{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T04:23:00Z","timestamp":1783052580549,"version":"3.54.6"},"reference-count":23,"publisher":"MDPI AG","issue":"13","license":[{"start":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T00:00:00Z","timestamp":1782259200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JCM"],"abstract":"<jats:p>Background: Dedicated artificial intelligence (AI) systems for fracture detection already exist, yet general-purpose multimodal models are increasingly accessible to clinicians despite not being developed or formally validated as medical devices. Their behavior in focused orthopedic imaging tasks remains insufficiently characterized. Purpose: To characterize how two accessible general-purpose multimodal models interpret AP pelvis radiographs with hip fractures, focusing on context dependence, overconfidence, and complementary error patterns within a surgically confirmed positive-only cohort. This was a behavioral characterization study of a fracture-positive cohort, not a diagnostic accuracy evaluation. Methods: In April 2026, we retrospectively studied 214 surgically confirmed hip fractures on AP pelvis radiographs using two general-purpose multimodal models under six prompting conditions. In runs A\u2013D, the models were explicitly told that a hip fracture was present and were asked to classify it; in runs E\u2013F, they were not told whether a hip fracture was present. Each image was rerun de novo in a separate chat session through vendor APIs using a fixed base prompt and no image preprocessing. We recorded hip-fracture detection, correct laterality, coarse fracture pattern, intracapsular displacement, AO\/OTA grading, subtrochanteric identification, and self-reported confidence. Because the cohort contained hip fractures only, we report fracture-detection rates and classification performance within a positive-only cohort rather than full diagnostic-accuracy metrics. Results: Using the more conservative endpoint of hip-fracture detection with correct laterality, GPT-5.4 was correct in 79.0% and 86.4% of cases in runs E and F, whereas Gemini was correct in 80.4% and 93.5%, respectively. When outputs from both models were combined, this endpoint reached 89.7% in run E and 96.7% in run F, indicating complementary rather than redundant error patterns. Incorrect laterality cues markedly degraded performance, from 90.7% to 66.4% in GPT-5.4 and from 97.7% to 57.0% in Gemini. Performance remained limited for treatment-relevant subtyping, particularly AO\/OTA grading and subtrochanteric identification. Both models frequently remained highly confident when wrong, and self-reported confidence did not reliably distinguish correct from incorrect outputs. Conclusions: Accessible general-purpose multimodal models showed partial capability for coarse hip-fracture interpretation, but they remained context-sensitive, unreliable for treatment-relevant subtyping, and highly confident even when incorrect. Their complementary error patterns are hypothesis-generating rather than evidence of clinical readiness. On the basis of these findings, we do not support unvalidated or uncontrolled clinical use of such models. As access to these tools expands, explicit usage boundaries, minimum performance expectations, repeated local revalidation, and sustained human oversight become increasingly necessary.<\/jats:p>","DOI":"10.3390\/jcm15134919","type":"journal-article","created":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T05:48:16Z","timestamp":1782366496000},"page":"4919","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Between Accessibility and Reliability: High Confidence, Low Control in General-Purpose Multimodal Models for Hip Fracture Radiograph Interpretation"],"prefix":"10.3390","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-4749-7691","authenticated-orcid":false,"given":"Hadar","family":"Gan-Or","sequence":"first","affiliation":[{"name":"Department of Orthopedic Surgery, Hillel Yaffe Medical Center, Hadera 3820302, Israel"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-9998-0818","authenticated-orcid":false,"given":"Shaked","family":"Ankol","sequence":"additional","affiliation":[{"name":"Ruth and Bruce Rappaport Faculty of Medicine, Technion\u2014Israel Institute of Technology, Haifa 3525433, Israel"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7602-3156","authenticated-orcid":false,"given":"Guy","family":"Ben Arie","sequence":"additional","affiliation":[{"name":"Department of Orthopedic Surgery, Tel Aviv Sourasky Medical Center, Tel Aviv 6423906, Israel"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4524-9120","authenticated-orcid":false,"given":"Itay","family":"Ashkenazi","sequence":"additional","affiliation":[{"name":"Department of Orthopedic Surgery, Tel Aviv Sourasky Medical Center, Tel Aviv 6423906, Israel"},{"name":"Gray Faculty of Medical and Health Sciences, Tel Aviv University, Tel Aviv 6997801, Israel"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2468-3091","authenticated-orcid":false,"given":"Yaniv","family":"Warschawski","sequence":"additional","affiliation":[{"name":"Department of Orthopedic Surgery, Tel Aviv Sourasky Medical Center, Tel Aviv 6423906, Israel"},{"name":"Gray Faculty of Medical and Health Sciences, Tel Aviv University, Tel Aviv 6997801, Israel"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,6,24]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"50","DOI":"10.1148\/radiol.211785","article-title":"Artificial Intelligence in Fracture Detection: A Systematic Review and Meta-Analysis","volume":"304","author":"Kuo","year":"2022","journal-title":"Radiology"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"23053","DOI":"10.1038\/s41598-024-73058-8","article-title":"Artificial intelligence in commercial fracture detection products: A systematic review and meta-analysis of diagnostic test accuracy","volume":"14","author":"Husarek","year":"2024","journal-title":"Sci. Rep."