[{"value":"15 May 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 August 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 August 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 September 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This study was approved by the Northwestern University Institutional Review Board under STU00214424.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Dr. Alpesh Patel has received royalties from Alphates Spine, Amedica, the Journal of the American Academy of Orthopaedic Surgeons, Nuvasive, and Springer and consulting fees from Alphates Spine, Amedica, DePuy (a Johnson & Johnson company), Kuros Biosciences, Muvasive, and Zimmer. Dr. Patel also holds leadership roles in the American Arthepaedic Association, the Cervical Spine Research Society, the North American Spine Society, Surgical Neurology.International, and Wolters Kluwer Health\u2014Lippincott Williams & Wilkins. Additionally, Dr. Patel owns stock in Extenics, Endaluxe, Necimed, nView Medical Inc, Spine BioPharma, and Tissue Differentiation Intelligence.Dr. Wellington Hsu has received royalties from Stryker and consulting fees from Asahi, Medtronic Sofamer Danek, and Stryker. Dr. Hsu also holds leadership roles in the Cervical Spine Research Society, the Lumbar Spine Research Society, and the North American Spine Society and owns stock in Amphix Bio.Dr. Srikanth Divi has received payment for lectures from Atec Spine, Inc. and travel support from Kuros Biosciences.For the remaining authors none were declared.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of interest"}}]}}