{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T14:24:54Z","timestamp":1788877494534,"version":"build-2803163510"},"reference-count":27,"publisher":"European Respiratory Society (ERS)","issue":"2","license":[{"start":{"date-parts":[[2022,4,1]],"date-time":"2022-04-01T00:00:00Z","timestamp":1648771200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":["publications.ersnet.org"],"crossmark-restriction":true},"short-container-title":["ERJ Open Res"],"accepted":{"date-parts":[[2022,4,19]]},"published-print":{"date-parts":[[2022,4]]},"abstract":"<jats:sec><jats:title>Background<\/jats:title><jats:p>Patients with coronavirus disease 2019 (COVID-19) could develop severe disease requiring admission to the intensive care unit (ICU). This article presents a novel method that predicts whether a patient will need admission to the ICU and assesses the risk of in-hospital mortality by training a deep-learning model that combines a set of clinical variables and features in chest radiographs.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>This was a prospective diagnostic test study. Patients with confirmed severe acute respiratory syndrome coronavirus 2 infection between March 2020 and January 2021 were included. This study was designed to build predictive models obtained by training convolutional neural networks for chest radiograph images using an artificial intelligence (AI) tool and a random forest analysis to identify critical clinical variables. Then, both architectures were connected and fine-tuned to provide combined models.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>2552 patients were included in the clinical cohort. The variables independently associated with ICU admission were age, fraction of inspired oxygen (<jats:italic>F<\/jats:italic><jats:sub>iO<jats:sub>2<\/jats:sub><\/jats:sub>) on admission, dyspnoea on admission and obesity. Moreover, the variables associated with hospital mortality were age,<jats:italic>F<\/jats:italic><jats:sub>iO<jats:sub>2<\/jats:sub><\/jats:sub>on admission and dyspnoea. When implementing the AI model to interpret the chest radiographs and the clinical variables identified by random forest, we developed a model that accurately predicts ICU admission (area under the curve (AUC) 0.92\u00b10.04) and hospital mortality (AUC 0.81\u00b10.06) in patients with confirmed COVID-19.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusions<\/jats:title><jats:p>This automated chest radiograph interpretation algorithm, along with clinical variables, is a reliable alternative to identify patients at risk of developing severe COVID-19 who might require admission to the ICU.<\/jats:p><\/jats:sec>","DOI":"10.1183\/23120541.00010-2022","type":"journal-article","created":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T15:35:49Z","timestamp":1653320149000},"page":"00010-2022","update-policy":"https:\/\/doi.org\/10.1183\/ers-crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["A novel model to predict severe COVID-19 and mortality using an artificial intelligence algorithm to interpret chest radiographs and clinical variables"],"prefix":"10.1183","volume":"8","author":[{"given":"Nicol\u00e1s","family":"Munera","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Esteban","family":"Garcia-Gallo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"\u00c1lvaro","family":"Gonzalez","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jos\u00e9","family":"Zea","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuli V.","family":"Fuentes","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8344-0535","authenticated-orcid":false,"given":"Cristian","family":"Serrano","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alejandra","family":"Ruiz-Cuartas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alejandro","family":"Rodriguez","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1172-6539","authenticated-orcid":false,"given":"Luis F.","family":"Reyes","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"81","published-online":{"date-parts":[[2022,4,29]]},"reference":[{"key":"2024101711344147000_8.2.00010-2022.1","doi-asserted-by":"crossref","first-page":"699","DOI":"10.1016\/S2213-2600(21)00013-8","article-title":"Risk