{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T21:05:30Z","timestamp":1775163930564,"version":"3.50.1"},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,9,24]],"date-time":"2025-09-24T00:00:00Z","timestamp":1758672000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,9,24]],"date-time":"2025-09-24T00:00:00Z","timestamp":1758672000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100000071","name":"National Institute of Child Health and Human Development","doi-asserted-by":"publisher","award":["5T32HD104612-03"],"award-info":[{"award-number":["5T32HD104612-03"]}],"id":[{"id":"10.13039\/100000071","id-type":"DOI","asserted-by":"publisher"}]},{"name":"NIH National Library of Medicine Biomedical Informatics and Data Science Research Training Program","award":["T15LM007092-30"],"award-info":[{"award-number":["T15LM007092-30"]}]},{"name":"Chiesi USA, Inc"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["npj Digit. Med."],"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>Deep learning has proven to be an excellent tool for interpreting medical images in adults and children. However, it is still underdeveloped for neonates. This study developed NeoCLIP, a novel deep contrastive learning model designed to detect pathologies and medical devices on neonatal radiographs. We retrospectively studied 4629 infants admitted to a neonatal intensive care unit in Boston, MA (2008\u20132023), compiling 20,154 radiographs and 15,795 corresponding reports. The cohort was randomized into training (80%), validation (10%), and test (10%) sets. NeoCLIP was trained to identify 15 radiological features and 5 medical devices relevant to neonatal intensive care. NeoCLIP achieved higher AUROC compared to controls in all labels except portal venous gas. Incorporating demographic data improved model performance, though not statistically significantly. NeoCLIP is the first deep learning model tailored for the interpretation of neonatal radiographs, surpassing the efficacy of comparable adult models.<\/jats:p>","DOI":"10.1038\/s41746-025-01922-6","type":"journal-article","created":{"date-parts":[[2025,9,24]],"date-time":"2025-09-24T16:23:14Z","timestamp":1758730994000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["NeoCLIP: a self-supervised foundation model for the interpretation of neonatal radiographs"],"prefix":"10.1038","volume":"8","author":[{"given":"Yixuan","family":"Huang","sequence":"first","affiliation":[]},{"given":"Puneet","family":"Sharma","sequence":"additional","affiliation":[]},{"given":"Anil","family":"Palepu","sequence":"additional","affiliation":[]},{"given":"Nathaniel","family":"Greenbaum","sequence":"additional","affiliation":[]},{"given":"Andrew","family":"Beam","sequence":"additional","affiliation":[]},{"given":"Kristyn","family":"Beam","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,9,24]]},"reference":[{"key":"1922_CR1","doi-asserted-by":"publisher","first-page":"328","DOI":"10.1515\/cclm-2018-0658","volume":"57","author":"G Gopal","year":"2019","unstructured":"Gopal, G., Suter-Crazzolara, C., Toldo, L. & Eberhardt, W. Digital transformation in healthcare \u2013 architectures of present and future information technologies. Clin. Chem. Lab. Med. 57, 328\u2013335 (2019).","journal-title":"Clin. Chem. Lab. Med."},{"key":"1922_CR2","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1038\/s41372-023-01719-z","volume":"44","author":"K Beam","year":"2024","unstructured":"Beam, K., Sharma, P., Levy, P. & Beam, A. L. Artificial intelligence in the neonatal intensive care unit: the time is now. J. Perinatol. 44, 131\u2013135 (2024).","journal-title":"J. Perinatol."},{"key":"1922_CR3","doi-asserted-by":"publisher","first-page":"1472","DOI":"10.1016\/j.acra.2018.02.018","volume":"25","author":"MP McBee","year":"2018","unstructured":"McBee, M. P. et al. Deep learning in radiology. Acad. Radio. 25, 1472\u20131480 (2018).","journal-title":"Acad. Radio."},{"key":"1922_CR4","doi-asserted-by":"publisher","first-page":"2139","DOI":"10.1007\/s00247-021-05057-0","volume":"52","author":"JR Dillman","year":"2022","unstructured":"Dillman, J. R., Somasundaram, E., Brady, S. L. & He, L. Current and emerging artificial intelligence applications for pediatric abdominal imaging. Pediatr. Radio. 52, 2139\u20132148 (2022).","journal-title":"Pediatr. Radio."},{"key":"1922_CR5","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1016\/j.ejrad.2019.02.038","volume":"114","author":"L Saba","year":"2019","unstructured":"Saba, L. et al. The present and future of deep learning in radiology. Eur. J. Radio. 