{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T12:06:24Z","timestamp":1787313984576,"version":"build-2736575974"},"reference-count":27,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR AI"],"abstract":"Abstract<\/jats:title>\n \n Background<\/jats:title>\n Magnetic resonance imaging (MRI) reports are challenging for patients to interpret and may subject patients to unnecessary anxiety. The advent of advanced artificial intelligence (AI) large language models (LLMs), such as GPT-4o, hold promise for translating complex medical information into layman terms.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n This paper aims to evaluate the accuracy, helpfulness, and readability of GPT-4o in explaining MRI reports of patients with thoracolumbar fractures.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n MRI reports of 20 patients presenting with thoracic or lumbar vertebral body fractures were obtained. GPT-4o was prompted to explain the MRI report in layman\u2019s terms. The generated explanations were then presented to 7 board-certified spine surgeons for evaluation on the reports\u2019 helpfulness and accuracy. The MRI report text and GPT-4o explanations were then analyzed to grade the readability of the texts using the Flesch Readability Ease Score (FRES) and Flesch-Kincaid Grade Level (FKGL) Scale.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n \n The layman explanations provided by GPT-4o were found to be helpful by all surgeons in 17 cases, with 6 of 7 surgeons finding the information helpful in the remaining 3 cases. ChatGPT-generated layman reports were rated as \u201caccurate\u201d by all 7 surgeons in 11\/20 cases (55%). In an additional 5\/20 cases (25%), 6 out of 7 surgeons agreed on their accuracy. In the remaining 4\/20 cases (20%), accuracy ratings varied, with 4 or 5 surgeons considering them accurate. Review of surgeon feedback on inaccuracies revealed that the radiology reports were often insufficiently detailed. The mean FRES score of the MRI reports was significantly lower than the GPT-4o explanations (32.15, SD 15.89 vs 53.9, SD 7.86;\n P<\/jats:italic>\n <.001). The mean FKGL score of the MRI reports trended higher compared to the GPT-4o explanations (11th-12th grade vs 10th-11th grade level;\n P<\/jats:italic>\n =.11).\n <\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n Overall helpfulness and readability ratings for AI-generated summaries of MRI reports were high, with few inaccuracies recorded. This study demonstrates the potential of GPT-4o to serve as a valuable tool for enhancing patient comprehension of MRI report findings.<\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/69654","type":"journal-article","created":{"date-parts":[[2025,5,14]],"date-time":"2025-05-14T14:00:10Z","timestamp":1747231210000},"page":"e69654-e69654","source":"Crossref","is-referenced-by-count":3,"title":["Enhancing Magnetic Resonance Imaging (MRI) Report Comprehension in Spinal Trauma: Readability Analysis of AI-Generated Explanations for Thoracolumbar Fractures"],"prefix":"10.2196","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5741-8411","authenticated-orcid":false,"given":"David C","family":"Sing","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0421-4829","authenticated-orcid":false,"given":"Kishan S","family":"Shah","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3749-8581","authenticated-orcid":false,"given":"Michael","family":"Pompliano","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9433-8093","authenticated-orcid":false,"given":"Paul H","family":"Yi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3393-5748","authenticated-orcid":false,"given":"Calogero","family":"Velluto","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-4875-0445","authenticated-orcid":false,"given":"Ali","family":"Bagheri","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2359-1707","authenticated-orcid":false,"given":"Robert