{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T03:04:19Z","timestamp":1779851059034,"version":"3.53.1"},"reference-count":47,"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"}],"funder":[{"DOI":"10.13039\/501100002332","name":"Semmelweis University","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100002332","id-type":"DOI","asserted-by":"crossref"}]}],"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>Lung ultrasound is essential for rapid, radiation-free bedside pneumothorax diagnosis but limited by variability in human interpretation. Key gaps include insufficiently large and diverse human datasets, inconsistent image acquisition, lack of rigorous expert benchmarking, and inadequate clinical interpretability of existing artificial intelligence models. We aimed to develop and validate a robust, explainable artificial intelligence (AI) ensemble model addressing these critical gaps.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>With our multidisciplinary team, we developed an explainable soft-voting ensemble model trained on 1,856 diverse ultrasound clips from critically ill patients, healthy volunteers, and tailored cadaver models. Model interpretability was ensured using visualization, with heatmaps validated by expert clinicians. The model\u2019s diagnostic performance was rigorously benchmarked against 11 experienced clinicians using an independent, balanced test set. Statistical analyses included sensitivity, specificity and inter-rater reliability.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      The ensemble model achieved 100% sensitivity (95% CI: 85\u00b78%-100\u00b70%) and 100% specificity (95% CI: 85\u00b78%-100\u00b70%), surpassing expert sensitivity and specificity. Diagnostic performance of experts significantly differed by ultrasound mode, with notably lower specificity in M-mode imaging (\n                      <jats:italic>p<\/jats:italic>\n                      \u2009&lt;\u20090\u00b7001). The AI consistently maintained perfect sensitivity and significantly reduced false positives compared to clinicians across all conditions, including challenging diagnostic scenarios (e.g., subtle pleural motions), and showed excellent generalizability to both cadaveric and clinical cases.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Our explainable AI ensemble robustly matches the consensus-level performance of an expert \"committee,\" significantly reducing diagnostic variability and false-positive diagnoses. This AI tool can serve as a critical second reader, standardize clinical decisions at the bedside, and substantially improve patient safety.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1186\/s13049-026-01614-4","type":"journal-article","created":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T08:07:21Z","timestamp":1776413241000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Explainable transfer learning ensemble AI model for lung ultrasound pneumothorax detection with expert benchmark"],"prefix":"10.1186","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9254-0623","authenticated-orcid":false,"given":"G\u00e1bor","family":"Orosz","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"R\u00f3bert Zsolt","family":"Szab\u00f3","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5482-6989","authenticated-orcid":false,"given":"Marcell","family":"Szab\u00f3","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7117-6351","authenticated-orcid":false,"given":"P\u00e1l","family":"Gyombolai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4993-4926","authenticated-orcid":false,"given":"J\u00f3zsef