{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T02:33:15Z","timestamp":1778725995779,"version":"3.51.4"},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2022,4,4]],"date-time":"2022-04-04T00:00:00Z","timestamp":1649030400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,4,4]],"date-time":"2022-04-04T00:00:00Z","timestamp":1649030400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council of Canada","doi-asserted-by":"publisher","award":["534769"],"award-info":[{"award-number":["534769"]}],"id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100010571","name":"R\u00e9seau en Bio-Imagerie du Quebec","doi-asserted-by":"publisher","award":["Concours sp\u00e9cial COVID-19"],"award-info":[{"award-number":["Concours sp\u00e9cial COVID-19"]}],"id":[{"id":"10.13039\/100010571","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Radiological findings on chest X-ray (CXR) have shown to be essential for the proper management of COVID-19 patients as the maximum severity over the course of the disease is closely linked to the outcome. As such, evaluation of future severity from current CXR would be highly desirable. We trained a repurposed deep learning algorithm on the CheXnet open dataset (224,316 chest X-ray images of 65,240 unique patients) to extract features that mapped to radiological labels. We collected CXRs of COVID-19-positive patients from an open-source dataset (COVID-19 image data collection) and from a multi-institutional local ICU dataset. The data was grouped into pairs of sequential CXRs and were categorized into three categories: \u2018Worse\u2019, \u2018Stable\u2019, or \u2018Improved\u2019 on the basis of radiological evolution ascertained from images and reports. Classical machine-learning algorithms were trained on the deep learning extracted features to perform immediate severity evaluation and prediction of future radiological trajectory. Receiver operating characteristic analyses and Mann-Whitney tests were performed. Deep learning predictions between \u201cWorse\u201d and \u201cImproved\u201d outcome categories and for severity stratification were significantly different for three radiological signs and one diagnostic (\u2018Consolidation\u2019, \u2018Lung Lesion\u2019, \u2018Pleural effusion\u2019 and \u2018Pneumonia\u2019; all\n                    <jats:italic>P<\/jats:italic>\n                    \u00a0&lt;\u00a00.05). Features from the first CXR of each pair could correctly predict the outcome category between \u2018Worse\u2019 and \u2018Improved\u2019 cases with a 0.81 (0.74\u20130.83 95% CI) AUC in the open-access dataset and with a 0.66 (0.67\u20130.64 95% CI) AUC in the ICU dataset. Features extracted from the CXR could predict disease severity with a 52.3% accuracy in a 4-way classification. Severity evaluation trained on the COVID-19 image data collection had good out-of-distribution generalization when testing on the local dataset, with 81.6% of intubated ICU patients being classified as critically ill, and the predicted severity was correlated with the clinical outcome with a 0.639 AUC. CXR deep learning features show promise for classifying disease severity and trajectory. Once validated in studies incorporating clinical data and with larger sample sizes, this information may be considered to inform triage decisions.\n                  <\/jats:p>","DOI":"10.1038\/s41598-022-09356-w","type":"journal-article","created":{"date-parts":[[2022,4,4]],"date-time":"2022-04-04T10:02:51Z","timestamp":1649066571000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Tracking and predicting COVID-19 radiological trajectory on chest X-rays using deep learning"],"prefix":"10.1038","volume":"12","author":[{"given":"Daniel","family":"Gourdeau","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Olivier","family":"Potvin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Patrick","family":"Archambault","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Carl","family":"Chartrand-Lefebvre","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Louis","family":"Dieumegarde","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Reza","family":"Forghani","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christian","family":"Gagn\u00e9","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexandre","family":"Hains","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David","family":"Hornstein","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huy","family":"Le","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Simon","family