K","family":"Eastlack","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2598-0984","authenticated-orcid":false,"given":"Stephen R","family":"Stephan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1483-7245","authenticated-orcid":false,"given":"Gregory M","family":"Mundis Jr","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2025,7,1]]},"reference":[{"key":"R1","unstructured":"21st Century Cures Act. FDA. Jan 31, 2020. URL: https:\/\/www.fda.gov\/regulatory-information\/selected-amendments-fdc-act\/21st-century-cures-act [Accessed 24-02-2025]"},{"issue":"11","key":"R2","doi-asserted-by":"publisher","first-page":"786","DOI":"10.1016\/j.jacr.2009.07.010","article-title":"Insight from patients for radiologists: improving our reporting systems","volume":"6","author":"Johnson","journal-title":"J Am Coll Radiol"},{"key":"R3","doi-asserted-by":"publisher","DOI":"10.1016\/j.clinimag.2023.06.008","article-title":"Decoding radiology reports: potential application of OpenAI ChatGPT to enhance patient understanding of diagnostic reports","volume":"101","author":"Li","journal-title":"Clin Imaging"},{"issue":"5","key":"R4","doi-asserted-by":"publisher","first-page":"2817","DOI":"10.1007\/s00330-023-10213-1","article-title":"ChatGPT makes medicine easy to swallow: an exploratory case study on simplified radiology reports","volume":"34","author":"Jeblick","journal-title":"Eur Radiol"},{"issue":"8","key":"R5","doi-asserted-by":"publisher","first-page":"433","DOI":"10.1007\/s002560050542","article-title":"MRI findings of thoracolumbar spine fractures: a categorisation based on MRI examinations of 100 fractures","volume":"28","author":"Oner","journal-title":"Skeletal Radiol"},{"issue":"1_suppl","key":"R6","doi-asserted-by":"publisher","first-page":"4S","DOI":"10.1177\/21925682231216584","article-title":"From radiographic evaluation to treatment decisions in neurologically intact patients with thoraco-lumbar burst fractures","volume":"14","author":"Dvorak","journal-title":"Global Spine J"},{"issue":"5","key":"R7","doi-asserted-by":"publisher","first-page":"2757","DOI":"10.1007\/s00590-024-03990-y","article-title":"Educating patients on osteoporosis and bone health: can \u201cChatGPT\u201d provide high-quality content?","volume":"34","author":"Ghanem","journal-title":"Eur J Orthop Surg Traumatol"},{"issue":"3","key":"R8","doi-asserted-by":"publisher","first-page":"385","DOI":"10.3171\/2024.4.SPINE231148","article-title":"An analysis of ChatGPT recommendations for the diagnosis and treatment of cervical radiculopathy","volume":"41","author":"Hoang","journal-title":"J Neurosurg Spine"},{"key":"R9","doi-asserted-by":"publisher","DOI":"10.1016\/j.wneu.2023.11.062","article-title":"Information quality and readability: ChatGPT\u2019s responses to the most common questions about spinal cord injury","volume":"181","author":"Temel","journal-title":"World Neurosurg"},{"key":"R10","unstructured":"Scott B . Readability scoring system. Readability Formulas. 2023. URL: https:\/\/readabilityformulas.com\/readability-scoring-system.php [Accessed 24-08-2024]"},{"issue":"3","key":"R11","doi-asserted-by":"publisher","first-page":"602","DOI":"10.2214\/AJR.18.20197","article-title":"Readability of lumbar spine MRI reports: will patients understand?","volume":"212","author":"Yi","journal-title":"AJR Am J Roentgenol"},{"issue":"2","key":"R12","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/acaae9","article-title":"A review of advances in image-guided orthopedic surgery","volume":"68","author":"Fan","journal-title":"Phys Med Biol"},{"issue":"15","key":"R13","doi-asserted-by":"publisher","first-page":"1073","DOI":"10.1097\/BRS.0000000000003458","article-title":"The association between physicians\u2019 communication and patient-reported outcomes in spine surgery","volume":"45","author":"Rabah","journal-title":"Spine (Phila Pa 1976)"},{"key":"R14","doi-asserted-by":"publisher","DOI":"10.2196\/54371","article-title":"Evaluation of generative language models in personalizing medical information: instrument validation