{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T06:27:14Z","timestamp":1786602434981,"version":"build-2736575974"},"reference-count":31,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T00:00:00Z","timestamp":1786579200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100007210","name":"RWTH Aachen University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100007210","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Surg."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Injuries to the brachial plexus and its terminal branches can be devastating at the functional and occupational levels, as loss of even partial functions causes major disruptions in dexterity and mobility. The brachial plexus comprises multiple interconnected anatomical layers, making thorough anatomical knowledge essential for determining the extent of injury and the best treatment. Thus, the correlation between functional deficit and precise localization of the injury site is crucial to avoid extensive surgical explorations and restore anatomical integrity.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Method<\/jats:title>\n                    <jats:p>In this study, we presented Medical Research Council (MRC) muscle strength grades from 50 standardized real-world-inspired fictional benchmark cases of brachial plexus and upper-extremity peripheral nerve injuries at different anatomical levels (roots, trunks, cords, terminal branches, and combined patterns) to various Multimodal Generative Models (MM-GMs), namely GPT-5 (OpenAI), Gemini 2.5 Pro (Google), Grok 4 (xAI), and Claude Opus 4.1 (Anthropic), and evaluated their ability to localize anatomical lesion sites based solely on functional motor deficits.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      GPT-5 achieved the highest overall accuracy with 39\/50 correct responses (78.0%; 95% CI 64.8\u201387.2), followed by Grok 4 and Claude Opus 4.1 with 26\/50 correct responses each (52.0%; 95% CI 38.5\u201365.2) and Gemini 2.5 Pro with 22\/50 correct responses (44.0%; 95% CI 31.2\u201357.7). Cochran's\n                      <jats:italic>Q<\/jats:italic>\n                      test showed a significant difference between the models, and Holm-adjusted exact McNemar\n                      <jats:italic>post-hoc<\/jats:italic>\n                      comparisons demonstrated the superior performance of GPT-5 compared with the other models. Combination injuries involving various anatomical sites proved challenging for MM-GMs, with only 20% of answers correct.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>Collectively, this controlled benchmark suggests that MM-GMs can assign standardized MRC strength-grade patterns to anatomical levels of brachial plexus and peripheral nerve injuries. However, performance varies substantially across models and lesion categories, requiring validation in real clinical cohorts before clinical implementation.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fsurg.2026.1814943","type":"journal-article","created":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T05:33:26Z","timestamp":1786599206000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Assessment of brachial plexus and upper-extremity peripheral nerve injuries at the anatomical level using multimodal generative models"],"prefix":"10.3389","volume":"13","author":[{"given":"Vincent G. J.","family":"Guillaume","sequence":"first","affiliation":[{"name":"Department of Plastic Surgery, Hand and Burn Surgery, University Hospital RWTH Aachen","place":["Aachen, Germany"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ron","family":"Martin","sequence":"additional","affiliation":[{"name":"Department of Plastic and Hand Surgery, Burn Care Center, BG Klinikum Bergmannstrost Halle","place":["Halle, Germany"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jonas","family":"Roos","sequence":"additional","affiliation":[{"name":"Clinic for Orthopedics and Trauma Surgery, University Hospital of Bonn, University of Bonn","place":["Bonn, Germany"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Robert","family":"Kaczmarczyk","sequence":"additional","affiliation":[{"name":"Department of Dermatology and Allergy, School of Medicine, Technical University of Munich","place":["Munich, Germany"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Justus P.","family":"Beier","sequence":"additional","affiliation":[{"name":"Department of Plastic Surgery, Hand and Burn Surgery, University Hospital RWTH Aachen","place":["Aachen, Germany"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Benedikt","family":"Sch\u00e4fer","sequence":"additional","affiliation":[{"name":"Department of Plastic Surgery, Hand and Burn Surgery, University Hospital RWTH Aachen","place":["Aachen, Germany"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tim","family":"Leypold","sequence":"additional","affiliation":[{"name":"Department of Plastic Surgery, Hand and Burn Surgery, University Hospital RWTH Aachen","place":["Aachen, Germany"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,8,13]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/s0749-0712(03)00088-x","article-title":"Brachial plexus anatomy","volume":"20","author":"Leinberry","year":"2004","journal-title":"Hand Clin"},{"key":"B2","doi-asserted-by":"publisher","first-page":"368","DOI":"10.1177\/17531934221146860","article-title":"Microsurgical reconstruction of obstetric brachial plexus palsy: ongoing challenges and future directions","volume":"48","author":"Bahm","year":"2023","journal-title":"J Hand Surg Eur Vol."