{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T00:46:02Z","timestamp":1792025162497,"version":"4.4.0"},"reference-count":25,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T00:00:00Z","timestamp":1770249600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T00:00:00Z","timestamp":1773014400000},"content-version":"vor","delay-in-days":32,"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>Accurate burn size and depth assessment at first contact guides fluid resuscitation, referral, and operative planning, yet both tasks show meaningful inter-clinician variability. General-purpose multimodal large language models may offer scalable, image-based decision support in emergency care, but prospective benchmarking against clinicians and a robust reference standard remains limited.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We conducted a prospective, single-centre diagnostic accuracy and agreement study in a tertiary emergency department (22 July\u20138 September 2025). Consecutive acute burn presentations (&lt;\u200924\u00a0h) were screened; protocol-conformant cases contributed standardized three-view photographs per anatomically distinct burn region. A multimodal large language model generated region-level estimates of total body surface area (TBSA) contribution and burn depth class. Eighteen emergency physicians independently rated the same images and minimal metadata, blinded to model and reference outputs. A three-member expert panel served as the reference standard by consensus. The primary endpoint was non-inferiority of the model versus the physician median for region-level absolute TBSA error relative to the panel, with a pre-specified margin of 3 percentage points, using patient-level cluster bootstrap for inference. Secondary endpoints included TBSA agreement and depth agreement (quadratic-weighted kappa).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Of 413 screened presentations, 52 patients were enrolled, yielding 64 analyzable burn region-cases (35 pediatric, 29 adult). The model\u2019s mean absolute TBSA error versus the panel was 1.40 percentage points (median 1.00); 87.5% of cases were within\u2009\u00b1\u20093 percentage points and 98.4% within\u2009\u00b1\u20095. The physician median had a mean absolute error of 0.89 percentage points (median 0.75). The paired non-inferiority analysis met the pre-specified criterion (Hodges\u2013Lehmann median \u0394\u2009=\u20090.25; one-sided 95% upper bound\u2009=\u20090.50), indicating the model was non-inferior to physicians for TBSA estimation. In contrast, depth agreement versus the panel was slight for the model (quadratic-weighted kappa 0.14), with systematic underestimation of deeper burns, while physician consensus showed substantially higher agreement (quadratic-weighted kappa 0.65).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>In this prospective emergency department evaluation, a general-purpose multimodal model achieved non-inferior performance to emergency physicians for region-level TBSA estimation but performed substantially worse for burn depth classification. These findings support a narrowly defined adjunct role for TBSA estimation, while depth-dependent decisions should remain clinician-led and require further method development and external validation.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1186\/s13049-026-01577-6","type":"journal-article","created":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T13:27:55Z","timestamp":1770298075000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Multimodal large language model versus emergency physicians for burn assessment: a prospective non-inferiority study"],"prefix":"10.1186","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-3173-8994","authenticated-orcid":false,"given":"Ahmet","family":"Aykut","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4080-4455","authenticated-orcid":false,"given":"Ali