":"Lemieux","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marie-H\u00e9l\u00e8ne","family":"L\u00e9vesque","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Diego","family":"Martin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lorne","family":"Rosenbloom","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"An","family":"Tang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fabrizio","family":"Vecchio","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Issac","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nathalie","family":"Duchesne","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Simon","family":"Duchesne","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,4,4]]},"reference":[{"key":"9356_CR1","first-page":"1839","volume":"323","author":"JT Poston","year":"2020","unstructured":"Poston, J. T., Patel, B. K. & Davis, A. M. Management of critically ill adults with COVID-19. Jama 323, 1839\u20131841 (2020).","journal-title":"Jama"},{"key":"9356_CR2","doi-asserted-by":"publisher","first-page":"E400","DOI":"10.1503\/cmaj.200465","volume":"192","author":"A Arya","year":"2020","unstructured":"Arya, A., Buchman, S., Gagnon, B. & Downar, J. Pandemic palliative care: Beyond ventilators and saving lives. CMAJ 192, E400\u2013E404 (2020).","journal-title":"CMAJ"},{"key":"9356_CR3","doi-asserted-by":"publisher","first-page":"1851","DOI":"10.1056\/NEJMe2005477","volume":"382","author":"LR Baden","year":"2020","unstructured":"Baden, L. R. & Rubin, E. J. COVID-19\u2014The search for effective therapy. New Engl. J. Med. 382, 1851\u20131852 (2020).","journal-title":"New Engl. J. Med."},{"key":"9356_CR4","doi-asserted-by":"publisher","first-page":"384","DOI":"10.1016\/S1473-3099(20)30134-1","volume":"20","author":"EY Lee","year":"2020","unstructured":"Lee, E. Y., Ng, M.-Y. & Khong, P.-L. COVID-19 pneumonia: What has CT taught us?. Lancet Infect. Dis. 20, 384\u2013385 (2020).","journal-title":"Lancet Infect. Dis."},{"key":"9356_CR5","doi-asserted-by":"publisher","first-page":"87","DOI":"10.2214\/AJR.20.23034","volume":"215","author":"S Salehi","year":"2020","unstructured":"Salehi, S., Abedi, A., Balakrishnan, S. & Gholamrezanezhad, A. Coronavirus disease 2019 (COVID-19): A systematic review of imaging findings in 919 patients. Am. J. Roentgenol. 215, 87\u201393 (2020).","journal-title":"Am. J. Roentgenol."},{"key":"9356_CR6","doi-asserted-by":"publisher","first-page":"1061","DOI":"10.1001\/jama.2020.1585","volume":"323","author":"D Wang","year":"2020","unstructured":"Wang, D. et al. Clinical characteristics of 138 hospitalized patients with 2019 novel coronavirus-infected pneumonia in Wuhan, China. Jama 323, 1061\u20131069 (2020).","journal-title":"Jama"},{"key":"9356_CR7","doi-asserted-by":"publisher","first-page":"1072","DOI":"10.2214\/AJR.20.22976","volume":"214","author":"W Zhao","year":"2020","unstructured":"Zhao, W., Zhong, Z., Xie, X., Yu, Q. & Liu, J. Relation between chest CT findings and clinical conditions of coronavirus disease (COVID-19) pneumonia: A multicenter study. Am. J. Roentgenol. 214, 1072\u20131077 (2020).","journal-title":"Am. J. Roentgenol."},{"key":"9356_CR8","doi-asserted-by":"publisher","first-page":"E72","DOI":"10.1148\/radiol.2020201160","volume":"296","author":"HYF Wong","year":"2020","unstructured":"Wong, H. Y. F. et al. Frequency and distribution of chest radiographic findings in patients positive for COVID-19. Radiology 296, E72\u2013E78 (2020).","journal-title":"Radiology"},{"key":"9356_CR9","doi-asserted-by":"publisher","first-page":"e200028","DOI":"10.1148\/ryct.2020200028","volume":"2","author":"W Kong","year":"2020","unstructured":"Kong, W. & Agarwal, P. P. Chest imaging appearance of COVID-19 infection. Radiol. Cardiothorac. Imaging 2, e200028 (2020).","journal-title":"Radiol. Cardiothorac. Imaging"},{"key":"9356_CR10","doi-asserted-by":"publisher","first-page":"323","DOI":"10.1016\/j.crad.2020.03.003","volume":"75","author":"J Rodrigues","year":"2020","unstructured":"Rodrigues, J. et al. An update on COVID-19 for the radiologist\u2014A British Society of Thoracic Imaging statement. Clin. Radiol. 75, 323\u2013325 (2020).","journal-title":"Clin. Radiol."},{"key":"9356_CR11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-020-79183-4","volume":"11","author":"Q Lei","year":"2021","unstructured":"Lei, Q. et al. Correlation between CT findings and outcomes in 46 patients with coronavirus disease 2019. Sci. Rep. 11, 1\u20136 (2021).","journal-title":"Sci. Rep."