T.","family":"T\u00f3th","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4501-824X","authenticated-orcid":false,"given":"Tam\u00e1s","family":"Ruttkay","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6791-3080","authenticated-orcid":false,"given":"Tam\u00e1s","family":"Ferenci","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4743-0609","authenticated-orcid":false,"given":"Tam\u00e1s","family":"Ungi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6354-262X","authenticated-orcid":false,"given":"G\u00e1bor","family":"Fichtinger","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1402-1139","authenticated-orcid":false,"given":"Tam\u00e1s","family":"Haidegger","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,4,17]]},"reference":[{"issue":"1","key":"1614_CR1","doi-asserted-by":"publisher","first-page":"72","DOI":"10.1177\/1742271X21994604","volume":"30","author":"S Rovida","year":"2022","unstructured":"Rovida S, Orso D, Naeem S, Vetrugno L, Volpicelli G. Lung ultrasound in blunt chest trauma: A clinical review. Ultrasound. 2022;30(1):72\u20139.","journal-title":"Ultrasound"},{"issue":"3","key":"1614_CR2","doi-asserted-by":"publisher","first-page":"203","DOI":"10.3390\/arm91030017","volume":"91","author":"E Rocca","year":"2023","unstructured":"Rocca E, Zanza C, Longhitano Y, Piccolella F, Romenskaya T, Racca F, et al. Lung ultrasound in critical care and emergency medicine: clinical review. Adv Respir Med. 2023;91(3):203\u201323.","journal-title":"Adv Respir Med"},{"key":"1614_CR3","doi-asserted-by":"publisher","first-page":"1200","DOI":"10.1007\/s00134-019-05725-8","volume":"45","author":"P Mayo","year":"2019","unstructured":"Mayo P, Copetti R, Feller-Kopman D, Mathis G, Maury E, Mongodi S, et al. Thoracic ultrasonography: a narrative review. Intensive Care Med. 2019;45:1200\u201311.","journal-title":"Intensive Care Med"},{"key":"1614_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/cc13016","volume":"17","author":"S Alrajab","year":"2013","unstructured":"Alrajab S, Youssef AM, Akkus NI, Caldito G. Pleural ultrasonography versus chest radiography for the diagnosis of pneumothorax: review of the literature and meta-analysis. Crit Care. 2013;17:1\u20138.","journal-title":"Crit Care"},{"issue":"1","key":"1614_CR5","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1111\/j.1553-2712.2009.00628.x","volume":"17","author":"R Gentry Wilkerson","year":"2010","unstructured":"Gentry Wilkerson R, Stone MB. Sensitivity of bedside ultrasound and supine anteroposterior chest radiographs for the identification of pneumothorax after blunt trauma. Acad Emerg Med. 2010;17(1):11\u20137.","journal-title":"Acad Emerg Med"},{"issue":"4","key":"1614_CR6","first-page":"618","volume":"5","author":"L Chen","year":"2015","unstructured":"Chen L, Zhang Z. Bedside ultrasonography for diagnosis of pneumothorax. Quant Imaging Med Surg. 2015;5(4):618.","journal-title":"Quant Imaging Med Surg"},{"issue":"1","key":"1614_CR7","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1186\/s13089-023-00351-4","volume":"16","author":"L Vetrugno","year":"2024","unstructured":"Vetrugno L, Biasucci DG, Deana C, Spadaro S, Lombardi FA, Longhini F, et al. Lung ultrasound and supine chest X-ray use in modern adult intensive care: mapping 30 years of advancement (1993\u20132023). Ultrasound J. 2024;16(1):7.","journal-title":"Ultrasound J"},{"key":"1614_CR8","unstructured":"Denault A, Girard M, Cavayas YA. Lung Ultrasound in the Critically Ill\u2013The BLUE Protocol: Daniel A. Lichtenstein. Springer International Publishing Switzerland 2016; Hardcover 149eBook 109; 376 pages ISBN 978\u20133\u2013319\u201315370\u20134.\u00a0Cham: Springer; 2016."},{"issue":"1","key":"1614_CR9","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1378\/chest.07-2800","volume":"134","author":"DA Lichtenstein","year":"2008","unstructured":"Lichtenstein DA, Meziere GA. Relevance of lung ultrasound in the diagnosis of acute respiratory failure*: the BLUE protocol. Chest. 