},{"key":"B3","doi-asserted-by":"publisher","first-page":"119","DOI":"10.3171\/2025.1.PEDS24626","article-title":"Epidemiology and surgical management of obstetric brachial plexus injury: a national cohort study","volume":"36","author":"Sargut","year":"2025","journal-title":"J Neurosurg Pediatr"},{"key":"B4","doi-asserted-by":"publisher","first-page":"705","DOI":"10.5435\/JAAOS-D-18-00433","article-title":"Adult traumatic brachial plexus injuries","volume":"27","author":"Noland","year":"2019","journal-title":"J Am Acad Orthop Surg"},{"key":"B5","doi-asserted-by":"publisher","first-page":"868","DOI":"10.1016\/j.wneu.2017.08.119","article-title":"Mechanisms, treatment, and patient outcome of iatrogenic injury to the brachial plexus \u2013 a retrospective single-center study","volume":"107","author":"Dengler","year":"2017","journal-title":"World Neurosurg"},{"key":"B6","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1212\/wnl.31.1.45","article-title":"Brachial plexus lesions in patients with cancer: 100 cases","volume":"31","author":"Kori","year":"1981","journal-title":"Neurology"},{"key":"B7","doi-asserted-by":"publisher","first-page":"e4294","DOI":"10.1097\/GOX.0000000000004294","article-title":"Early referral in brachial plexus injury: an ethical obligation","volume":"10","author":"Morris","year":"","journal-title":"Plast Reconstr Surg Glob Open"},{"key":"B8","doi-asserted-by":"publisher","first-page":"929.e1","DOI":"10.1016\/j.jhsa.2021.01.026","article-title":"Delayed referral for adult traumatic brachial plexus injuries","volume":"46","author":"Zhang","year":"2021","journal-title":"J Hand Surg Am"},{"key":"B9","doi-asserted-by":"publisher","first-page":"1161","DOI":"10.1002\/mus.70003","article-title":"Aging accelerates degradation of human neuromuscular junction following peripheral nerve injury","volume":"72","author":"Gonzales","year":"2025","journal-title":"Muscle Nerve"},{"key":"B10","doi-asserted-by":"publisher","first-page":"123753","DOI":"10.1016\/j.wneu.2025.123753","article-title":"Evaluating ChatGPT o1's capabilities in peripheral nerve surgery: advancing artificial intelligence in clinical practice","volume":"196","author":"Leypold","year":"2025","journal-title":"World Neurosurg"},{"key":"B11","doi-asserted-by":"publisher","first-page":"1526288","DOI":"10.3389\/fonc.2024.1526288","article-title":"Evaluating ChatGPT-4o as a decision support tool in multidisciplinary sarcoma tumor boards: heterogeneous performance across various specialties","volume":"14","author":"Ammo","year":"2024","journal-title":"Front Oncol"},{"key":"B12","doi-asserted-by":"publisher","first-page":"246","DOI":"10.1007\/s12178-025-09961-y","article-title":"A current review of generative AI in medicine: core concepts, applications, and current limitations","volume":"18","author":"Rouzrokh","year":"2025","journal-title":"Curr Rev Musculoskelet Med"},{"key":"B13","doi-asserted-by":"publisher","first-page":"665","DOI":"10.2340\/16501977-0235","article-title":"Reliability and validity of the Medical Research Council (MRC) scale and a modified scale for testing muscle strength in patients with radial palsy","volume":"40","author":"Paternostro-Sluga","year":"2008","journal-title":"J Rehabil Med"},{"key":"B14","doi-asserted-by":"publisher","first-page":"e2532956","DOI":"10.2214\/AJR.25.32956","article-title":"Prompt engineering for large language models in interventional radiology","volume":"225","author":"Dietrich","year":"2025","journal-title":"AJR Am J Roentgenol"},{"key":"B15","doi-asserted-by":"publisher","first-page":"1504532","DOI":"10.3389\/fmed.2024.1504532","article-title":"A guide to prompt design: foundations and applications for healthcare simulationists","volume":"11","author":"Maaz","year":"2024","journal-title":"Front Med (Lausanne)"},{"key":"B16","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1038\/s41746-024-01029-4","article-title":"Prompt engineering in consistency and reliability with the evidence-based guideline for LLMs","volume":"7","author":"Wang","year":"2024","journal-title":"NPJ Digit Med"},{"key":"B17","doi-asserted-by":"publisher","first-page":"1689178","DOI":"10.3389\/frai.2025.1689178","article-title":"In the search for the perfect prompt in medical AI queries","volume":"8","author":"Berghea","year":"2025","journal-title":"Front Artif Intell"},{"key":"B18","doi-asserted-by":"publisher","first-page":"e70312","DOI":"10.1002\/hsr2.70312","article-title":"The impact of artificial