},{"key":"9356_CR12","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1016\/j.clinimag.2020.11.004","volume":"71","author":"AS Al-Smadi","year":"2021","unstructured":"Al-Smadi, A. S., Bhatnagar, A., Ali, R., Lewis, N. & Johnson, S. Correlation of chest radiography findings with the severity and progression of COVID-19 pneumonia. Clin. Imaging 71, 17\u201323 (2021).","journal-title":"Clin. Imaging"},{"key":"9356_CR13","doi-asserted-by":"publisher","first-page":"1999","DOI":"10.1007\/s00330-020-07270-1","volume":"31","author":"M Balbi","year":"2021","unstructured":"Balbi, M. et al. Chest X-ray for predicting mortality and the need for ventilatory support in COVID-19 patients presenting to the emergency department. Eur. Radiol. 31, 1999\u20132012 (2021).","journal-title":"Eur. Radiol."},{"key":"9356_CR14","doi-asserted-by":"publisher","first-page":"291","DOI":"10.1016\/j.ijid.2020.05.021","volume":"96","author":"A Borghesi","year":"2020","unstructured":"Borghesi, A. et al. Chest X-ray severity index as a predictor of in-hospital mortality in coronavirus disease 2019: a study of 302 patients from Italy. Int. J. Infect. Dis. 96, 291\u2013293 (2020).","journal-title":"Int. J. Infect. Dis."},{"key":"9356_CR15","doi-asserted-by":"publisher","first-page":"1973","DOI":"10.1056\/NEJMp2005689","volume":"382","author":"RD Truog","year":"2020","unstructured":"Truog, R. D., Mitchell, C. & Daley, G. Q. The toughest triage-allocating ventilators in a pandemic. New England J. Med. 382, 1973\u20131975 (2020).","journal-title":"New England J. Med."},{"key":"9356_CR16","doi-asserted-by":"publisher","first-page":"1423","DOI":"10.1016\/j.cell.2020.04.045","volume":"181","author":"K Zhang","year":"2020","unstructured":"Zhang, K. et al. Clinically applicable AI system for accurate diagnosis, quantitative measurements, and prognosis of COVID-19 pneumonia using computed tomography. Cell 181, 1423\u20131433 (2020).","journal-title":"Cell"},{"key":"9356_CR17","doi-asserted-by":"publisher","first-page":"1224","DOI":"10.1038\/s41591-020-0931-3","volume":"8","author":"X Mei","year":"2020","unstructured":"Mei, X. et al. Artificial intelligence-enabled rapid diagnosis of patients with COVID-19. Nat. Med. 8, 1224\u20131228 (2020).","journal-title":"Nat. Med."},{"key":"9356_CR18","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s43055-021-00524-y","volume":"52","author":"SM Rezaeijo","year":"2021","unstructured":"Rezaeijo, S. M., Ghorvei, M., Abedi-Firouzjah, R., Mojtahedi, H. & Zarch, H. E. Detecting COVID-19 in chest images based on deep transfer learning and machine learning algorithms. Egypt. J. Radiol. Nucl. Med. 52, 1\u201312 (2021).","journal-title":"Egypt. J. Radiol. Nucl. Med."},{"key":"9356_CR19","doi-asserted-by":"publisher","first-page":"229","DOI":"10.3233\/XST-200831","volume":"29","author":"S Masoud Rezaeijo","year":"2021","unstructured":"Masoud Rezaeijo, S., Abedi-Firouzjah, R., Ghorvei, M. & Sarnameh, S. Screening of COVID-19 based on the extracted radiomics features from chest CT images. J. X-ray Sci. Technol. 29, 229\u2013243 (2021).","journal-title":"J. X-ray Sci. Technol."},{"key":"9356_CR20","doi-asserted-by":"publisher","first-page":"105581","DOI":"10.1016\/j.cmpb.2020.105581","volume":"196","author":"AI Khan","year":"2020","unstructured":"Khan, A. I., Shah, J. L. & Bhat, M. M. Coronet: A deep neural network for detection and diagnosis of COVID-19 from chest X-ray images. Comput. Methods Progr. Biomed. 196, 105581 (2020).","journal-title":"Comput. Methods Progr. Biomed."},{"key":"9356_CR21","doi-asserted-by":"publisher","first-page":"635","DOI":"10.1007\/s13246-020-00865-4","volume":"43","author":"ID Apostolopoulos","year":"2020","unstructured":"Apostolopoulos, I. D. & Mpesiana, T. A. COVID-19: Automatic detection from X-ray images utilizing transfer learning with convolutional neural networks. Phys. Eng. Sci. Med. 43, 635\u2013640 (2020).","journal-title":"Phys. Eng. Sci. Med."},{"key":"9356_CR22","doi-asserted-by":"crossref","unstructured":"Al-Waisy, A.\u00a0S. et\u00a0al. COVID-CheXNet: Hybrid deep learning framework for identifying COVID-19 virus in chest X-rays images. Soft Comput. 