R\u0131za","family":"Karay\u0131l","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\/0000-0002-9653-3236","authenticated-orcid":false,"given":"Ertu\u011f","family":"G\u00fcnsoy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5907-9161","authenticated-orcid":false,"given":"Mehmet","family":"Tatl\u0131","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0025-1108","authenticated-orcid":false,"given":"Murat","family":"Avc\u0131","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,2,5]]},"reference":[{"key":"1577_CR1","doi-asserted-by":"publisher","first-page":"e30","DOI":"10.1097\/BCR.0000000000000460","volume":"38","author":"JR Armstrong","year":"2017","unstructured":"Armstrong JR, Willand L, Gonzalez B, Sandhu J, Mosier MJ. Quantitative analysis of estimated burn size accuracy for transfer patients. J Burn Care Res. 2017;38:e30\u20135. https:\/\/doi.org\/10.1097\/BCR.0000000000000460.","journal-title":"J Burn Care Res"},{"key":"1577_CR2","doi-asserted-by":"publisher","DOI":"10.1177\/20595131211019403","volume":"7","author":"S Holm","year":"2021","unstructured":"Holm S, Engstr\u00f6m O, Pet\u00e4j\u00e4 I, Huss F. Does the estimation of burn extent at admission differ from the assessment at discharge? Scars, Burns & Healing. 2021;7:20595131211019403. https:\/\/doi.org\/10.1177\/20595131211019403.","journal-title":"Scars, Burns & Healing"},{"key":"1577_CR3","doi-asserted-by":"publisher","first-page":"493","DOI":"10.1016\/j.burns.2022.05.007","volume":"49","author":"RL Brekke","year":"2023","unstructured":"Brekke RL, Almeland SK, Hufthammer KO, Hansson E. Agreement of clinical assessment of burn size and burn depth between referring hospitals and burn centres: a systematic review. Burns. 2023;49:493\u2013515. https:\/\/doi.org\/10.1016\/j.burns.2022.05.007.","journal-title":"Burns"},{"key":"1577_CR4","doi-asserted-by":"publisher","first-page":"241","DOI":"10.1016\/j.burns.2013.06.019","volume":"40","author":"D Parvizi","year":"2014","unstructured":"Parvizi D, Kamolz L-P, Giretzlehner M, Haller HL, Trop M, Selig H, et al. The potential impact of wrong TBSA estimations on fluid resuscitation in patients suffering from burns: things to keep in mind. Burns. 2014;40:241\u20135. https:\/\/doi.org\/10.1016\/j.burns.2013.06.019.","journal-title":"Burns"},{"key":"1577_CR5","doi-asserted-by":"publisher","DOI":"10.1186\/s12873-017-0151-4","volume":"17","author":"L Blom","year":"2017","unstructured":"Blom L, Boissin C, Allorto N, Wallis L, Hasselberg M, Laflamme L. Accuracy of acute burns diagnosis made using smartphones and tablets: a questionnaire-based study among medical experts. BMC Emerg Med. 2017;17:39. https:\/\/doi.org\/10.1186\/s12873-017-0151-4.","journal-title":"BMC Emerg Med"},{"key":"1577_CR6","doi-asserted-by":"publisher","first-page":"753","DOI":"10.1136\/emj.2007.046730","volume":"24","author":"K Shokrollahi","year":"2007","unstructured":"Shokrollahi K, Sayed M, Dickson W, Potokar T. Mobile phones for the assessment of burns: we have the technology. Emerg Med J. 2007;24:753\u20135. https:\/\/doi.org\/10.1136\/emj.2007.046730.","journal-title":"Emerg Med J"},{"key":"1577_CR7","doi-asserted-by":"publisher","first-page":"1039","DOI":"10.1016\/j.burns.2022.07.006","volume":"49","author":"CW Chang","year":"2023","unstructured":"Chang CW, Ho CY, Lai F, Christian M, Huang SC, Chang DH, et al. Application of multiple deep learning models for automatic burn wound assessment. Burns. 2023;49:1039\u201351. https:\/\/doi.org\/10.1016\/j.burns.2022.07.006.","journal-title":"Burns"},{"key":"1577_CR8","doi-asserted-by":"publisher","DOI":"10.2196\/22798","volume":"9","author":"CW Chang","year":"2021","unstructured":"Chang CW, Lai F, Christian M, Chen YC, Hsu C, Chen YS, et al. Deep learning-assisted burn wound diagnosis: diagnostic model development study. JMIR Med Inform. 2021;9:e22798. https:\/\/doi.org\/10.2196\/22798.","journal-title":"JMIR Med Inform"},{"key":"1577_CR9","doi-asserted-by":"publisher","DOI":"10.3389\/frai.2025.1510905","volume":"8","author":"CW Chang","year":"2025","unstructured":"Chang CW, Wang H, Lai F, Christian M, Chen Huang S, Yi Tsai H. Comparison of 3D and 2D area measurement of acute burn wounds with LiDAR technique and deep learning model. Front Artif Intell. 