{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T03:40:52Z","timestamp":1791517252692,"version":"4.3.4"},"reference-count":27,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,7,10]],"date-time":"2025-07-10T00:00:00Z","timestamp":1752105600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,7,10]],"date-time":"2025-07-10T00:00:00Z","timestamp":1752105600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"DOI":"10.13039\/100008792","name":"Novartis Pharma","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100008792","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["npj Digit. Med."],"DOI":"10.1038\/s41746-025-01837-2","type":"journal-article","created":{"date-parts":[[2025,7,10]],"date-time":"2025-07-10T14:15:29Z","timestamp":1752156929000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":16,"title":["Benchmarking vision-language models for diagnostics in emergency and critical care settings"],"prefix":"10.1038","volume":"8","author":[{"given":"Christoph F.","family":"Kurz","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tatiana","family":"Merzhevich","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bjoern M.","family":"Eskofier","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jakob Nikolas","family":"Kather","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Benjamin","family":"Gmeiner","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,7,10]]},"reference":[{"key":"1837_CR1","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1038\/s41591-018-0300-7","volume":"25","author":"EJ Topol","year":"2019","unstructured":"Topol, E. J. High-performance medicine: the convergence of human and artificial intelligence. Nat. Med. 25, 44\u201356 (2019).","journal-title":"Nat. Med."},{"key":"1837_CR2","doi-asserted-by":"publisher","unstructured":"Zhang, Z. & Ni, H. Critical care studies using large language models based on electronic healthcare records: a technical note. J. Intens. Med. https:\/\/doi.org\/10.1016\/j.jointm.2024.09.002 (2024).","DOI":"10.1016\/j.jointm.2024.09.002"},{"key":"1837_CR3","doi-asserted-by":"crossref","unstructured":"Koga, S. & Du, W. From text to image: challenges in integrating vision into ChatGPT for medical image interpretation. Neural Regen. Res. 20, https:\/\/journals.lww.com\/nrronline\/fulltext\/2025\/02000\/from_text_to_image__challenges_in_integrating.25.aspx (2025).","DOI":"10.4103\/NRR.NRR-D-24-00165"},{"key":"1837_CR4","doi-asserted-by":"publisher","unstructured":"Clusmann J. et al. The future landscape of large language models in medicine. Commun. Med. 3, https:\/\/doi.org\/10.1038\/s43856-023-00370-1 (2023).","DOI":"10.1038\/s43856-023-00370-1"},{"key":"1837_CR5","doi-asserted-by":"publisher","first-page":"319","DOI":"10.1001\/jama.2024.21700","volume":"333","author":"S Bedi","year":"2025","unstructured":"Bedi, S. et al. Testing and evaluation of health care applications of large language models. JAMA 333, 319 (2025).","journal-title":"JAMA"},{"key":"1837_CR6","doi-asserted-by":"publisher","unstructured":"Sonoda, Y. et al. Diagnostic performances of GPT-4o, Claude 3 Opus, and Gemini 1.5 Pro in \u201cDiagnosis Please\u201d cases. Jpn J. Radiol. https:\/\/doi.org\/10.1007\/s11604-024-01619-y (2024).","DOI":"10.1007\/s11604-024-01619-y"},{"key":"1837_CR7","doi-asserted-by":"crossref","unstructured":"Kim, S. H. et al. Benchmarking the diagnostic performance of open source LLMs in 1933 Eurorad case reports. NPJ Digit. Med. 8, https:\/\/www.nature.com\/articles\/s41746-025-01488-3 (2025).","DOI":"10.1038\/s41746-025-01488-3"},{"key":"1837_CR8","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1038\/s41586-023-06291-2","volume":"620","author":"K Singhal","year":"2023","unstructured":"Singhal, K. et al. Large language models encode clinical knowledge. Nature 620, 172\u2013180, https:\/\/doi.org\/10.1038\/s41586-023-06291-2 (2023).","journal-title":"Nature"},{"key":"1837_CR9","unstructured":"Liu, X. et al. A generalist medical language model for disease diagnosis assistance. Nat. Med. http:\/\/www.ncbi.nlm.nih.gov\/pubmed\/39779927 (2025)."},{"key":"1837_CR10","doi-asserted-by":"publisher","first-page":"4","DOI":"10.21037\/atm-24-150","volume":"13","author":"MT Chua","year":"2025","unstructured":"Chua, M. T. et al. The role of artificial intelligence in sepsis in the Emergency Department: a narrative review. Ann. Transl. Med. 13, 4\u20134 (2025).","journal-title":"Ann. Transl. Med."