1\u201316 (2020).","DOI":"10.1007\/s00500-020-05424-3"},{"key":"9356_CR23","first-page":"e9448","volume":"12","author":"JP Cohen","year":"2020","unstructured":"Cohen, J. P. et al. Predicting COVID-19 pneumonia severity on chest X-ray with deep learning. Cureus 12, e9448 (2020).","journal-title":"Cureus"},{"key":"9356_CR24","doi-asserted-by":"publisher","first-page":"e0236621","DOI":"10.1371\/journal.pone.0236621","volume":"15","author":"J Zhu","year":"2020","unstructured":"Zhu, J. et al. Deep transfer learning artificial intelligence accurately stages COVID-19 lung disease severity on portable chest radiographs. PLoS one 15, e0236621 (2020).","journal-title":"PLoS one"},{"key":"9356_CR25","doi-asserted-by":"publisher","first-page":"20","DOI":"10.5152\/dir.2020.20205","volume":"27","author":"M Blain","year":"2021","unstructured":"Blain, M. et al. Determination of disease severity in COVID-19 patients using deep learning in chest X-ray images. Diagn. Interv. Radiol. 27, 20 (2021).","journal-title":"Diagn. Interv. Radiol."},{"key":"9356_CR26","unstructured":"Sriram, A. et\u00a0al. COVID-19 prognosis via self-supervised representation learning and multi-image prediction (2021). arXiv preprint arXiv:2101.04909."},{"key":"9356_CR27","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1136\/bmjinnov-2020-000593","volume":"7","author":"AR Kulkarni","year":"2021","unstructured":"Kulkarni, A. R. et al. Deep learning model to predict the need for mechanical ventilation using chest X-ray images in hospitalised patients with COVID-19. BMJ Innov. 7, 261\u2013270 (2021).","journal-title":"BMJ Innov."},{"key":"9356_CR28","doi-asserted-by":"crossref","unstructured":"Irvin, J. et al. Chexpert: A large chest radiograph dataset with uncertainty labels and expert comparison. In Proceedings of AAAI Conference on Artificial Intelligence 33, 590\u2013597 (2019).","DOI":"10.1609\/aaai.v33i01.3301590"},{"key":"9356_CR29","doi-asserted-by":"publisher","first-page":"1446","DOI":"10.1373\/clinchem.2015.246280","volume":"61","author":"PM Bossuyt","year":"2015","unstructured":"Bossuyt, P. M. et al. STARD 2015: An updated list of essential items for reporting diagnostic accuracy studies. Clin. Chem. 61, 1446\u20131452 (2015).","journal-title":"Clin. Chem."},{"key":"9356_CR30","doi-asserted-by":"crossref","unstructured":"Zhou, B., Khosla, A., Lapedriza, A., Oliva, A. & Torralba, A. Learning deep features for discriminative localization. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2921\u20132929 (2016).","DOI":"10.1109\/CVPR.2016.319"},{"key":"9356_CR31","doi-asserted-by":"publisher","first-page":"375","DOI":"10.1086\/589754","volume":"47","author":"PG Charles","year":"2008","unstructured":"Charles, P. G. et al. Smart-cop: A tool for predicting the need for intensive respiratory or vasopressor support in community-acquired pneumonia. Clini. Infect. Dis. 47, 375\u2013384 (2008).","journal-title":"Clini. Infect. Dis."},{"key":"9356_CR32","doi-asserted-by":"publisher","first-page":"199","DOI":"10.1038\/s42256-021-00307-0","volume":"3","author":"M Roberts","year":"2021","unstructured":"Roberts, M. et al. Common pitfalls and recommendations for using machine learning to detect and prognosticate for COVID-19 using chest radiographs and CT scans. Nat. Mach. Intelli. 3, 199\u2013217 (2021).","journal-title":"Nat. Mach. Intelli."},{"key":"9356_CR33","doi-asserted-by":"publisher","first-page":"m1328","DOI":"10.1136\/bmj.m1328","volume":"369","author":"L Wynants","year":"2020","unstructured":"Wynants, L. et al. Prediction models for diagnosis and prognosis of COVID-19: systematic review and critical appraisal. BMJ 369, m1328 (2020).","journal-title":"BMJ"},{"key":"9356_CR34","doi-asserted-by":"publisher","first-page":"430","DOI":"10.1038\/s41586-020-2521-4","volume":"584","author":"EJ Williamson","year":"2020","unstructured":"Williamson, E. J. et al. Factors associated with COVID-19-related death using OpenSAFELY. Nature 584, 430\u2013436 (2020).","journal-title":"Nature"}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-022-09356-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-022-09356-w","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-022-09356-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,24]],"date-time":"2022-11-24T20:36:38Z","timestamp":1669322198000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-022-09356-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4,4]]},"references-count":34,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2022,12]]}},"alternative-id":["9356"],"URL":"https:\/\/doi.org\/10.1038\/s41598-022-09356-w","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2020.05.01.20086207","asserted-by":"object"}]},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,4,4]]},"assertion":[{"value":"14 May 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 March 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 April 2022","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":"5616"}}