{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T12:50:58Z","timestamp":1765371058875,"version":"3.46.0"},"reference-count":20,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T00:00:00Z","timestamp":1765238400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T00:00:00Z","timestamp":1765324800000},"content-version":"vor","delay-in-days":1,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Private Universit\u00e4t Witten\/Herdecke gGmbH"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Chest radiography is widely used as an initial imaging modality. However, how specific findings relate to subsequent care or follow-up actions remains unclear. Prior studies have rarely examined follow-up actions, and potential sex-specific differences have been understudied. We analyzed 112,120 frontal chest radiographs from the NIH ChestX-ray14 dataset (63,340 male, 48,780 female). Images were labeled with 14 findings using a natural language processing (NLP) pipeline applied to reports. We modeled a metadata-derived proxy of 90-day follow-up using logistic regression, including sex-stratified analyses and interaction testing, with models adjusted for sex. Robustness was assessed through sensitivity analyses (30\/60\/180-day windows), patient-level clustering, and false discovery rate (FDR) adjustment. The strongest associations with proxy follow-up were observed for pulmonary edema (OR 10.6, 95% CI 8.5\u201313.2), pneumothorax (OR 7.6, 95% CI 6.7\u20138.6), and pleural effusion (OR 4.0, 95% CI 3.8\u20134.3). Interactions between sex and specific findings were modest but reached statistical significance for atelectasis (\n                    <jats:italic>P<\/jats:italic>\n                    \u2009=\u20090.003), pneumothorax (\n                    <jats:italic>P<\/jats:italic>\n                    \u2009=\u20090.0083), and emphysema (\n                    <jats:italic>P<\/jats:italic>\n                    \u2009=\u20090.0238). Radiographic findings were associated with metadata-derived proxy follow-up, but residual confounding from unmeasured factors (e.g., age, comorbidities, clinical context) likely remains. Sex-specific effects were statistically significant but small, and not clinically meaningful. Results should therefore be interpreted strictly as hypothesis-generating signals, not as causal evidence or clinically directive guidance.\n                  <\/jats:p>","DOI":"10.1038\/s41598-025-31885-3","type":"journal-article","created":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T14:32:56Z","timestamp":1765290776000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Exploratory associations between radiographic findings and metadata-derived proxies of 90-day follow-up in 112,120 ChestX-ray14 radiographs"],"prefix":"10.1038","volume":"15","author":[{"given":"Josef","family":"Yayan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kurt","family":"Rasche","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marcus","family":"Kr\u00fcger","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christian","family":"Biancosino","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,12,9]]},"reference":[{"key":"31885_CR1","doi-asserted-by":"publisher","unstructured":"Mettler, F. A. Jr et al. Radiologic and nuclear medicine studies in the United States and worldwide: frequency, radiation dose, and comparison with other radiation sources, 1950\u20132007.  Radiology 253 (2), 520\u2009\u2013\u200931. https:\/\/doi.org\/10.1148\/radiol.2532082010 (2009).","DOI":"10.1148\/radiol.2532082010"},{"issue":"1","key":"31885_CR2","doi-asserted-by":"publisher","first-page":"149","DOI":"10.2214\/ajr.179.1.1790149","volume":"179","author":"JF Gruden","year":"2002","unstructured":"Gruden, J. F., Ouanounou, S., Tigges, S., Norris, S. D. & Klausner, T. S. Incremental benefit of maximum-intensity-projection images on observer detection of small pulmonary nodules revealed by multidetector CT. AJR Am. J. Roentgenol. 179 (1), 149\u2013157. https:\/\/doi.org\/10.2214\/ajr.179.1.1790149 (2002). PMID:12076925.","journal-title":"AJR Am. J. Roentgenol."},{"key":"31885_CR3","unstructured":"Fraser, R. S., M\u00fcller, N. L., Colman, N. & Par\u00e9, P. D. Diagnosis of Diseases of the Chest 4th edn (W.B. Saunders, 1999)."