of adverse outcomes in patients with underlying respiratory conditions admitted to hospital with COVID-19: a national, multicentre prospective cohort study using the ISARIC WHO Clinical Characterisation Protocol UK","volume":"9","author":"Bloom","year":"2021","journal-title":"Lancet Respir Med"},{"key":"2024101711344147000_8.2.00010-2022.2","doi-asserted-by":"crossref","first-page":"e14759","DOI":"10.1111\/ijcp.14759","article-title":"Performance of the CURB-65, ISARIC-4C and COVID-GRAM scores in terms of severity for COVID-19 patients","volume":"75","author":"Do\u011fanay","year":"2021","journal-title":"Int J Clin Pract"},{"key":"2024101711344147000_8.2.00010-2022.3","doi-asserted-by":"crossref","first-page":"889","DOI":"10.1007\/s15010-021-01599-5","article-title":"COVID-19 symptoms at hospital admission vary with age and sex: results from the ISARIC prospective multinational observational study","volume":"49","year":"2021","journal-title":"Infection"},{"key":"2024101711344147000_8.2.00010-2022.4","doi-asserted-by":"publisher","DOI":"10.1183\/23120541.00552-2021"},{"key":"2024101711344147000_8.2.00010-2022.5","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.m1985"},{"key":"2024101711344147000_8.2.00010-2022.6","doi-asserted-by":"crossref","first-page":"100882","DOI":"10.1016\/j.accpm.2021.100882","article-title":"Post-acute COVID-19 Syndrome (PACS): a public health emergency","volume":"40","author":"Rello","year":"2021","journal-title":"Anaesth Crit Care Pain Med"},{"key":"2024101711344147000_8.2.00010-2022.7","first-page":"20","article-title":"ISARIC 4c mortality score as a predictor of in-hospital mortality in COVID-19 patients admitted in Ayub teaching hospital during first wave of the pandemic","volume":"33","author":"Ali","year":"2021","journal-title":"J Ayub Med Coll Abbottabad"},{"key":"2024101711344147000_8.2.00010-2022.8","doi-asserted-by":"crossref","first-page":"525","DOI":"10.1016\/j.medin.2020.05.018","article-title":"Severe infection due to the SARS-CoV-2 coronavirus: experience of a tertiary hospital with COVID-19 patients during the 2020 pandemic","volume":"44","author":"Rodr\u00edguez","year":"2020","journal-title":"Med Intensiva"},{"key":"2024101711344147000_8.2.00010-2022.9","doi-asserted-by":"publisher","DOI":"10.1126\/sciimmunol.abl4340"},{"key":"2024101711344147000_8.2.00010-2022.10","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2020.6775"},{"key":"2024101711344147000_8.2.00010-2022.11","doi-asserted-by":"crossref","first-page":"2161","DOI":"10.1001\/jama.2021.20714","article-title":"Effect of high-flow oxygen therapy vs conventional oxygen therapy on invasive mechanical ventilation and clinical recovery in patients with severe COVID-19: a randomized clinical trial","volume":"326","author":"Ospina-Tasc\u00f3n","year":"2021","journal-title":"JAMA"},{"key":"2024101711344147000_8.2.00010-2022.12","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1007\/s00134-020-06294-x","article-title":"Clinical characteristics and day-90 outcomes of 4244 critically ill adults with COVID-19: a prospective cohort study","volume":"47","year":"2021","journal-title":"Intensive Care Med"},{"key":"2024101711344147000_8.2.00010-2022.13","doi-asserted-by":"crossref","first-page":"493","DOI":"10.1016\/j.medj.2021.04.015","article-title":"COVID-19: the therapeutic landscape","volume":"2","author":"Paules","year":"2021","journal-title":"Med"},{"key":"2024101711344147000_8.2.00010-2022.14","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1186\/s13054-021-03487-8","article-title":"Deploying unsupervised clustering analysis to derive clinical phenotypes and risk factors associated with mortality risk in 2022 critically ill patients with COVID-19 in Spain","volume":"25","author":"Rodr\u00edguez","year":"2021","journal-title":"Crit Care"},{"key":"2024101711344147000_8.2.00010-2022.15","doi-asserted-by":"crossref","first-page":"598","DOI":"10.1097\/CCM.0000000000004895","article-title":"The Surviving Sepsis Campaign: research priorities for coronavirus disease 2019 in critical