2008;134(1):117\u201325.","journal-title":"Chest"},{"key":"1614_CR10","doi-asserted-by":"publisher","DOI":"10.5114\/pjr.2023.128866","volume":"88","author":"P \u0141y\u017aniak","year":"2023","unstructured":"\u0141y\u017aniak P, \u015awi\u0119to\u0144 D, Serafin Z, Szurowska E. Lung ultrasound in a nutshell. Lines, signs, some applications, and misconceptions from a radiologist\u2019s point of view. Pol J Radiol. 2023;88:e294.","journal-title":"Pol J Radiol"},{"issue":"11","key":"1614_CR11","doi-asserted-by":"publisher","first-page":"2681","DOI":"10.1002\/jum.14629","volume":"37","author":"J Avila","year":"2018","unstructured":"Avila J, Smith B, Mead T, Jurma D, Dawson M, Mallin M, et al. Does the Addition of M-Mode to B-Mode Ultrasound Increase the Accuracy of Identification of Lung Sliding in Traumatic Pneumothoraces? J Ultrasound Med. 2018;37(11):2681\u20137.","journal-title":"J Ultrasound Med"},{"issue":"1","key":"1614_CR12","volume":"2014","author":"T Berlet","year":"2014","unstructured":"Berlet T, Etter R. Favourable Experience with M\u2010Mode Sonography in the Diagnosis of Pneumothorax in Two Patients with Thoracic Subcutaneous Emphysema. Case Rep Radiol. 2014;2014(1):906127.","journal-title":"Case Rep Radiol"},{"issue":"5","key":"1614_CR13","doi-asserted-by":"publisher","DOI":"10.3390\/bioengineering10050555","volume":"10","author":"A Bruno","year":"2023","unstructured":"Bruno A, Ignesti G, Salvetti O, Moroni D, Martinelli M. Efficient lung ultrasound classification. Bioengineering. 2023;10(5):555.","journal-title":"Bioengineering"},{"issue":"8","key":"1614_CR14","doi-asserted-by":"publisher","first-page":"69","DOI":"10.12700\/APH.20.8.2023.8.5","volume":"20","author":"G Orosz","year":"2023","unstructured":"Orosz G, Szab\u00f3 RZ, Ungi T, Barr C, Yeung C, Fichtinger G, et al. Lung ultrasound imaging and image processing with artificial intelligence methods for bedside diagnostic examinations. Acta Polytech Hung. 2023;20(8):69\u201387.","journal-title":"Acta Polytech Hung"},{"issue":"15","key":"1614_CR15","doi-asserted-by":"publisher","DOI":"10.3390\/app11156976","volume":"11","author":"M Ja\u0161\u010dur","year":"2021","unstructured":"Ja\u0161\u010dur M, Bundzel M, Mal\u00edk M, Dzian A, Feren\u010d\u00edk N, Babi\u010d F. Detecting the absence of lung sliding in lung ultrasounds using deep learning. Appl Sci. 2021;11(15):6976.","journal-title":"Appl Sci"},{"key":"1614_CR16","unstructured":"Mehanian C, Kulhare S, Millin R, Zheng X, Gregory C, Zhu M, et al., editors. Deep learning-based pneumothorax detection in ultrasound videos. Smart Ultrasound Imaging and Perinatal, Preterm and Paediatric Image Analysis: First International Workshop, SUSI 2019, and 4th International Workshop, PIPPI 2019, Held in Conjunction with MICCAI 2019, Shenzhen, China, October 13 and 17, 2019, Proceedings 4; 2019:\u00a0Cham: Springer."},{"key":"1614_CR17","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2022.105953","volume":"148","author":"B VanBerlo","year":"2022","unstructured":"VanBerlo B, Wu D, Li B, Rahman MA, Hogg G, VanBerlo B, et al. Accurate assessment of the lung sliding artefact on lung ultrasonography using a deep learning approach. Comput Biol Med. 2022;148:105953.","journal-title":"Comput Biol Med"},{"key":"1614_CR18","doi-asserted-by":"crossref","unstructured":"VanBerlo B, Li B, Wong A, Hoey J, Arntfield R, editors. Exploring the utility of self-supervised pretraining strategies for the detection of absent lung sliding in m-mode lung ultrasound. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition; 2023.","DOI":"10.1109\/CVPRW59228.2023.00309"},{"issue":"2","key":"1614_CR19","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11548-022-02765-2","volume":"18","author":"T Zhang","year":"2023","unstructured":"Zhang T, Yan S, Wei G, Yang L, Yu T, Ma Y. Automatic diagnosis of pneumothorax with M-mode ultrasound images based on D-MPL. Int J Comput Assist Radiol Surg. 2023;18(2):303\u201312.","journal-title":"Int J Comput Assist Radiol Surg"},{"issue":"12","key":"1614_CR20","doi-asserted-by":"publisher","DOI":"10.3390\/electronics10121491","volume":"10","author":"M Ranaweera","year":"2021","unstructured":"Ranaweera M, Mahmoud QH. Virtual to real-world transfer learning: a systematic review. Electronics. 