114, 14\u201324 (2019).","journal-title":"Eur. J. Radio."},{"key":"1922_CR6","first-page":"1597","volume":"119","author":"T Chen","year":"2020","unstructured":"Chen, T., Kornblith, S., Norouzi, M. & Hinton, G. A simple framework for contrastive learning of visual representations. Proc. 37th Int. Conf. Mach. Learn. 119, 1597\u20131607 (2020).","journal-title":"Proc. 37th Int. Conf. Mach. Learn."},{"key":"1922_CR7","doi-asserted-by":"publisher","first-page":"1399","DOI":"10.1038\/s41551-022-00936-9","volume":"6","author":"E Tiu","year":"2022","unstructured":"Tiu, E. et al. Expert-level detection of pathologies from unannotated chest X-ray images via self-supervised learning. Nat. Biomed. Eng. 6, 1399\u20131406 (2022).","journal-title":"Nat. Biomed. Eng."},{"key":"1922_CR8","doi-asserted-by":"crossref","unstructured":"Wu, C. et al. Medical knowledge enhanced language-image pre-training for x-ray diagnosis. In Proceedings of the IEEE\/CVF International Conference on Computer Vision. 21372-21383 (2023).","DOI":"10.1109\/ICCV51070.2023.01954"},{"key":"1922_CR9","doi-asserted-by":"publisher","first-page":"259","DOI":"10.1038\/s41586-023-05881-4","volume":"616","author":"M Moor","year":"2023","unstructured":"Moor, M. et al. Foundation models for generalist medical artificial intelligence. Nature 616, 259\u2013265 (2023).","journal-title":"Nature"},{"key":"1922_CR10","first-page":"548","volume":"219","author":"A Palepu","year":"2023","unstructured":"Palepu, A. & Beam, A. Tier: Text-image entropy regularization for medical clip-style models. Proc. 8th Mach. Learn. Healthc. Conf. 219, 548\u2013564 (2023).","journal-title":"Proc. 8th Mach. Learn. Healthc. Conf."},{"key":"1922_CR11","first-page":"44","volume":"43","author":"EB Hysinger","year":"2022","unstructured":"Hysinger, E. B., Higano, N. S., Critser, P. J. & Woods, J. C. Imaging in neonatal respiratory disease. Paediatr. Respir. Rev. 43, 44\u201352 (2022).","journal-title":"Paediatr. Respir. Rev."},{"key":"1922_CR12","doi-asserted-by":"publisher","first-page":"2206943","DOI":"10.1080\/14767058.2023.2206943","volume":"36","author":"J Liu","year":"2023","unstructured":"Liu, J. Ultrasound diagnosis and grading criteria of neonatal respiratory distress syndrome. J. Matern Fetal Neonatal Med. 36, 2206943 (2023).","journal-title":"J. Matern Fetal Neonatal Med"},{"key":"1922_CR13","doi-asserted-by":"publisher","first-page":"552","DOI":"10.1542\/pir.2017-0002","volume":"38","author":"BS Rich","year":"2017","unstructured":"Rich, B. S. & Dolgin, S. E. Necrotizing enterocolitis. Pediatr. Rev. 38, 552\u2013559 (2017).","journal-title":"Pediatr. Rev."},{"key":"1922_CR14","doi-asserted-by":"publisher","first-page":"A1","DOI":"10.1016\/j.mri.2019.12.006","volume":"68","author":"JC Gore","year":"2020","unstructured":"Gore, J. C. Artificial intelligence in medical imaging. Magn. Reson Imaging 68, A1\u2013A4 (2020).","journal-title":"Magn. Reson Imaging"},{"key":"1922_CR15","doi-asserted-by":"publisher","first-page":"1568","DOI":"10.1007\/s00247-022-05368-w","volume":"52","author":"S Padash","year":"2022","unstructured":"Padash, S., Mohebbian, M. R., Adams, S. J., Henderson, R. D. E. & Babyn, P. Pediatric chest radiograph interpretation: how far has artificial intelligence come? A systematic literature review. Pediatr. Radio. 52, 1568\u20131580 (2022).","journal-title":"Pediatr. Radio."},{"key":"1922_CR16","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.231236","volume":"308","author":"L Lind Plesner","year":"2023","unstructured":"Lind Plesner, L. et al. Commercially Available Chest Radiograph AI Tools for Detecting Airspace Disease, Pneumothorax, and Pleural Effusion. Radiology 308, e231236 (2023).","journal-title":"Radiology"},{"key":"1922_CR17","doi-asserted-by":"publisher","DOI":"10.2196\/47612","volume":"25","author":"W Jang","year":"2023","unstructured":"Jang, W. et al. Artificial intelligence-driven respiratory distress syndrome prediction for very low birth weight infants: korean multicenter prospective cohort study. J. Med. Internet Res. 25, e47612 (2023).","journal-title":"J. Med. Internet Res"},{"key":"1922_CR18","doi-asserted-by":"publisher","first-page":"1267","DOI":"10.1080\/14767058.2016.1210597","volume":"30","author":"V Cond\u00f2","year":"2017","unstructured":"Cond\u00f2, V. et al. Neonatal respiratory distress syndrome: are risk factors the same in preterm and term infants?. J. Matern Fetal Neonatal Med. 30, 1267\u20131272 (2017).","journal-title":"J. Matern Fetal Neonatal Med"},{"key":"1922_CR19","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-019-51617-8","volume":"9","author":"E Jung","year":"2019","unstructured":"Jung, E. & Lee, B. S. Late-onset sepsis as a risk factor for bronchopulmonary dysplasia in extremely low birth weight infants: a nationwide cohort study. Sci. Rep. 9, 15448 (2019).","journal-title":"Sci. Rep."