},{"key":"31885_CR4","doi-asserted-by":"publisher","unstructured":"Wang, X. et al. ChestX-ray8: Hospital-scale chest X-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 3462-71 https:\/\/doi.org\/10.1109\/CVPR.2017.369 (2017).","DOI":"10.1109\/CVPR.2017.369"},{"issue":"01","key":"31885_CR5","doi-asserted-by":"publisher","first-page":"590","DOI":"10.1609\/aaai.v33i01.3301590","volume":"33","author":"J Irvin","year":"2019","unstructured":"Irvin, J. et al. CheXpert: A large chest radiograph dataset with uncertainty labels and expert comparison. Proc. AAAI Conf. Artif. Intell. 33 (01), 590\u2013597. https:\/\/doi.org\/10.1609\/aaai.v33i01.3301590 (2019).","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"issue":"11","key":"31885_CR6","doi-asserted-by":"publisher","first-page":"e1002686","DOI":"10.1371\/journal.pmed.1002686","volume":"15","author":"P Rajpurkar","year":"2018","unstructured":"Rajpurkar, P. et al. Deep learning for chest radiograph diagnosis: A retrospective comparison of the CheXNeXt algorithm to practicing radiologists. PLoS Med. 15 (11), e1002686. https:\/\/doi.org\/10.1371\/journal.pmed.1002686 (2018). PMID:30457988; PMCID:PMC6245676.","journal-title":"PLoS Med."},{"issue":"5","key":"31885_CR7","doi-asserted-by":"publisher","first-page":"1472","DOI":"10.1378\/chest.121.5.1472","volume":"121","author":"JA Gold","year":"2002","unstructured":"Gold, J. A., Rom, W. N. & Harkin, T. J. Significance of abnormal chest radiograph findings in patients with HIV-1 infection without respiratory symptoms. Chest 121 (5), 1472\u20131477. https:\/\/doi.org\/10.1378\/chest.121.5.1472 (2002).","journal-title":"Chest"},{"issue":"2","key":"31885_CR8","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1111\/j.1553-2712.1995.tb03172.x","volume":"2","author":"R Silbergleit","year":"1995","unstructured":"Silbergleit, R. & McNamara, R. M. Effect of gender on the emergency department evaluation of patients with chest pain. Acad. Emerg. Med. 2 (2), 115\u2013119. https:\/\/doi.org\/10.1111\/j.1553-2712.1995.tb03172.x (1995). PMID:7621216.","journal-title":"Acad. Emerg. Med."},{"key":"31885_CR9","doi-asserted-by":"publisher","unstructured":"Baumann, S. et al. Gender differences in the diagnostic performance of machine learning coronary CT angiography-derived fractional flow reserve: results from the MACHINE registry. Eur. J. Radiol. 119, 108657 https:\/\/doi.org\/10.1016\/j.ejrad.2019.108657 (2019).","DOI":"10.1016\/j.ejrad.2019.108657"},{"issue":"11","key":"31885_CR10","doi-asserted-by":"publisher","first-page":"1504","DOI":"10.1007\/s11606-013-2441-1","volume":"28","author":"EN Chapman","year":"2013","unstructured":"Chapman, E. N., Kaatz, A. & Carnes, M. Physicians and implicit bias: how Doctors May unwittingly perpetuate health care disparities. J. Gen. Intern. Med. 28 (11), 1504\u20131510. https:\/\/doi.org\/10.1007\/s11606-013-2441-1 (2013). PMID:23576243; PMCID:PMC3797360.","journal-title":"J. Gen. Intern. Med."},{"key":"31885_CR11","doi-asserted-by":"publisher","unstructured":"Flanders, A. E. & Lakhani, P. Radiology reporting and communications: a look forward. Neuroimaging Clin. N. Am. 22 (3), 477\u2009\u2013\u200996        https:\/\/doi.org\/10.1016\/j.nic.2012.04.009 (2012).","DOI":"10.1016\/j.nic.2012.04.009"},{"issue":"25","key":"31885_CR12","doi-asserted-by":"publisher","first-page":"3958","DOI":"10.1161\/CIRCULATIONAHA.105.590091","volume":"112","author":"M Gheorghiade","year":"2005","unstructured":"Gheorghiade, M. et al. Acute heart failure syndromes: current state and framework for future research. Circulation 112 (25), 3958\u20133968. https:\/\/doi.org\/10.1161\/CIRCULATIONAHA.105.590091 (2005). PMID:16365214.","journal-title":"Circulation"},{"issue":"25","key":"31885_CR13","doi-asserted-by":"publisher","first-page":"1971","DOI":"10.1056\/NEJMcp010731","volume":"346","author":"RW Light","year":"2002","unstructured":"Light, R. W. Clinical practice. Pleural effusion. N Engl. J. Med. 346 (25), 1971\u20131977. https:\/\/doi.org\/10.1056\/NEJMcp010731 (2002). PMID:12075059.","journal-title":"N Engl. J. Med."