{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,23]],"date-time":"2026-08-23T17:20:01Z","timestamp":1787505601415,"version":"build-2736575974"},"reference-count":14,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,10,2]],"date-time":"2025-10-02T00:00:00Z","timestamp":1759363200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,10,2]],"date-time":"2025-10-02T00:00:00Z","timestamp":1759363200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Scand J Trauma Resusc Emerg Med"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Large Language Models (LLMs), such as GPT-4o, are increasingly investigated for clinical decision support in emergency medicine. However, their real-world performance in disposition prediction remains insufficiently studied. This study evaluated the diagnostic accuracy of GPT-4o in predicting ED disposition\u2014discharge, ward admission, or ICU admission\u2014in complex emergency respiratory cases requiring pulmonology consultation and chest CT, representing a selective high-acuity subgroup of ED patients.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We conducted a retrospective observational study in a tertiary ED between November 2024 and February 2025. We retrospectively included ED patients with complex respiratory presentations who underwent pulmonology consultation and chest CT, representing a selective high-acuity subgroup rather than the general ED respiratory population. GPT-4o was prompted to predict the most appropriate ED disposition using three progressively enriched input models: Model 1 (age, sex, oxygen saturation, home oxygen therapy, and venous blood gas parameters); Model 2 (Model 1 plus laboratory data); and Model 3 (Model 2 plus chest CT findings). Model performance was assessed using accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and F1 score.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      Among the 221 patients included, 69.2% were admitted to the ward, 9.0% to the intensive care unit (ICU), and 21.7% were discharged. For hospital admission prediction, Model 3 demonstrated the highest sensitivity (91.9%) and overall accuracy (76.5%), but the lowest specificity (20.8%). In contrast, for discharge prediction, Model 3 achieved the highest specificity (91.9%) but the lowest sensitivity (20.8%). Numerical improvements were observed across models, but none reached statistical significance (all\n                      <jats:italic>p<\/jats:italic>\n                      \u2009&gt;\u20090.22). Model 1 therefore performed comparably to Models 2\u20133 while being less complex. Among patients who were discharged despite GPT-4o predicting admission, the 14-day ED re-presentation rates were 23.8% (5\/21) for Model 1, 30.0% (9\/30) for Model 2, and 28.9% (11\/38) for Model 3.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>GPT-4o demonstrated high sensitivity in identifying ED patients requiring hospital admission, particularly those needing intensive care, when provided with progressively enriched clinical input. However, its low sensitivity for discharge prediction resulted in frequent overtriage, limiting its utility for autonomous decision-making. This proof-of-concept study demonstrates GPT-4o\u2019s capacity to stratify disposition decisions in complex respiratory cases under varying levels of limited input data. However, these findings should be interpreted in light of key limitations, including the selective high-acuity cohort and the absence of vital signs, and require prospective validation before clinical implementation.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1186\/s13049-025-01475-3","type":"journal-article","created":{"date-parts":[[2025,10,2]],"date-time":"2025-10-02T12:36:06Z","timestamp":1759408566000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Evaluating GPT-4o for emergency disposition of complex respiratory cases with pulmonology consultation: a diagnostic accuracy study"],"prefix":"10.1186","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-5359-6335","authenticated-orcid":false,"given":"Cem","family":"Y\u0131ld\u0131r\u0131m","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-3173-8994","authenticated-orcid":false,"given":"Ahmet","family":"Aykut","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9653-3236","authenticated-orcid":false,"given":"Ertu\u011f","family":"G\u00fcnsoy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3865-8364","authenticated-orcid":false,"given":"Mehmet Veysel","family":"\u00d6nc\u00fcl","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,10,2]]},"reference":[{"key":"1475_CR1","doi-asserted-by":"publisher","first-page":"8236","DOI":"10.1038\/s41467-024-52415-1","volume":"15","author":"CYK Williams","year":"2024","unstructured":"Williams CYK, Miao BY, Kornblith AE, Butte AJ. Evaluating the use of large Language models to provide clinical recommendations in the emergency department. Nat Commun. 2024;15:8236.","journal-title":"Nat Commun"},{"key":"1475_CR2","doi-asserted-by":"publisher","first-page":"e56110","DOI":"10.2196\/56110","volume":"26","author":"JM Hoppe","year":"2024","unstructured":"Hoppe JM, Auer MK, Str\u00fcven A, Massberg S, Stremmel C. ChatGPT with GPT-4 outperforms emergency department physicians in diagnostic accuracy: retrospective analysis. J Med Internet Res. 2024;26:e56110.","journal-title":"J Med Internet Res"},{"issue":"1","key":"1475_CR3","doi-asserted-by":"publisher","first-page":"22106","DOI":"10.1038\/s41598-024-73229-7","volume":"14","author":"C Colakca","year":"2024","unstructured":"Colakca C, Erg\u0131n M, Ozensoy HS, Sener A, Guru S, Ozhasenekler A. Emergency department triaging using ChatGPT based on emergency severity index principles: a cross-sectional study. Sci Rep. 2024;14(1):22106.","journal-title":"Sci Rep"},{"key":"1475_CR4","doi-asserted-by":"publisher","first-page":"e53297","DOI":"10.2196\/53297","volume":"26","author":"L