intelligence on healthcare: a comprehensive review of advancements in diagnostics, treatment, and operational efficiency","volume":"8","author":"Faiyazuddin","year":"2025","journal-title":"Health Sci Rep"},{"key":"B19","doi-asserted-by":"publisher","first-page":"18994","DOI":"10.1038\/s41598-024-70073-7","article-title":"Innovation and challenges of artificial intelligence technology in personalized healthcare","volume":"14","author":"Li","year":"2024","journal-title":"Sci Rep"},{"key":"B20","doi-asserted-by":"publisher","first-page":"847","DOI":"10.1016\/j.jhsg.2024.07.011","article-title":"Large language models in the diagnosis of hand and peripheral nerve injuries: an evaluation of ChatGPT and the Isabel differential diagnosis generator","volume":"6","author":"AlShenaiber","year":"2024","journal-title":"J Hand Surg Glob Online"},{"key":"B21","doi-asserted-by":"publisher","first-page":"3824","DOI":"10.1016\/j.acra.2025.04.004","article-title":"A deep learning approach for nerve injury classification in brachial plexopathies using magnetic resonance neurography with modified hiking optimization algorithm","volume":"32","author":"Dahou","year":"2025","journal-title":"Acad Radiol"},{"key":"B22","doi-asserted-by":"publisher","first-page":"2052","DOI":"10.1016\/j.ultrasmedbio.2022.05.030","article-title":"Using deep learning for ultrasound images to diagnose carpal tunnel syndrome with high accuracy","volume":"48","author":"Shinohara","year":"2022","journal-title":"Ultrasound Med Biol"},{"key":"B23","doi-asserted-by":"publisher","first-page":"3689","DOI":"10.1109\/TNSRE.2024.3468995","article-title":"A scoping review of machine learning applied to peripheral nerve interfaces","volume":"32","author":"Koh","year":"2024","journal-title":"IEEE Trans Neural Syst Rehabil Eng"},{"key":"B24","doi-asserted-by":"publisher","first-page":"2683555261460252","DOI":"10.1177\/02683555261460252","article-title":"Artificial intelligence in the management of chronic pain and lipedema: a comparative analysis of ChatGPT-5o, Gemini-3, and Perplexity AI in terms of readability and academic reliability","author":"\u00d6zbek","year":"2026","journal-title":"Phlebology"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.1007\/s00586-026-10069-1","article-title":"Performance of large language models in interpreting evidence-based clinical guidelines for lumbar disc herniation with radiculopathy","author":"\u00d6zbek","year":"2026","journal-title":"Eur Spine J"},{"key":"B26","doi-asserted-by":"publisher","first-page":"e0350402","DOI":"10.1371\/journal.pone.0350402","article-title":"Readability, quality, and reliability of AI-generated information on myofascial pain syndrome: a comparative analysis of ChatGPT, Gemini, and Perplexity","volume":"21","author":"Erkin","year":"2026","journal-title":"PLoS One"},{"key":"B27","doi-asserted-by":"publisher","first-page":"95","DOI":"10.4274\/tod.galenos.2025.66664","article-title":"Digital rehabilitation in Parkinson's disease: the role of artificial intelligence-assisted exercise training","volume":"32","author":"\u00d6zbek","year":"2026","journal-title":"Turk J Osteoporos"},{"key":"B28","doi-asserted-by":"publisher","first-page":"e18847","DOI":"10.7717\/peerj.18847","article-title":"Assessing the readability, quality and reliability of responses produced by ChatGPT, Gemini, and Perplexity regarding most frequently asked keywords about low back pain","volume":"13","author":"\u00d6zduran","year":"2025","journal-title":"PeerJ"},{"key":"B29","doi-asserted-by":"publisher","first-page":"21","DOI":"10.31609\/jpmrs.2024-103532","article-title":"Evaluation of artificial intelligence-supported osteoarthritis information texts: content quality and readability analysis","volume":"28","author":"\u00d6zbek","year":"2025","journal-title":"Turkiye Klinikleri J Phys Med Rehabil Sci"},{"key":"B30","doi-asserted-by":"publisher","first-page":"168","DOI":"10.29058\/mjwbs.1881313","article-title":"Artificial intelligence in pain: a comprehensive review","volume":"10","author":"\u00d6zbek","year":"2026","journal-title":"Med J West Black Sea"},{"key":"B31","doi-asserted-by":"publisher","first-page":"12","DOI":"10.4274\/tod.galenos.2024.76743","article-title":"Digital guidance: quality and readability analysis of artificial intelligence-generated spondyloarthropathy texts","volume":"31","author":"\u00d6zbek","year":"2025","journal-title":"Turk J Osteoporos"}],"container-title":["Frontiers in Surgery"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fsurg.2026.1814943\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T05:33:27Z","timestamp":1786599207000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fsurg.2026.1814943\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,13]]},"references-count":31,"alternative-id":["10.3389\/fsurg.2026.1814943"],"URL":"https:\/\/doi.org\/10.3389\/fsurg.2026.1814943","relation":{},"ISSN":["2296-875X"],"issn-type":[{"value":"2296-875X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,13]]},"article-number":"1814943"}}