},{"key":"1837_CR11","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1038\/s41746-025-01476-7","volume":"8","author":"F Dennst\u00e4dt","year":"2025","unstructured":"Dennst\u00e4dt, F., Hastings, J., Putora, P. M., Schmerder, M. & Cihoric, N. Implementing large language models in healthcare while balancing control, collaboration, costs and security. NPJ Digit Med 8, 143 (2025).","journal-title":"NPJ Digit Med"},{"key":"1837_CR12","doi-asserted-by":"publisher","unstructured":"Riedemann, L., Labonne, M. & Gilbert, S. The path forward for large language models in medicine is open. NPJ Digit. Med. 7, https:\/\/doi.org\/10.1038\/s41746-024-01344-w (2024).","DOI":"10.1038\/s41746-024-01344-w"},{"key":"1837_CR13","doi-asserted-by":"crossref","unstructured":"Ueda, D. et al. Evaluating GPT-4-based ChatGPT\u2019s clinical potential on the NEJM quiz. BMC Digital Health 2, https:\/\/bmcdigitalhealth.biomedcentral.com\/articles\/10.1186\/s44247-023-00058-5. (2024).","DOI":"10.1186\/s44247-023-00058-5"},{"key":"1837_CR14","doi-asserted-by":"publisher","unstructured":"Yang, H. et al. One LLM is not enough: harnessing the power of ensemble learning for medical question answering. J. Med. Internet Res. https:\/\/doi.org\/10.2196\/70080 (2024).","DOI":"10.2196\/70080"},{"key":"1837_CR15","doi-asserted-by":"publisher","unstructured":"Hager, P. et al. Evaluation and mitigation of the limitations of large language models in clinical decision-making. Nat. Med. https:\/\/doi.org\/10.1038\/s41591-024-03097-1 (2024).","DOI":"10.1038\/s41591-024-03097-1"},{"key":"1837_CR16","doi-asserted-by":"crossref","unstructured":"Jin, Q. et al. Hidden flaws behind expert-level accuracy of multimodal GPT-4 vision in medicine. NPJ Digit. Med. 7, https:\/\/www.nature.com\/articles\/s41746-024-01185-7 (2024).","DOI":"10.1038\/s41746-024-01185-7"},{"key":"1837_CR17","doi-asserted-by":"publisher","unstructured":"Longpre, S. et al. Data authenticity, consent, and provenance for AI are all broken: what will it take to fix them? An MIT exploration of generative AI. https:\/\/doi.org\/10.21428\/e4baedd9.a650f77d (2024).","DOI":"10.21428\/e4baedd9.a650f77d"},{"key":"1837_CR18","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-024-03302-1","author":"R Tanno","year":"2024","unstructured":"Tanno, R. et al. Collaboration between clinicians and vision\u2013language models in radiology report generation. Nat. Med https:\/\/doi.org\/10.1038\/s41591-024-03302-1 (2024).","journal-title":"Nat. Med"},{"key":"1837_CR19","unstructured":"Wu, Z. et al. DeepSeek-VL2: mixture-of-experts vision-language models for advanced multimodal understanding. Preprint at http:\/\/arxiv.org\/abs\/2412.10302 (2024)."},{"key":"1837_CR20","unstructured":"Gemma Team. Gemma 3 Technical Report. https:\/\/goo.gle\/Gemma3Report (2025)."},{"key":"1837_CR21","unstructured":"Granite Vision Team, Karlinsky, L. et al. Granite Vision: a lightweight, open-source multimodal model for enterprise Intelligence. Preprint at http:\/\/arxiv.org\/abs\/2502.09927 (2025)."},{"key":"1837_CR22","doi-asserted-by":"crossref","unstructured":"Chen, Z. et al. InternVL: scaling up vision foundation models and aligning for generic visual-linguistic tasks. https:\/\/github.com\/OpenGVLab\/InternVL (2024).","DOI":"10.1109\/CVPR52733.2024.02283"},{"key":"1837_CR23","unstructured":"Abdin, M. et al. Phi-4 technical report. Preprint at http:\/\/arxiv.org\/abs\/2412.08905 (2024)."},{"key":"1837_CR24","unstructured":"Wang, P. et al. Qwen2-VL: enhancing vision-language model\u2019s perception of the world at any resolution. Preprint at http:\/\/arxiv.org\/abs\/2409.12191 (2024)."},{"key":"1837_CR25","unstructured":"Marafioti, A. et al. Smolvlm: redefining small and efficient multimodal models. arXiv preprint arXiv:2504.05299 (2025)."},{"key":"1837_CR26","unstructured":"Hurst, A. et al. GPT-4o system card. Preprint at http:\/\/arxiv.org\/abs\/2410.21276 (2024)."},{"key":"1837_CR27","unstructured":"Bordes, F. et al. An introduction to vision-language modeling. Preprint at http:\/\/arxiv.org\/abs\/2405.17247 (2024)."}],"container-title":["npj Digital Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-01837-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-01837-2","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-01837-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,7]],"date-time":"2025-09-07T04:41:44Z","timestamp":1757220104000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-01837-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,10]]},"references-count":27,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["1837"],"URL":"https:\/\/doi.org\/10.1038\/s41746-025-01837-2","relation":{},"ISSN":["2398-6352"],"issn-type":[{"value":"2398-6352","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,10]]},"assertion":[{"value":"23 April 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 June 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 July 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"C.F.K. and B.G. report employment and stock ownership from Novartis Pharma. B.G. is a Strategic Advisory Board Member at Fraunhofer IZI-BB. B.G. serves as an Associate Editor of npj Digital Medicine and was not involved in the review or decision-making process for this manuscript. J.N.K. declares consulting services for Bioptimus, France; Panakeia, UK; AstraZeneca, UK; and MultiplexDx, Slovakia. Furthermore, J.N.K. holds shares in StratifAI, Germany, Synagen, Germany, Ignition Lab, Germany; J.N.K. has received an institutional research grant by GSK; and has received honoraria by AstraZeneca, Bayer, Daiichi Sankyo, Eisai, Janssen, Merck, MSD, BMS, Roche, Pfizer, and Fresenius. T.M. and B.M.E. have nothing to declare.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"423"}}