2021;10(12):1491.","journal-title":"Electronics"},{"key":"1614_CR21","doi-asserted-by":"publisher","DOI":"10.1183\/16000617.0259-2022","author":"T Sugibayashi","year":"2023","unstructured":"Sugibayashi T, Walston SL, Matsumoto T, Mitsuyama Y, Miki Y, Ueda D. Deep learning for pneumothorax diagnosis: a systematic review and meta-analysis. Eur Respir Rev. 2023. https:\/\/doi.org\/10.1183\/16000617.0259-2022.","journal-title":"Eur Respir Rev"},{"key":"1614_CR22","unstructured":"Akinbo RS, Daramola OA. Ensemble machine learning algorithms for prediction and classification of medical images. Algorithms Models Appl. 2021:59\u201378."},{"issue":"5","key":"1614_CR23","doi-asserted-by":"publisher","first-page":"882","DOI":"10.1038\/s41591-021-01342-5","volume":"27","author":"R Arnaout","year":"2021","unstructured":"Arnaout R, Curran L, Zhao Y, Levine JC, Chinn E, Moon-Grady AJ. An ensemble of neural networks provides expert-level prenatal detection of complex congenital heart disease. Nat Med. 2021;27(5):882\u201391.","journal-title":"Nat Med"},{"key":"1614_CR24","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J, editors. Deep residual learning for image recognition. Proceedings of the IEEE conference on computer vision and pattern recognition; 2016.","DOI":"10.1109\/CVPR.2016.90"},{"key":"1614_CR25","doi-asserted-by":"crossref","unstructured":"Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z, editors. Rethinking the inception architecture for computer vision. Proceedings of the IEEE conference on computer vision and pattern recognition; 2016.","DOI":"10.1109\/CVPR.2016.308"},{"key":"1614_CR26","doi-asserted-by":"crossref","unstructured":"Chollet F, editor Xception: Deep learning with depthwise separable convolutions. Proceedings of the IEEE conference on computer vision and pattern recognition; 2017.","DOI":"10.1109\/CVPR.2017.195"},{"key":"1614_CR27","doi-asserted-by":"crossref","unstructured":"Szegedy C, Ioffe S, Vanhoucke V, Alemi A, editors. Inception-v4, inception-resnet and the impact of residual connections on learning. Proceedings of the AAAI conference on artificial intelligence; 2017.","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"1614_CR28","unstructured":"Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:14091556. 2014."},{"key":"1614_CR29","doi-asserted-by":"crossref","unstructured":"Yan WQ. Transfer Learning and\u00a0Ensemble Learning. Computational Methods for Deep Learning: Theory, Algorithms, and Implementations. Singapore: Springer Nature Singapore; 2023. p. 191\u2013203.","DOI":"10.1007\/978-981-99-4823-9_7"},{"issue":"46","key":"1614_CR30","doi-asserted-by":"publisher","first-page":"1824","DOI":"10.1556\/650.2023.32906","volume":"164","author":"N \u00c1d\u00e1m","year":"2023","unstructured":"\u00c1d\u00e1m N, Orosz G, Berczi M, Ruttkay T. Proposal of a human cadaveric model for bedside ultrasound-based pneumothorax detection. Orv Hetil. 2023;164(46):1824\u201330.","journal-title":"Orv Hetil"},{"issue":"10","key":"1614_CR31","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0276213","volume":"17","author":"G Orosz","year":"2022","unstructured":"Orosz G, Gyombolai P, T\u00f3th JT, Szab\u00f3 M. Reliability and clinical correlations of semi-quantitative lung ultrasound on BLUE points in COVID-19 mechanically ventilated patients: the \u2018BLUE-LUSS\u2019\u2014a feasibility clinical study. PLoS ONE. 2022;17(10):e0276213.","journal-title":"PLoS ONE"},{"issue":"22","key":"1614_CR32","doi-asserted-by":"publisher","first-page":"864","DOI":"10.1556\/650.2023.32795","volume":"164","author":"M Szab\u00f3","year":"2023","unstructured":"Szab\u00f3 M, Orosz G, Iv\u00e1nyi ZD, Darvas K. A mellkas \u00e9s a t\u00fcd\u0151 ultrahangvizsg\u00e1lat\u00e1nak szerepe az \u00e1ltal\u00e1nos \u00e9rz\u00e9stelen\u00edt\u00e9s sor\u00e1n. Orv Hetil. 