{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T13:19:34Z","timestamp":1790169574456,"version":"4.1.0"},"reference-count":10,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T00:00:00Z","timestamp":1776384000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T00:00:00Z","timestamp":1779840000000},"content-version":"vor","delay-in-days":40,"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\/Objective<\/jats:title>\n                    <jats:p>Spontaneous pneumothorax (SP) commonly presents to the emergency department (ED), and clinicians must rapidly decide between conservative care and tube thoracostomy. Most artificial intelligence tools focus on pneumothorax detection rather than quantitative size estimation and actionable management recommendations. We aimed to evaluate whether a vision-enabled generative pre-trained transformer (GPT) model could estimate apical SP depth on chest radiographs (CXRs) and predict initial ED management.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We conducted a single-center retrospective observational study of adult patients (\u2265\u200918\u00a0years) with confirmed SP on pre-intervention posteroanterior CXR (January 1, 2023\u2013December 31, 2025). GPT received only the CXR plus age and sex and returned laterality, estimated apical depth (Depth_cm), and a binary management recommendation (tube thoracostomy vs conservative). The reference outcome was tube thoracostomy within 24\u00a0h. We calculated diagnostic performance metrics and area under the receiver operating characteristic curve (AUC). We assessed agreement between GPT depth estimates and blinded radiologist measurements using intraclass correlation coefficient (ICC), Bland\u2013Altman analysis, and mean absolute error (MAE).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Among 101 patients, mean age was 33.1\u2009\u00b1\u200914.6\u00a0years and 89 (88.1%) were male; 53 (52.5%) underwent tube thoracostomy within 24\u00a0h. GPT showed sensitivity 86.8% (95% CI, 75.2%\u201393.5%), specificity 93.8% (95% CI, 83.2%\u201397.9%), and accuracy 90.1% (95% CI, 82.7%\u201394.5%), with Cohen\u2019s \u03ba\u2009=\u20090.80 and AUC 0.90 (95% CI, 0.84\u20130.96). Depth agreement was strong (ICC, 0.893), with MAE 0.69\u00a0cm and mean bias\u2009\u22120.51\u00a0cm (95% limits of agreement,\u2009\u2212\u20092.30 to 1.27\u00a0cm).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>In confirmed SP, a vision-enabled GPT model produced apical depth estimates that closely agreed with radiologist measurements and generated management recommendations that substantially matched real-world ED decisions, supporting its potential role as adjunct imaging decision support.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1186\/s13049-026-01616-2","type":"journal-article","created":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T07:39:19Z","timestamp":1776411559000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Chest X-Ray evaluation using GPT for tube thoracostomy or conservative care in non-tension spontaneous pneumothorax"],"prefix":"10.1186","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9653-3236","authenticated-orcid":false,"given":"Ertu\u011f","family":"G\u00fcnsoy","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\/0009-0004-5359-6335","authenticated-orcid":false,"given":"Cem","family":"Y\u0131ld\u0131r\u0131m","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"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8247-2009","authenticated-orcid":false,"given":"Saim","family":"T\u00fcrko\u011flu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,4,17]]},"reference":[{"issue":"1","key":"1616_CR1","doi-asserted-by":"publisher","DOI":"10.1080\/20018525.2024.2307648","volume":"11","author":"SH Skaarup","year":"2024","unstructured":"Skaarup SH, Laursen CB, Hallifax RJ, Iqbal B, B\u00f8dtger U. National survey on management of spontaneous pneumothorax from emergency department to specialised treatment: room for improvement. Eur Clin Respir J. 2024;11(1):2307648. https:\/\/doi.org\/10.1080\/20018525.2024.2307648.","journal-title":"Eur Clin Respir J"},{"issue":"2","key":"1616_CR2","doi-asserted-by":"publisher","first-page":"404","DOI":"10.1016\/j.amjsurg.2021.05.017","volume":"223","author":"BV Udelsman","year":"2022","unstructured":"Udelsman BV, Chang DC, Lanuti M, Mathisen DJ, Muniappan A. Risk factors for recurrent spontaneous pneumothorax: a population level analysis. Am J Surg. 2022;223(2):404\u20139. https:\/\/doi.org\/10.1016\/j.amjsurg.2021.05.017.","journal-title":"Am J Surg"},{"issue":"3","key":"1616_CR3","doi-asserted-by":"publisher","first-page":"s1","DOI":"10.1136\/thorax-2022-219784","volume":"78","author":"ME Roberts","year":"2023","unstructured":"Roberts ME, Rahman NM, Maskell NA, et al. British Thoracic Society guideline for pleural disease. Thorax. 