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"e233391","DOI":"10.1001\/jamanetworkopen.2023.3391","article-title":"Artificial Intelligence for Hip Fracture Detection and Outcome Prediction: A Systematic Review and Meta-analysis","volume":"6","author":"Lex","year":"2023","journal-title":"JAMA Netw. Open"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"e190023","DOI":"10.1148\/ryai.2020190023","article-title":"Automatic Hip Fracture Identification and Functional Subclassification with Deep Learning","volume":"2","author":"Krogue","year":"2020","journal-title":"Radiol. Artif. Intell."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"527","DOI":"10.21037\/qims-23-814","article-title":"Development and validation of a deep-learning model for the detection of non-displaced femoral neck fractures with anteroposterior and lateral hip radiographs","volume":"14","author":"Wang","year":"2024","journal-title":"Quant. Imaging Med. Surg."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1166","DOI":"10.1007\/s11604-025-01754-0","article-title":"Added value of artificial intelligence for the detection of pelvic and hip fractures","volume":"43","author":"Jaillat","year":"2025","journal-title":"Jpn. J. Radiol."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"314","DOI":"10.1177\/02841851261417239","article-title":"Hip fracture detection on radiographs using an artificial intelligence-based support tool: A diagnostic accuracy study","volume":"67","author":"Bonde","year":"2026","journal-title":"Acta Radiol."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"518","DOI":"10.1038\/s41746-025-01923-5","article-title":"Comparative analysis of AI support levels in clinical interpretation of traumatic pelvic radiographs","volume":"8","author":"Tee","year":"2025","journal-title":"npj Digit. Med."},{"key":"ref_9","unstructured":"National Institute for Health and Care Excellence (2025). Artificial Intelligence (AI) Technologies to Help Detect Fractures on X-Rays in Urgent Care: Early Value Assessment (HTG739), NICE."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"924","DOI":"10.1038\/s41591-022-01772-9","article-title":"Reporting guideline for the early-stage clinical evaluation of decision support systems driven by artificial intelligence: DECIDE-AI","volume":"28","author":"Vasey","year":"2022","journal-title":"Nat. Med."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1364","DOI":"10.1038\/s41591-020-1034-x","article-title":"Reporting guidelines for clinical trial reports for interventions involving artificial intelligence: The CONSORT-AI extension","volume":"26","author":"Liu","year":"2020","journal-title":"Nat. Med."},{"key":"ref_12","unstructured":"World Health Organization (2021). Ethics and Governance of Artificial Intelligence for Health, WHO."},{"key":"ref_13","unstructured":"The Royal College of Radiologists (2024). AI Deployment Fundamentals for Medical Imaging, RCR."},{"key":"ref_14","unstructured":"The Royal College of Radiologists (2026). Post-Deployment Monitoring and Safety Reporting of AI Medical Imaging Devices in Clinical Practice, RCR."},{"key":"ref_15","unstructured":"US Food and Drug Administration (2025). Marketing Submission Recommendations for a Predetermined Change Control Plan for Artificial Intelligence-Enabled Device Software Functions."},{"key":"ref_16","unstructured":"US Food and Drug Administration, Health Canada, and Medicines and Healthcare Products Regulatory Agency (2024). Transparency for Machine Learning-Enabled Medical Devices: Guiding Principles."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Bray, T. (2017). The JavaScript Object Notation (JSON) Data Interchange Format, RFC Editor. RFC 8259.","DOI":"10.17487\/RFC8259"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"112230","DOI":"10.1016\/j.ejrad.2025.112230","article-title":"Artificial intelligence-assisted detection of fractures on radiographs with BoneView: A systematic review","volume":"190","author":"Kwee","year":"2025","journal-title":"Eur. J. Radiol."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"103189","DOI":"10.1016\/j.radi.2025.103189","article-title":"Evaluation of commercial AI algorithms for the detection of fractures, effusions, and dislocations on real-world clinical data: A prospective registry study","volume":"31","author":"Luiken","year":"2025","journal-title":"Radiography"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"101801","DOI":"10.1016\/j.bonr.2024.101801","article-title":"Classification of AO\/OTA 31A\/B femur fractures in X-ray images using YOLOv8 and advanced data augmentation techniques","volume":"22","author":"Marullo","year":"2024","journal-title":"Bone Rep."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"1434","DOI":"10.1016\/j.injury.2020.10.067","article-title":"Inter- and intra-observer reliability of the new AO\/OTA classification of proximal femur fractures","volume":"52","author":"Chan","year":"2021","journal-title":"Injury"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"3394","DOI":"10.1016\/j.ejrad.2012.03.014","article-title":"Is a lateral view essential in management of hip fracture?","volume":"81","author":"Naqvi","year":"2012","journal-title":"Eur. J. Radiol."},{"key":"ref_23","first-page":"96","article-title":"Management and treatment of femoral neck stress fractures in recreational runners: A report of four cases and review of the literature","volume":"88","author":"Biz","year":"2017","journal-title":"Acta Biomed."}],"container-title":["Journal of Clinical Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2077-0383\/15\/13\/4919\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T04:11:37Z","timestamp":1783051897000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2077-0383\/15\/13\/4919"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,24]]},"references-count":23,"journal-issue":{"issue":"13","published-online":{"date-parts":[[2026,7]]}},"alternative-id":["jcm15134919"],"URL":"https:\/\/doi.org\/10.3390\/jcm15134919","relation":{},"ISSN":["2077-0383"],"issn-type":[{"value":"2077-0383","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,24]]}}}