2023;164(22):864\u201370.","journal-title":"Orv Hetil"},{"issue":"2","key":"1614_CR33","doi-asserted-by":"publisher","first-page":"309","DOI":"10.1002\/jum.16088","volume":"42","author":"L Demi","year":"2023","unstructured":"Demi L, Wolfram F, Klersy C, De Silvestri A, Ferretti VV, Muller M, et al. New international guidelines and consensus on the use of lung ultrasound. J Ultrasound Med. 2023;42(2):309\u201344.","journal-title":"J Ultrasound Med"},{"key":"1614_CR34","doi-asserted-by":"publisher","first-page":"577","DOI":"10.1007\/s00134-012-2513-4","volume":"38","author":"G Volpicelli","year":"2012","unstructured":"Volpicelli G, Elbarbary M, Blaivas M, Lichtenstein DA, Mathis G, Kirkpatrick AW, et al. International evidence-based recommendations for point-of-care lung ultrasound. Intensive Care Med. 2012;38:577\u201391.","journal-title":"Intensive Care Med"},{"key":"1614_CR35","doi-asserted-by":"crossref","unstructured":"Szab\u00f3 RZ, Orosz G, Ungi T, Barr C, Yeung C, Incze R, et al., editors. Automation of lung ultrasound imaging and image processing for bedside diagnostic examinations. 2023 IEEE 17th International Symposium on Applied Computational Intelligence and Informatics (SACI).\u00a0Piscataway: IEEE; 2023.","DOI":"10.1109\/SACI58269.2023.10158672"},{"key":"1614_CR36","doi-asserted-by":"publisher","first-page":"224","DOI":"10.1007\/s00134-010-2079-y","volume":"37","author":"G Volpicelli","year":"2011","unstructured":"Volpicelli G. Sonographic diagnosis of pneumothorax. Intensive Care Med. 2011;37:224\u201332.","journal-title":"Intensive Care Med"},{"issue":"2","key":"1614_CR37","doi-asserted-by":"publisher","first-page":"435","DOI":"10.7863\/ultra.15.02024","volume":"35","author":"BC Smith III","year":"2016","unstructured":"Smith BC III, Avila JM. Mode. ify: a free online tool to generate post hoc M\u2010mode images from any ultrasound clip. J Ultrasound Med. 2016;35(2):435\u20139.","journal-title":"J Ultrasound Med"},{"key":"1614_CR38","unstructured":"Cheng D, Lam EY. Transfer learning U-Net deep learning for lung ultrasound segmentation. arXiv preprint arXiv:211002196. 2021."},{"key":"1614_CR39","doi-asserted-by":"crossref","unstructured":"Yi Z, Wang Y, editors. Transfer learning on interstitial lung disease classification. 2021 International Conference on Signal Processing and Machine Learning (CONF-SPML).\u00a0Piscataway: IEEE; 2021.","DOI":"10.1109\/CONF-SPML54095.2021.00046"},{"issue":"12","key":"1614_CR40","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0261307","volume":"16","author":"S Rajaraman","year":"2021","unstructured":"Rajaraman S, Zamzmi G, Antani SK. Novel loss functions for ensemble-based medical image classification. PLoS ONE. 2021;16(12):e0261307.","journal-title":"PLoS ONE"},{"key":"1614_CR41","doi-asserted-by":"crossref","unstructured":"Chattopadhay A, Sarkar A, Howlader P, Balasubramanian VN, editors. Grad-cam++: Generalized gradient-based visual explanations for deep convolutional networks. 2018 IEEE winter conference on applications of computer vision (WACV).\u00a0Piscataway: IEEE; 2018.","DOI":"10.1109\/WACV.2018.00097"},{"key":"1614_CR42","unstructured":"Cardoso MJ, Li W, Brown R, Ma N, Kerfoot E, Wang Y, et al. Monai: An open-source framework for deep learning in healthcare. arXiv preprint arXiv:221102701. 2022."