},{"issue":"23","key":"31885_CR14","doi-asserted-by":"publisher","first-page":"12592","DOI":"10.1073\/pnas.1919012117","volume":"117","author":"AJ Larrazabal","year":"2020","unstructured":"Larrazabal, A. J., Nieto, N., Peterson, V., Milone, D. H. & Ferrante, E. Gender imbalance in medical imaging datasets produces biased classifiers for computer-aided diagnosis. Proc. Natl. Acad. Sci. USA. 117 (23), 12592\u201312594. https:\/\/doi.org\/10.1073\/pnas.1919012117 (2020).","journal-title":"Proc. Natl. Acad. Sci. U S A"},{"issue":"6","key":"31885_CR15","doi-asserted-by":"publisher","first-page":"e368","DOI":"10.1016\/S2589-7500(21)00033-3","volume":"3","author":"L Seyyed-Kalantari","year":"2021","unstructured":"Seyyed-Kalantari, L., Zhang, H., McDermott, M. B. A., Chen, I. Y. & Ghassemi, M. Underdiagnosis bias of artificial intelligence algorithms applied to chest radiographs in under-served patient populations. Lancet Digit. Health. 3 (6), e368\u2013e376. https:\/\/doi.org\/10.1016\/S2589-7500(21)00033-3 (2021).","journal-title":"Lancet Digit. Health"},{"issue":"22","key":"31885_CR16","doi-asserted-by":"publisher","first-page":"2849","DOI":"10.1001\/jama.286.22.2849","volume":"286","author":"SS Rathore","year":"2001","unstructured":"Rathore, S. S. et al. Gender differences in cardiac catheterization: the role of physician gender. JAMA 286 (22), 2849\u20132856. https:\/\/doi.org\/10.1001\/jama.286.22.2849 (2001).","journal-title":"JAMA"},{"key":"31885_CR17","doi-asserted-by":"publisher","unstructured":"Oakden-Rayner, L. Exploring large-scale public medical image datasets. Acad. Radiol. 26 (1), 101-9 https:\/\/doi.org\/10.1016\/j.acra.2018.08.010 (2019).","DOI":"10.1016\/j.acra.2018.08.010"},{"issue":"5","key":"31885_CR18","doi-asserted-by":"publisher","first-page":"540","DOI":"10.1055\/s-0038-1673383","volume":"22","author":"AB Syed","year":"2018","unstructured":"Syed, A. B. & Zoga, A. C. Artificial intelligence in radiology: current technology and future directions. Semin Musculoskelet. Radiol. 22 (5), 540\u2013545. https:\/\/doi.org\/10.1055\/s-0038-1673383 (2018).","journal-title":"Semin Musculoskelet. Radiol."},{"key":"31885_CR19","doi-asserted-by":"publisher","unstructured":"Bustos, A., Pertusa, A., Salinas, J. M., de la Iglesia-Vay\u00e1, M. & PadChest A large chest x-ray image dataset with multi-label annotated reports. Med. Image Anal. 66, 101797  https:\/\/doi.org\/10.1016\/j.media.2020.101797 (2020).","DOI":"10.1016\/j.media.2020.101797"},{"issue":"1","key":"31885_CR20","doi-asserted-by":"publisher","first-page":"532","DOI":"10.1007\/s00330-024-10938-7","volume":"35","author":"YX Tay","year":"2025","unstructured":"Tay, Y. X. et al. Impact and effect of imaging referral guidelines on patients and radiology services: a systematic review. Eur. Radiol. 35 (1), 532\u2013541. https:\/\/doi.org\/10.1007\/s00330-024-10938-7 (2025).","journal-title":"Eur. Radiol."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-31885-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-31885-3","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-31885-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T09:39:36Z","timestamp":1765359576000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-31885-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,9]]},"references-count":20,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["31885"],"URL":"https:\/\/doi.org\/10.1038\/s41598-025-31885-3","relation":{},"ISSN":["2045-2322"],"issn-type":[{"type":"electronic","value":"2045-2322"}],"subject":[],"published":{"date-parts":[[2025,12,9]]},"assertion":[{"value":"28 June 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 December 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 December 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 authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}},{"value":"This study was conducted using the publicly available NIH ChestX-ray14 dataset, which includes only fully anonymized radiographic and sex data. According to the dataset provider\u2019s policy and institutional ethical guidelines, no ethical approval or informed consent was required. The dataset analyzed was the NIH ChestX-ray14, not ChestX-ray8; we consistently refer to ChestX-ray14 to ensure reproducibility and avoid prior ambiguities in dataset naming. The ChestX-ray14 dataset consists of de-identified radiographs and metadata collected at the NIH Clinical Center and was released for research benchmarking purposes.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}},{"value":"This study adheres to the STROBE reporting guideline; the completed STROBE checklist is provided as Supplementary File\n                      \n                      .","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"STROBE compliance"}}],"article-number":"43495"}}