{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T06:53:23Z","timestamp":1781506403601,"version":"3.54.1"},"reference-count":17,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2026,6,14]],"date-time":"2026-06-14T00:00:00Z","timestamp":1781395200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Medical Sciences"],"abstract":"<jats:p>Background: Chest radiography remains central to post-procedural assessment of central venous catheter (CVC) placement in intensive care units. Multimodal large language models (MLLMs) can process medical images, but their reliability for practical radiography tasks remains uncertain. This study assessed the diagnostic performance of MLLMs and intensivists for CVC access classification, CVC tip assessment, and pneumothorax-related radiographic findings. Methods: In this retrospective diagnostic performance study, consecutive portable anteroposterior chest radiographs obtained after CVC placement in adult critically ill patients were independently evaluated by four intensivists and five MLLMs. A radiologist consensus served as the reference standard. Interobserver agreement and diagnostic performance were assessed using Fleiss\u2019 kappa, Gwet AC1, Cohen\u2019s kappa, accuracy, sensitivity, specificity, precision, F1 score, balanced accuracy, and Matthews correlation coefficient. Results: The final cohort included 183 unique radiographs. Intensivist reviewers showed high performance for CVC access classification but lower and more heterogeneous performance for CVC tip-position assessment. Among MLLMs, CVC access accuracy ranged from 0.339 to 0.874, whereas CVC tip assessment was dominated by almost universal classification of tips as appropriate, with near-zero specificity and chance-level balanced accuracy. For pneumothorax-related findings, all MLLMs classified every case as negative. Intensivist reviewers had higher balanced accuracy than MLLMs for CVC access classification (difference, 0.420; 95% CI, 0.349\u20130.490; p &lt; 0.001) and CVC tip assessment (difference, 0.247; 95% CI, 0.205\u20130.290; p &lt; 0.001). Pneumothorax analyses were exploratory because only five positive cases were present. Conclusions: The evaluated MLLMs showed unreliable diagnostic performance compared with experienced intensivists. Apparent performance was influenced by class imbalance and dominant-response behavior, supporting cautious task-specific validation and complete diagnostic performance reporting.<\/jats:p>","DOI":"10.3390\/medsci14020315","type":"journal-article","created":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T05:59:47Z","timestamp":1781503187000},"page":"315","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Diagnostic Performance of Multimodal Large Language Models for Central Venous Catheter Assessment Chest Radiographs in the Intensive Care Unit"],"prefix":"10.3390","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0889-9626","authenticated-orcid":false,"given":"Christina-Chrysanthi","family":"Theocharidou","sequence":"first","affiliation":[{"name":"1st Intensive Care Unit, General Hospital of Thessaloniki \u201cG. Papanikolaou\u201d, 57010 Thessaloniki, Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7823-071X","authenticated-orcid":false,"given":"Zafeiris","family":"Tsinaris","sequence":"additional","affiliation":[{"name":"Department of Microbiology, AHEPA University Hospital, School of Medicine, Aristotle University of Thessaloniki, 54636 Thessaloniki, Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christos","family":"Karachristos","sequence":"additional","affiliation":[{"name":"1st Intensive Care Unit, General Hospital of Thessaloniki \u201cG. Papanikolaou\u201d, 57010 Thessaloniki, Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8601-2230","authenticated-orcid":false,"given":"Anastasia","family":"Theocharidou","sequence":"additional","affiliation":[{"name":"Radiology Department, Asklipios Diagnostic Center, 54622 Thessaloniki, Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michail","family":"Kourtidis","sequence":"additional","affiliation":[{"name":"1st Intensive Care Unit, General Hospital of Thessaloniki \u201cG. Papanikolaou\u201d, 57010 Thessaloniki, Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kiriaki","family":"Papadopoulou","sequence":"additional","affiliation":[{"name":"1st Intensive Care Unit, General Hospital of Thessaloniki \u201cG. Papanikolaou\u201d, 57010 Thessaloniki, Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-0367-8656","authenticated-orcid":false,"given":"Athanasia-Marina","family":"Peristeri","sequence":"additional","affiliation":[{"name":"1st Intensive Care Unit, General Hospital of Thessaloniki \u201cG. Papanikolaou\u201d, 57010 Thessaloniki, Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Athanasios","family":"Astreinidis","sequence":"additional","affiliation":[{"name":"Interventional Radiology Unit, Clinical Radiology Department, AHEPA University Hospital, 54636 Thessaloniki, Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anna","family":"Simichanidou","sequence":"additional","affiliation":[{"name":"Radiology Department, Theagenion Anti-Cancer Hospital, 54639 Thessaloniki, Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chrysavgi","family":"Giannaki","sequence":"additional","affiliation":[{"name":"1st Intensive Care Unit, General Hospital of Thessaloniki \u201cG. Papanikolaou\u201d, 57010 Thessaloniki, Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6579-9509","authenticated-orcid":false,"given":"Myrto","family":"Tzimou","sequence":"additional","affiliation":[{"name":"1st Intensive Care Unit, General Hospital of Thessaloniki \u201cG. Papanikolaou\u201d, 57010 Thessaloniki, Greece"},{"name":"Deparment of Medicine, Medical School, Democritus University of Thrace, 68100 Alexandroupoli, Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2081-0337","authenticated-orcid":false,"given":"Evangelos","family":"Kaimakamis","sequence":"additional","affiliation":[{"name":"1st Intensive Care Unit, General Hospital of Thessaloniki \u201cG. Papanikolaou\u201d, 57010 Thessaloniki, Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2872-6084","authenticated-orcid":false,"given":"Vasileios","family":"Voutsas","sequence":"additional","affiliation":[{"name":"1st Intensive Care Unit, General Hospital of Thessaloniki \u201cG. Papanikolaou\u201d, 57010 Thessaloniki, Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vasiliki","family":"Soulountsi","sequence":"additional","affiliation":[{"name":"1st Intensive Care Unit, General Hospital of Thessaloniki \u201cG. Papanikolaou\u201d, 57010 Thessaloniki, Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Athina","family":"Lavrentieva","sequence":"additional","affiliation":[{"name":"1st Intensive Care Unit, General Hospital of Thessaloniki \u201cG. Papanikolaou\u201d, 57010 Thessaloniki, Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,6,14]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"899","DOI":"10.1055\/s-0042-1750041","article-title":"Imaging in the Intensive Care Unit","volume":"43","author":"Toy","year":"2022","journal-title":"Semin. Respir. Crit. Care Med."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"213","DOI":"10.1016\/j.ccm.2024.02.001","article-title":"Chest Intensive Care Unit Imaging","volume":"45","author":"Toussie","year":"2024","journal-title":"Clin. Chest Med."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"38","DOI":"10.23958\/ijirms\/vol06-i01\/1022","article-title":"The Role of Chest X-Ray in Intensive Care Unit","volume":"6","author":"Khair","year":"2021","journal-title":"Int. J. Innov. Res. Med. Sci."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Tanaka, K., Nakada, T., Takahashi, N., Dozono, T., Yoshimura, Y., Yokota, H., Horikoshi, T., Nakaguchi, T., and Shinozaki, K. (2021). Superiority of Supervised Machine Learning on Reading Chest X-Rays in Intensive Care Units. Front. Med., 8.","DOI":"10.3389\/fmed.2021.676277"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"156","DOI":"10.1067\/j.cpradiol.2017.05.012","article-title":"Reducing STAT Portable Chest Radiograph Turnaround Times: A Pilot Study","volume":"47","author":"Rachh","year":"2018","journal-title":"Curr. Probl. Diagn. Radiol."