},{"key":"1922_CR20","doi-asserted-by":"publisher","first-page":"e226","DOI":"10.1542\/neo.21-4-e226","volume":"21","author":"K Gibbs","year":"2020","unstructured":"Gibbs, K., Jensen, E. A., Alexiou, S., Munson, D. & Zhang, H. Ventilation strategies in severe bronchopulmonary dysplasia. Neoreviews 21, e226\u2013e237 (2020).","journal-title":"Neoreviews"},{"key":"1922_CR21","doi-asserted-by":"crossref","unstructured":"Bannur, S. et al. Learning to exploit temporal structure for biomedical vision-language processing. arXiv.org. Published March 16, 2023.","DOI":"10.1109\/CVPR52729.2023.01442"},{"key":"1922_CR22","first-page":"2","volume":"1","author":"JD Kenton","year":"2019","unstructured":"Kenton, J. D., Chang, M. W. & Toutanova, K. BERT: Pre-training of deep bidirectional transformers for language understanding. Proc. NAACL-HLT 1, 2 (2019).","journal-title":"Proc. NAACL-HLT"},{"key":"1922_CR23","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S. & Sun, J. Deep Residual Learning for Image Recognition. In IEEE Conference on Computer Vision and Pattern Recognition. 770-778 (2016).","DOI":"10.1109\/CVPR.2016.90"},{"key":"1922_CR24","unstructured":"Radford, A. et al. Learning transferable visual models from natural language supervision. In International Conference on Machine Learning, PMLR. 8748-8763 (2021)."},{"key":"1922_CR25","doi-asserted-by":"publisher","unstructured":"Horng, S. Machine Learning Core. figshare. https:\/\/doi.org\/10.6084\/m9.figshare.19104917.v2 (2022).","DOI":"10.6084\/m9.figshare.19104917.v2"},{"key":"1922_CR26","unstructured":"Krizhevsky, A., Sutskever, I. & Hinton, G. E. ImageNet classification with deep convolutional neural networks. In Advances in Neural Information Processing Systems. 1097\u20131105 (2012)."},{"key":"1922_CR27","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s40537-019-0197-0","volume":"6","author":"C Shorten","year":"2019","unstructured":"Shorten, C. & Khoshgoftaar, T. M. A survey on image data augmentation for deep learning. J. Big Data 6, 1\u201348 (2019).","journal-title":"J. Big Data"},{"key":"1922_CR28","unstructured":"PyTorch team. torchvision.models.resnext50_32x4d. PyTorch documentation https:\/\/pytorch.org\/vision\/stable\/models\/generated\/torchvision.models.resnext50_32x4d.html (2024)."},{"key":"1922_CR29","doi-asserted-by":"publisher","first-page":"e2229289","DOI":"10.1001\/jamanetworkopen.2022.29289","volume":"5","author":"JS Ahn","year":"2022","unstructured":"Ahn, J. S. et al. Association of Artificial Intelligence-Aided Chest Radiograph Interpretation With Reader Performance and Efficiency. JAMA Netw. Open 5, e2229289 (2022).","journal-title":"JAMA Netw. Open"},{"key":"1922_CR30","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.230860","volume":"309","author":"S Bennani","year":"2023","unstructured":"Bennani, S. et al. Using AI to Improve Radiologist Performance in Detection of Abnormalities on Chest Radiographs. Radiology 309, e230860 (2023).","journal-title":"Radiology"}],"container-title":["npj Digital Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-01922-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-01922-6","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-01922-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,24]],"date-time":"2025-09-24T16:23:18Z","timestamp":1758730998000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-01922-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,24]]},"references-count":30,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["1922"],"URL":"https:\/\/doi.org\/10.1038\/s41746-025-01922-6","relation":{},"ISSN":["2398-6352"],"issn-type":[{"value":"2398-6352","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,24]]},"assertion":[{"value":"1 April 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 August 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 September 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"570"}}