2023;78(3):s1\u201342. https:\/\/doi.org\/10.1136\/thorax-2022-219784.","journal-title":"Thorax"},{"issue":"12","key":"1616_CR4","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2022.47172","volume":"5","author":"JM Hillis","year":"2022","unstructured":"Hillis JM, Bizzo BC, Mercaldo S, et al. Evaluation of an artificial intelligence model for detection of pneumothorax and tension pneumothorax in chest radiographs. JAMA Netw Open. 2022;5(12):e2247172. https:\/\/doi.org\/10.1001\/jamanetworkopen.2022.47172.","journal-title":"JAMA Netw Open"},{"issue":"10","key":"1616_CR5","doi-asserted-by":"publisher","first-page":"602","DOI":"10.1136\/emermed-2023-213620","volume":"41","author":"A Novak","year":"2024","unstructured":"Novak A, Ather S, Gill A, et al. Evaluation of the impact of artificial intelligence-assisted image interpretation on the diagnostic performance of clinicians in identifying pneumothoraces on plain chest X-ray: a multi-case multi-reader study. Emerg Med J. 2024;41(10):602\u20139. https:\/\/doi.org\/10.1136\/emermed-2023-213620.","journal-title":"Emerg Med J"},{"issue":"20","key":"1616_CR6","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics15202639","volume":"15","author":"CW Ho","year":"2025","unstructured":"Ho CW, Wu YL, Chen YC, Ju YJ, Wu MT. Impact of AI assistance in pneumothorax detection on chest radiographs among readers of varying experience. Diagnostics (Basel). 2025;15(20):2639. https:\/\/doi.org\/10.3390\/diagnostics15202639.","journal-title":"Diagnostics (Basel)"},{"issue":"7","key":"1616_CR7","doi-asserted-by":"publisher","first-page":"4374","DOI":"10.1007\/s00330-024-11339-6","volume":"35","author":"S Lee","year":"2025","unstructured":"Lee S, Youn J, Kim H, Kim M, Yoon SH. CXR-LLaVA: a multimodal large language model for interpreting chest X-ray images. Eur Radiol. 2025;35(7):4374\u201386. https:\/\/doi.org\/10.1007\/s00330-024-11339-6.","journal-title":"Eur Radiol"},{"issue":"10243","key":"1616_CR8","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1016\/S0140-6736(20)31043-6","volume":"396","author":"RJ Hallifax","year":"2020","unstructured":"Hallifax RJ, McKeown E, Sivakumar P, et al. Ambulatory management of primary spontaneous pneumothorax: an open-label, randomised controlled trial. Lancet. 2020;396(10243):39\u201349. https:\/\/doi.org\/10.1016\/S0140-6736(20)31043-6.","journal-title":"Lancet"},{"issue":"5","key":"1616_CR9","doi-asserted-by":"publisher","first-page":"405","DOI":"10.1056\/NEJMoa1910775","volume":"382","author":"SGA Brown","year":"2020","unstructured":"Brown SGA, Ball EL, Perrin K, et al. Conservative versus interventional treatment for spontaneous pneumothorax. N Engl J Med. 2020;382(5):405\u201315. https:\/\/doi.org\/10.1056\/NEJMoa1910775.","journal-title":"N Engl J Med"},{"issue":"10","key":"1616_CR10","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2023.36100","volume":"6","author":"J Huang","year":"2023","unstructured":"Huang J, Neill L, Wittbrodt M, et al. Generative artificial intelligence for chest radiograph interpretation in the emergency department. JAMA Netw Open. 2023;6(10):e2336100. https:\/\/doi.org\/10.1001\/jamanetworkopen.2023.36100.","journal-title":"JAMA Netw Open"}],"container-title":["Scandinavian Journal of Trauma, Resuscitation and Emergency Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s13049-026-01616-2","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13049-026-01616-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13049-026-01616-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T02:42:48Z","timestamp":1779849768000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1186\/s13049-026-01616-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,17]]},"references-count":10,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["1616"],"URL":"https:\/\/doi.org\/10.1186\/s13049-026-01616-2","relation":{},"ISSN":["1757-7241"],"issn-type":[{"value":"1757-7241","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,17]]},"assertion":[{"value":"8 January 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 April 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 April 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This study was conducted in accordance with the Declaration of Helsinki. Ethical approval was obtained from the SB\u00dc Van Education and Research Hospital Non-Interventional Clinical Research Ethics Committee (Decision No.: GOKAEK-2025\u201309-16, Date: 07.11.2025). The requirement for informed consent was waived by the ethics committee due to the retrospective design of the study and the use of anonymized data.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"The authors declare no competing interests.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"94"}}