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"100030","DOI":"10.1016\/j.medp.2024.100030","article-title":"Large Language Models Illuminate a Progressive Pathway to Artificial Intelligent Healthcare Assistant","volume":"1","author":"Yuan","year":"2024","journal-title":"Med. Plus"},{"key":"ref_7","unstructured":"Rajpurkar, P., Irvin, J., Zhu, K., Yang, B., Mehta, H., Duan, T., Ding, D., Bagul, A., Langlotz, C., and Shpanskaya, K. (2017). CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learning 2017. arXiv."},{"key":"ref_8","first-page":"234","article-title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","volume":"Volume 9349","author":"Ronneberger","year":"2015","journal-title":"Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Munich, Germany, 5\u20139 October 2015"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"106227","DOI":"10.1016\/j.ijmedinf.2025.106227","article-title":"Vision-Language Models in Diagnostic Imaging: Review of Technical Advances, Clinical Validation, and Practical Deployment","volume":"208","author":"Dutta","year":"2026","journal-title":"Int. J. Med. Inform."},{"key":"ref_10","unstructured":"Sellergren, A., Kazemzadeh, S., Jaroensri, T., Kiraly, A., Traverse, M., Kohlberger, T., Xu, S., Jamil, F., Hughes, C., and Lau, C. (2025). MedGemma Technical Report. arXiv."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"71","DOI":"10.1016\/j.jemermed.2024.12.010","article-title":"Can Gpt-4o Accurately Diagnose Trauma X-Rays? A Comparative Study with Expert Evaluations","volume":"73","year":"2025","journal-title":"J. Emerg. Med."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Y\u0131ld\u0131r\u0131m, A., Cicek, O., and Gen\u00e7, Y.S. (2025). Can AI-Based ChatGPT Models Accurately Analyze Hand\u2013Wrist Radiographs? A Comparative Study. Diagnostics, 15.","DOI":"10.3390\/diagnostics15121513"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"103910","DOI":"10.1016\/j.identj.2025.103910","article-title":"Diagnostic Performance of Large Language Models in Multimodal Analysis of Radiolucent Jaw Lesions","volume":"75","author":"Kim","year":"2025","journal-title":"Int. Dent. J."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Ak\u00e7ay, O., \u00d6zel, A., \u00d6zt\u00fcrk, \u00d6., Acar, T., Tekneci, A.K., Ak\u00e7am, T.\u0130., and G\u00fcrsoy, S. (2025). Evaluation of the Effectiveness of the ChatGPT Artificial Intelligence Application in the Diagnosis of Spontaneous Pneumothorax on Chest Radiograph Interpretation. BMC Pulm. Med., 26.","DOI":"10.1186\/s12890-025-04041-w"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Tong, S., Liu, Z., Zhai, Y., Ma, Y., LeCun, Y., and Xie, S. (2024). Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs. Proceedings of the 2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.","DOI":"10.1109\/CVPR52733.2024.00914"},{"key":"ref_16","unstructured":"Theocharidou, C.C., Tsinaris, Z., Karachristos, C., Theocharidou, A., Kourtidis, M., Papadopoulou, K., Giannaki, C., Kaimakamis, E., Papaioannou, M., and Voutsas, V. (2025, January 25\u201329). Reliability of Multimodal Large Language Models in Evaluating Correct Placement of Central Venous Catheters in Critically Ill Patients. ESICM LIVES 2025, Proceedings of the European Society of Intensive Care Medicine Annual Congress, Munich, Germany. Abstract No. 000518."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1381","DOI":"10.1111\/anae.16727","article-title":"Association of Anaesthetists Guidelines: Safe Vascular Access 2025","volume":"80","author":"Johnston","year":"2025","journal-title":"Anaesthesia"}],"container-title":["Medical Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2076-3271\/14\/2\/315\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T06:19:54Z","timestamp":1781504394000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2076-3271\/14\/2\/315"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,14]]},"references-count":17,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026,6]]}},"alternative-id":["medsci14020315"],"URL":"https:\/\/doi.org\/10.3390\/medsci14020315","relation":{},"ISSN":["2076-3271"],"issn-type":[{"value":"2076-3271","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,14]]}}}