2025;8:1510905. https:\/\/doi.org\/10.3389\/frai.2025.1510905.","journal-title":"Front Artif Intell"},{"key":"1577_CR10","doi-asserted-by":"publisher","DOI":"10.1080\/16549716.2017.1340254","volume":"10","author":"L Wallis","year":"2017","unstructured":"Wallis L, Hasselberg M, Barkman C, Bogoch I, Broomhead S, Dumont G, et al. A roadmap for the implementation of mHealth innovations for image-based diagnostic support in clinical and public-health settings: a focus on front-line health workers and health-system organizations. Glob Health Action. 2017;10:1340254. https:\/\/doi.org\/10.1080\/16549716.2017.1340254.","journal-title":"Glob Health Action"},{"key":"1577_CR11","doi-asserted-by":"publisher","first-page":"67","DOI":"10.4103\/tjem.tjem_45_25","volume":"25","author":"GB Berikol","year":"2025","unstructured":"Berikol GB, Kanbakan A, Ilhan B, Do\u011fanay F. Mapping artificial intelligence models in emergency medicine: a scoping review on artificial intelligence performance in emergency care and education. Turk J Emerg Med. 2025;25:67\u201391. https:\/\/doi.org\/10.4103\/tjem.tjem_45_25.","journal-title":"Turk J Emerg Med"},{"key":"1577_CR12","doi-asserted-by":"publisher","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 Inform. 2024;12:e53787. https:\/\/doi.org\/10.2196\/53787.","journal-title":"JMIR Med Inform"},{"key":"1577_CR13","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1016\/s0305-4179(99)00047-9","volume":"26","author":"TL Wachtel","year":"2000","unstructured":"Wachtel TL, Berry CC, Wachtel EE, Frank HA. The inter-rater reliability of estimating the size of burns from various burn area chart drawings. Burns. 2000;26:156\u201370. https:\/\/doi.org\/10.1016\/s0305-4179(99)00047-9.","journal-title":"Burns"},{"key":"1577_CR14","doi-asserted-by":"publisher","first-page":"721","DOI":"10.1093\/jbcr\/iraa212","volume":"42","author":"MJ Yoo","year":"2021","unstructured":"Yoo MJ, Pawlukiewicz AJ, Wray JP, Long BJ, Hunter CJ. Interrater Agreement and Reliability of Burn Size Estimations Between Emergency Physicians and Burn Unit. J Burn Care Res. 2021;42:721\u20136. https:\/\/doi.org\/10.1093\/jbcr\/iraa212.","journal-title":"J Burn Care Res"},{"key":"1577_CR15","doi-asserted-by":"publisher","first-page":"1446","DOI":"10.1373\/clinchem.2015.246280","volume":"61","author":"PM Bossuyt","year":"2015","unstructured":"Bossuyt PM, Reitsma JB, Bruns DE, Gatsonis CA, Glasziou PP, Irwig L, et al. STARD 2015: An Updated List of Essential Items for Reporting Diagnostic Accuracy Studies. Clin Chem. 2015;61:1446\u201352. https:\/\/doi.org\/10.1373\/clinchem.2015.246280.","journal-title":"Clin Chem"},{"key":"1577_CR16","doi-asserted-by":"publisher","first-page":"3283","DOI":"10.1038\/s41591-025-03953-8","volume":"31","author":"V Sounderajah","year":"2025","unstructured":"Sounderajah V, Guni A, Liu X, Collins GS, Karthikesalingam A, Markar SR, et al. The STARD-AI reporting guideline for diagnostic accuracy studies using artificial intelligence. Nat Med. 2025;31:3283\u20139. https:\/\/doi.org\/10.1038\/s41591-025-03953-8.","journal-title":"Nat Med"},{"key":"1577_CR17","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1177\/000313481508100131","volume":"81","author":"DS Swords","year":"2015","unstructured":"Swords DS, Hadley ED, Swett KR, Pranikoff T. Total body surface area overestimation at referring institutions in children transferred to a burn center. Am Surg. 2015;81:56\u201363. https:\/\/doi.org\/10.1177\/000313481508100131.","journal-title":"Am Surg"},{"key":"1577_CR18","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1111\/wrr.12189","volume":"22","author":"MJ Hop","year":"2014","unstructured":"Hop MJ, Polinder S, van der Vlies CH, Middelkoop E, van Baar ME. Costs of burn care: a systematic review. Wound Repair Regen. 2014;22:436\u201350. https:\/\/doi.org\/10.1111\/wrr.12189.","journal-title":"Wound Repair Regen"},{"key":"1577_CR19","doi-asserted-by":"publisher","first-page":"833","DOI":"10.1016\/j.burns.2006.10.404","volume":"33","author":"DJ McGill","year":"2007","unstructured":"McGill DJ, S\u00f8rensen K, MacKay IR, Taggart I, Watson SB. Assessment of burn depth: a prospective, blinded comparison of laser Doppler imaging and videomicroscopy. Burns. 