},{"key":"1614_CR43","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102684","volume":"84","author":"W Jin","year":"2023","unstructured":"Jin W, Li X, Fatehi M, Hamarneh G. Guidelines and evaluation of clinical explainable AI in medical image analysis. Med Image Anal. 2023;84:102684.","journal-title":"Med Image Anal"},{"issue":"3","key":"1614_CR44","doi-asserted-by":"publisher","first-page":"398","DOI":"10.1164\/rccm.201802-0227LE","volume":"198","author":"J-J Rouby","year":"2018","unstructured":"Rouby J-J, Arbelot C, Gao Y, Zhang M, Lv J, An Y, et al. Training for lung ultrasound score measurement in critically ill patients. Am J Respir Crit Care Med. 2018;198(3):398\u2013401.","journal-title":"Am J Respir Crit Care Med"},{"issue":"1","key":"1614_CR45","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/0895-4356(92)90180-U","volume":"45","author":"SS Coughlin","year":"1992","unstructured":"Coughlin SS, Trock B, Criqui MH, Pickle LW, Browner D, Tefft MC. The logistic modeling of sensitivity, specificity, and predictive value of a diagnostic test. J Clin Epidemiol. 1992;45(1):1\u20137.","journal-title":"J Clin Epidemiol"},{"key":"1614_CR46","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102470","volume":"79","author":"BH Van der Velden","year":"2022","unstructured":"Van der Velden BH, Kuijf HJ, Gilhuijs KG, Viergever MA. Explainable artificial intelligence (XAI) in deep learning-based medical image analysis. Med Image Anal. 2022;79:102470.","journal-title":"Med Image Anal"},{"issue":"1","key":"1614_CR47","doi-asserted-by":"publisher","first-page":"204","DOI":"10.1378\/chest.07-1595","volume":"133","author":"G Soldati","year":"2008","unstructured":"Soldati G, Testa A, Sher S, Pignataro G, La Sala M, Silveri NG. Occult traumatic pneumothorax: diagnostic accuracy of lung ultrasonography in the emergency department. Chest. 2008;133(1):204\u201311.","journal-title":"Chest"}],"container-title":["Scandinavian Journal of Trauma, Resuscitation and Emergency Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s13049-026-01614-4","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13049-026-01614-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13049-026-01614-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T02:44:55Z","timestamp":1779849895000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1186\/s13049-026-01614-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,17]]},"references-count":47,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["1614"],"URL":"https:\/\/doi.org\/10.1186\/s13049-026-01614-4","relation":{},"ISSN":["1757-7241"],"issn-type":[{"value":"1757-7241","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,17]]},"assertion":[{"value":"11 July 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 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":"The comprehensive LUS dataset of this study was prospectively collected with institutional ethics approval (\n                      No. 303\/2021 Semmelweis University Regional and Institutional Committee of Science and Research Ethics\n                      ) and in compliance with GDPR.All subjects were adults (>\u200918\u00a0years), and patient identifiers were removed (pseudo-anonymized) to protect privacy. Bedside lung ultrasound assessment is a declared part of the daily care at the study site, constructed by the authors of this study and therefore no additional consent was needed. The cadavers included in the study were donated specifically for educational and research purposes to the Department of Anatomy, Histology and Embryology at Semmelweis University. Additional ethical review and approval was not required for the use of donated human cadaveric tissue in accordance with the local legislation and institutional requirements. All healthy volunteer provided informed consent for ultrasound examination, anonymized data collection, storage, and subsequent analysis and use for research purposes.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","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":"95"}}