study","volume":"3","author":"Spina","journal-title":"JMIR AI"},{"issue":"1","key":"R15","doi-asserted-by":"publisher","DOI":"10.1016\/j.inpm.2025.100550","article-title":"Optimizing patient understanding of spine MRI reports using AI: a prospective single center study","volume":"4","author":"Encalada","journal-title":"Interv Pain Med"},{"issue":"1","key":"R16","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-47500-2","article-title":"A pilot study on the efficacy of GPT-4 in providing orthopedic treatment recommendations from MRI reports","volume":"13","author":"Truhn","journal-title":"Sci Rep"},{"issue":"8","key":"R17","doi-asserted-by":"publisher","first-page":"1621","DOI":"10.1007\/s00256-024-04599-2","article-title":"Translating musculoskeletal radiology reports into patient-friendly summaries using ChatGPT-4","volume":"53","author":"Kuckelman","journal-title":"Skeletal Radiol"},{"issue":"1","key":"R18","doi-asserted-by":"publisher","DOI":"10.1186\/s42492-023-00136-5","article-title":"Translating radiology reports into plain language using ChatGPT and GPT-4 with prompt learning: results, limitations, and potential","volume":"6","author":"Lyu","journal-title":"Vis Comput Ind Biomed Art"},{"issue":"1","key":"R19","doi-asserted-by":"publisher","DOI":"10.7759\/cureus.77258","article-title":"Is ChatGPT a reliable tool for explaining medical terms?","volume":"17","author":"Oztermeli","journal-title":"Cureus"},{"issue":"4","key":"R20","doi-asserted-by":"publisher","first-page":"554","DOI":"10.1016\/j.spinee.2016.11.009","article-title":"Variability in diagnostic error rates of 10 MRI centers performing lumbar spine MRI examinations on the same patient within a 3-week period","volume":"17","author":"Herzog","journal-title":"Spine J"},{"issue":"10","key":"R21","doi-asserted-by":"publisher","DOI":"10.7759\/cureus.72646","article-title":"Revolutionizing radiology with artificial intelligence","volume":"16","author":"Bhandari","journal-title":"Cureus"},{"issue":"4","key":"R22","doi-asserted-by":"publisher","first-page":"939","DOI":"10.1002\/jmri.26534","article-title":"Deep learning in radiology: an overview of the concepts and a survey of the state of the art with focus on MRI","volume":"49","author":"Mazurowski","journal-title":"J Magn Reson Imaging"},{"key":"R23","author":"Wu","journal-title":"AMIA Annu Symp Proc"},{"issue":"6","key":"R24","doi-asserted-by":"publisher","first-page":"1065","DOI":"10.1007\/s00256-020-03668-6","article-title":"Spine trauma: radiological approach and new concepts","volume":"50","author":"de Almeida Prado","journal-title":"Skeletal Radiol"},{"issue":"2","key":"R25","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3597307","article-title":"Biases in large language models: origins, inventory, and discussion","volume":"15","author":"Navigli","journal-title":"J Data Inf Qual"},{"issue":"1","key":"R26","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1136\/emermed-2011-200451","article-title":"How well informed are patients when leaving the emergency department? comparing information provided and information retained","volume":"30","author":"Marty","journal-title":"Emerg Med J"},{"issue":"7","key":"R27","doi-asserted-by":"publisher","first-page":"1272","DOI":"10.1016\/j.spinee.2018.03.017","article-title":"Anxiety and depression in spine surgery\u2014a systematic integrative review","volume":"18","author":"Str\u00f8m","journal-title":"Spine J"}],"container-title":["JMIR AI"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/ai.jmir.org\/2025\/1\/e69654","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T17:57:40Z","timestamp":1782842260000},"score":1,"resource":{"primary":{"URL":"https:\/\/ai.jmir.org\/2025\/1\/e69654"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,1]]},"references-count":27,"URL":"https:\/\/doi.org\/10.2196\/69654","relation":{},"ISSN":["2817-1705"],"issn-type":[{"value":"2817-1705","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,1]]},"article-number":"v4i11e69654"}}