2007;33:833\u201342. https:\/\/doi.org\/10.1016\/j.burns.2006.10.404.","journal-title":"Burns"},{"key":"1577_CR20","doi-asserted-by":"publisher","first-page":"1802951","DOI":"10.1080\/16549716.2020.1802951","volume":"13","author":"L Blom","year":"2020","unstructured":"Blom L. mHealth for image-based diagnostics of acute burns in resource-poor settings: studies on the role of experts and the accuracy of their assessments. Glob Health Action. 2020;13:1802951. https:\/\/doi.org\/10.1080\/16549716.2020.1802951.","journal-title":"Glob Health Action"},{"issue":"4","key":"1577_CR21","doi-asserted-by":"publisher","first-page":"281","DOI":"10.3390\/ebj2040020","volume":"2","author":"C Boissin","year":"2021","unstructured":"Boissin C, Laflamme L. Accuracy of image-based automated diagnosis in the identification and classification of acute burn injuries. A systematic review. Eur Burn J. 2021;2(4):281\u201392. https:\/\/doi.org\/10.3390\/ebj2040020.","journal-title":"Eur Burn J"},{"key":"1577_CR22","doi-asserted-by":"publisher","first-page":"6","DOI":"10.1093\/jbcr\/irae121","volume":"46","author":"JJ Lee","year":"2025","unstructured":"Lee JJ, Abdolahnejad M, Morzycki A, Freeman T, Chan H, Hong C, et al. Comparing artificial intelligence guided image assessment to current methods of burn assessment. J Burn Care Res. 2025;46:6\u201313. https:\/\/doi.org\/10.1093\/jbcr\/irae121.","journal-title":"J Burn Care Res"},{"key":"1577_CR23","doi-asserted-by":"publisher","DOI":"10.1016\/j.isci.2024.109713","volume":"27","author":"X Meng","year":"2024","unstructured":"Meng X, Yan X, Zhang K, Liu D, Cui X, Yang Y, et al. The application of large language models in medicine: a scoping review. iScience. 2024;27:109713. https:\/\/doi.org\/10.1016\/j.isci.2024.109713.","journal-title":"iScience"},{"key":"1577_CR24","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-92096-4","volume":"15","author":"PKB Rangaiah","year":"2025","unstructured":"Rangaiah PKB, Kumar BPP, Huss F, Augustine R. Precision diagnosis of burn injuries using imaging and predictive modeling for clinical applications. Sci Rep. 2025;15:7604. https:\/\/doi.org\/10.1038\/s41598-025-92096-4.","journal-title":"Sci Rep"},{"key":"1577_CR25","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2024.40969","volume":"7","author":"E Goh","year":"2024","unstructured":"Goh E, Gallo R, Hom J, Strong E, Weng Y, Kerman H, et al. Large language model influence on diagnostic reasoning: a randomized clinical trial. JAMA Netw Open. 2024;7:e2440969. https:\/\/doi.org\/10.1001\/jamanetworkopen.2024.40969.","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\/s13049-026-01577-6","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13049-026-01577-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13049-026-01577-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T11:58:29Z","timestamp":1773057509000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1186\/s13049-026-01577-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,5]]},"references-count":25,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["1577"],"URL":"https:\/\/doi.org\/10.1186\/s13049-026-01577-6","relation":{},"ISSN":["1757-7241"],"issn-type":[{"value":"1757-7241","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,5]]},"assertion":[{"value":"18 December 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 February 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 February 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 approved by the Institutional Ethics Committee of SBU. Van Education and Research Hospital (Non-Interventional Clinical Research Ethics Committee) on 09 May 2025 (approval number: GOKAEK\/2025\u201304-06). The study was conducted in accordance with the Declaration of Helsinki and local regulations. Written informed consent for study participation and clinical photography was obtained from all adult participants. For paediatric patients, written informed consent was obtained from a parent or legal guardian, with age-appropriate assent obtained from the child when feasible.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"All clinical photographs used in this study were de-identified prior to analysis. Written informed consent for publication of anonymised images and data was obtained from all adult participants, and from parents or legal guardians for paediatric participants.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"54"}}