illness","volume":"49","author":"Coopersmith","year":"2021","journal-title":"Crit Care Med"},{"key":"2024101711344147000_8.2.00010-2022.16","doi-asserted-by":"publisher","DOI":"10.1183\/13993003.00048-2021"},{"key":"2024101711344147000_8.2.00010-2022.17","doi-asserted-by":"publisher","DOI":"10.1007\/s11547-020-01232-9"},{"key":"2024101711344147000_8.2.00010-2022.18","doi-asserted-by":"publisher","DOI":"10.1183\/13993003.00775-2020"},{"key":"2024101711344147000_8.2.00010-2022.19","doi-asserted-by":"crossref","first-page":"e0265529","DOI":"10.1371\/journal.pone.0265529","article-title":"Clinical characteristics, systemic complications, and in-hospital outcomes for patients with COVID-19 in Latin America. LIVEN-Covid-19 study: a prospective, multicenter, multinational, cohort study","volume":"17","author":"Reyes","year":"2022","journal-title":"PLoS One"},{"key":"2024101711344147000_8.2.00010-2022.20","doi-asserted-by":"crossref","first-page":"154014","DOI":"10.1016\/j.jcrc.2022.154014","article-title":"Dexamethasone as risk-factor for ICU-acquired respiratory tract infections in severe COVID-19","volume":"69","author":"Reyes","year":"2022","journal-title":"J Crit Care"},{"key":"2024101711344147000_8.2.00010-2022.21","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2008.08.010"},{"key":"2024101711344147000_8.2.00010-2022.22","doi-asserted-by":"crossref","first-page":"e0236618","DOI":"10.1371\/journal.pone.0236618","article-title":"Prediction model and risk scores of ICU admission and mortality in COVID-19","volume":"15","author":"Zhao","year":"2020","journal-title":"PLoS One"},{"key":"2024101711344147000_8.2.00010-2022.23","doi-asserted-by":"crossref","first-page":"e286","DOI":"10.1016\/S2589-7500(21)00039-X","article-title":"Prognostication of patients with COVID-19 using artificial intelligence based on chest x-rays and clinical data: a retrospective study","volume":"3","author":"Jiao","year":"2021","journal-title":"Lancet Digit Health"},{"key":"2024101711344147000_8.2.00010-2022.24","doi-asserted-by":"crossref","first-page":"102216","DOI":"10.1016\/j.media.2021.102216","article-title":"AIforCOVID: predicting the clinical outcomes in patients with COVID-19 applying AI to chest-X-rays. An Italian multicentre study","volume":"74","author":"Soda","year":"2021","journal-title":"Med Image Anal"},{"key":"2024101711344147000_8.2.00010-2022.25","doi-asserted-by":"crossref","first-page":"1999","DOI":"10.1007\/s00330-020-07270-1","article-title":"Chest X-ray for predicting mortality and the need for ventilatory support in COVID-19 patients presenting to the emergency department","volume":"31","author":"Balbi","year":"2021","journal-title":"Eur Radiol"},{"key":"2024101711344147000_8.2.00010-2022.26","doi-asserted-by":"crossref","first-page":"207","DOI":"10.1016\/j.amsu.2020.09.044","article-title":"Mortality prediction model for the triage of COVID-19, pneumonia, and mechanically ventilated ICU patients: a retrospective study","volume":"59","author":"Ryan","year":"2020","journal-title":"Ann Med Surg"},{"key":"2024101711344147000_8.2.00010-2022.27","doi-asserted-by":"crossref","first-page":"210986","DOI":"10.1148\/radiol.2021219021","article-title":"Chest radiograph scoring alone or combined with other risk scores for predicting outcomes in COVID-19: a UK study","volume":"301","author":"Au-Yong","year":"2021","journal-title":"Radiology"}],"container-title":["ERJ Open Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1183\/23120541.00010-2022","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,24]],"date-time":"2025-02-24T05:15:30Z","timestamp":1740374130000},"score":1,"resource":{"primary":{"URL":"https:\/\/publications.ersnet.org\/lookup\/doi\/10.1183\/23120541.00010-2022"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4]]},"references-count":27,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2022,6,27]]},"published-print":{"date-parts":[[2022,4]]}},"alternative-id":["10.1183\/23120541.00010-2022"],"URL":"https:\/\/doi.org\/10.1183\/23120541.00010-2022","relation":{},"ISSN":["2312-0541"],"issn-type":[{"value":"2312-0541","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,4]]}}}