Masanneck","year":"2024","unstructured":"Masanneck L, Schmidt L, Seifert A, K\u00f6lsche T, Huntemann N, Jansen R, et al. Triage performance across large Language models, chatgpt, and untrained Doctors in emergency medicine: comparative study. J Med Internet Res. 2024;26:e53297.","journal-title":"J Med Internet Res"},{"issue":"1","key":"1475_CR5","first-page":"e60","volume":"12","author":"N Kaboudi","year":"2024","unstructured":"Kaboudi N, Firouzbakht S, Shahir Eftekhar M, Fayazbakhsh F, Joharivarnoosfaderani N, Ghaderi S, et al. Diagnostic accuracy of ChatGPT for patients\u2019 triage; a systematic review and Meta-Analysis. Arch Acad Emerg Med. 2024;12(1):e60.","journal-title":"Arch Acad Emerg Med"},{"key":"1475_CR6","unstructured":"Mehandru N, Golchini N, Bamman D, Zack T, Molina MF, Alaa A. ER-REASON: A Benchmark Dataset for LLM-Based Clinical Reasoning in the Emergency Room [Internet]. arXiv; 2025 [cited 2025 Jun 9]. Available from: http:\/\/arxiv.org\/abs\/2505.22919"},{"key":"1475_CR7","unstructured":"ctv.veeva. com [Internet]. [cited 2025 Jun 9]. Multi-Disciplinary Treatment on the Anthropomorphism of Large Language Models. Available from: https:\/\/ctv.veeva.com\/study\/multi-disciplinary-treatment-on-the-anthropomorphism-of-large-language-models"},{"key":"1475_CR8","doi-asserted-by":"publisher","first-page":"36","DOI":"10.21037\/jmai-24-100","volume":"7","author":"K Tang","year":"2024","unstructured":"Tang K, Reisler J, Rose C, Suffoletto B, Kim D. GPT-4 accurately classifies the clinical actionability of emergency department imaging reports. J Med Artif Intell. 2024;7:36\u201336.","journal-title":"J Med Artif Intell"},{"issue":"7","key":"1475_CR9","doi-asserted-by":"publisher","first-page":"e046598","DOI":"10.1136\/bmjopen-2020-046598","volume":"11","author":"T Trinh","year":"2021","unstructured":"Trinh T, Elfergani A, Bann M. Qualitative analysis of disposition decision making for patients referred for admission from the emergency department without definite medical acuity. BMJ Open. 2021;11(7):e046598.","journal-title":"BMJ Open"},{"issue":"1","key":"1475_CR10","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1111\/jnu.13024","volume":"57","author":"N Yi","year":"2025","unstructured":"Yi N, Baik D, Baek G. The effects of applying artificial intelligence to triage in the emergency department: A systematic review of prospective studies. J Nurs Scholarsh. 2025;57(1):105\u201318.","journal-title":"J Nurs Scholarsh"},{"key":"1475_CR11","doi-asserted-by":"crossref","unstructured":"Gebrael G, Sahu KK, Chigarira B, Tripathi N, Mathew Thomas V, Sayegh N et al. Enhancing triage efficiency and accuracy in emergency rooms for patients with metastatic prostate cancer: A retrospective analysis of artificial Intelligence-Assisted triage using ChatGPT 4.0. Cancers (Basel). 2023;15(14):3717.","DOI":"10.3390\/cancers15143717"},{"key":"1475_CR12","doi-asserted-by":"publisher","first-page":"e53787","DOI":"10.2196\/53787","volume":"12","author":"C Preiksaitis","year":"2024","unstructured":"Preiksaitis C, Ashenburg N, Bunney G, Chu A, Kabeer R, Riley F, et al. The role of large Language models in transforming emergency medicine: scoping review. JMIR Med Inf. 2024;12:e53787.","journal-title":"JMIR Med Inf"},{"key":"1475_CR13","doi-asserted-by":"publisher","first-page":"100059","DOI":"10.1016\/j.hfh.2023.100059","volume":"4","author":"RA Rutkowski","year":"2023","unstructured":"Rutkowski RA, Scheer E, Carlson C, Parks R, Pulia MS, Patterson BW, et al. A scoping review of work system elements that influence emergency department disposition decision-making. Hum Factors Healthc. 2023;4:100059.","journal-title":"Hum Factors Healthc"},{"key":"1475_CR14","unstructured":"A Practical Guide to the Utilization of ChatGPT in the Emergency Department. A Systematic Review of Current Applications, Future Directions, and Limitations | Cureus [Internet]. [cited 2025 Jun 9]. Available from: https:\/\/www.cureus.com\/articles\/346933-a-practical-guide-to-the-utilization-of-chatgpt-in-the-emergency-department-a-systematic-review-of-current-applications-future-directions-and-limitations#!\/"}],"container-title":["Scandinavian Journal of Trauma, Resuscitation and Emergency Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13049-025-01475-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s13049-025-01475-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13049-025-01475-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,2]],"date-time":"2025-10-02T12:36:07Z","timestamp":1759408567000},"score":1,"resource":{"primary":{"URL":"https:\/\/sjtrem.biomedcentral.com\/articles\/10.1186\/s13049-025-01475-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,2]]},"references-count":14,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["1475"],"URL":"https:\/\/doi.org\/10.1186\/s13049-025-01475-3","relation":{},"ISSN":["1757-7241"],"issn-type":[{"value":"1757-7241","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,2]]},"assertion":[{"value":"29 June 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 September 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 October 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The study was approved by the Ethics Committee of Van Education and Research Hospital (Approval No: GOKAEK\/2025-04-09). All methods were performed in accordance with the relevant guidelines and regulations, including the Declaration of Helsinki.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"Not applicable. Written informed consent was waived by the ethics committee due to the use of de-identified retrospective data.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to participate"}},{"value":"The authors declare no competing interests.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"159"}}