{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T04:38:04Z","timestamp":1792730284837,"version":"4.5.0"},"reference-count":24,"publisher":"Ovid Technologies (Wolters Kluwer Health)","content-domain":{"domain":["lww.com","ovid.com"],"crossmark-restriction":true},"short-container-title":[],"abstract":"\n Objectives:<\/jats:title>\n To determine whether predictions from a deep learning model that identifies acute respiratory distress syndrome (ARDS) findings on chest radiographs (CXRs) can also predict clinical outcomes beyond traditional indicators of hypoxemia and illness severity.<\/jats:p>\n <\/jats:sec>\n \n Design:<\/jats:title>\n Retrospective cohort study.<\/jats:p>\n <\/jats:sec>\n \n Setting:<\/jats:title>\n Single academic medical center.<\/jats:p>\n <\/jats:sec>\n \n Intervention:<\/jats:title>\n None.<\/jats:p>\n <\/jats:sec>\n \n Patients:<\/jats:title>\n Adult patients with CXRs performed at the time of invasive mechanical ventilation initiation.<\/jats:p>\n <\/jats:sec>\n \n Methods and Main Results:<\/jats:title>\n \n We applied a deep learning model that was previously trained to identify bilateral airspace opacities consistent with ARDS to CXRs of 6591 patients receiving invasive mechanical ventilation. The resulting ARDS-CXR scores were evaluated for their ability to discriminate risk of 28-day mortality and their association with 28-day mortality and time to extubation after adjusting for a patient\u2019s Pa\n o<\/jats:sc>\n 2<\/jats:sub>\n \/F\n io<\/jats:sc>\n 2<\/jats:sub>\n or Acute Physiology and Chronic Health Evaluation-IV. The median ARDS-CXR score was \u20132.09, corresponding to an ARDS probability of 15%, and 1089 (17%) patients had a positive score, corresponding to an ARDS probability above 50%. Twenty-eight-day mortality was 35.1% among patients with a positive score and 13.5% among patients with a negative score. ARDS-CXR scores below the ARDS threshold also stratified risk, with mortality increasing from 12.8% at a score of \u20132 to 19.9% at \u20131 and 27.5% at 0. The ARDS-CXR score area under the receiver operating characteristic (AUROC) curve was 0.68 (95% CI, 0.66\u20130.70) for predicting 28-day mortality, whereas the Pa\n o<\/jats:sc>\n 2<\/jats:sub>\n \/F\n io<\/jats:sc>\n 2<\/jats:sub>\n AUROC was 0.64 (95% CI, 0.62\u20130.66). After adjusting for either the patient\u2019s Pa\n o<\/jats:sc>\n 2<\/jats:sub>\n \/F\n io<\/jats:sc>\n 2<\/jats:sub>\n or Acute Physiology and Chronic Health Evaluation-IV, a 1-point increase in the ARDS-CXR score was significantly associated with higher 28-day mortality or prolonged time to extubation.\n <\/jats:p>\n <\/jats:sec>\n \n Conclusions:<\/jats:title>\n A deep learning\u2013derived ARDS-CXR score quantifying radiographic findings of ARDS independently predicted mortality and ventilator outcomes beyond hypoxemia and illness severity. Algorithmically derived markers of lung injury severity from chest imaging could be used to support clinical care decisions, predictive enrichment in research studies, or incorporated into a future ARDS definition.<\/jats:p>\n <\/jats:sec>","DOI":"10.1097\/ccm.0000000000007384","type":"journal-article","created":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T04:00:16Z","timestamp":1792728016000},"update-policy":"https:\/\/doi.org\/10.1097\/lww.0000000000001000","source":"Crossref","is-referenced-by-count":0,"title":["Association of Acute Respiratory Distress Syndrome Radiographic Findings Identified by Machine Learning and Outcomes of Patients Receiving Invasive Mechanical Ventilation"],"prefix":"10.1097","author":[{"given":"Yingchao","family":"Zhong","sequence":"first","affiliation":[{"name":"Department of Medicine, Stanford University, Palo Alto, CA."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mark","family":"Nuppnau","sequence":"additional","affiliation":[{"name":"Department of Internal Medicine, Division of Pulmonary and Critical Care, University of Michigan Medical School, Ann Arbor, MI."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Negar","family":"Farzaneh","sequence":"additional","affiliation":[{"name":"The Max Harry Weil Institute for Critical Care Research & Innovation, University of Michigan, Ann Arbor, MI."},{"name":"Department of Emergency Medicine, University of Michigan Medical School, Ann Arbor, MI."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sardar","family":"Ansari","sequence":"additional","affiliation":[{"name":"The Max Harry Weil Institute for Critical Care Research & Innovation, University of Michigan, Ann Arbor, MI."},{"name":"Department of Emergency Medicine, University of Michigan Medical School, Ann Arbor, MI."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael W.","family":"Sjoding","sequence":"additional","affiliation":[{"name":"Department of Internal Medicine, Division of Pulmonary and Critical Care, University of Michigan Medical School, Ann Arbor, MI."},{"name":"The Max Harry Weil Institute for Critical Care Research & Innovation, University of Michigan, Ann Arbor, MI."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"276","published-online":{"date-parts":[[2026,10,23]]},"reference":[{"key":"R1-20261023","doi-asserted-by":"crossref","first-page":"1742","DOI":"10.1513\/AnnalsATS.201512-841OC","article-title":"Mortality trends of acute respiratory distress syndrome in the United States from 1999 to 2013.","volume":"13","author":"Cochi","year":"2016","journal-title":"Ann Am Thorac Soc"},{"key":"R2-20261023","doi-asserted-by":"crossref","first-page":"788","DOI":"10.1001\/jama.2016.0291","article-title":"Epidemiology, patterns of care, and mortality for patients with acute respiratory distress syndrome in intensive care units in 50 Countries.","volume":"315","author":"Bellani","year":"2016","journal-title":"JAMA"},{"key":"R3-20261023","doi-asserted-by":"crossref","first-page":"1932","DOI":"10.1007\/s00134-011-2380-4","article-title":"The ALIEN study: Incidence and outcome of acute respiratory distress syndrome in the era of lung protective ventilation.","volume":"37","author":"Villar","year":"2011","journal-title":"Intensive Care Med"},{"key":"R4-20261023","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1164\/rccm.202303-0558WS","article-title":"A new global definition of acute respiratory distress syndrome.","volume":"209","author":"Matthay","year":"2024","journal-title":"Am J Respir Crit Care Med"},{"key":"R5-20261023","first-page":"2526","article-title":"Acute respiratory distress syndrome: The Berlin definition.","volume":"307","author":"Ranieri","year":"2012","journal-title":"JAMA"},{"key":"R6-20261023","doi-asserted-by":"crossref","first-page":"1347","DOI":"10.1378\/chest.116.5.1347","article-title":"Interobserver variability in applying a radiographic definition for ARDS.","volume":"116","author":"Rubenfeld","year":"1999","journal-title":"Chest"},{"key":"R7-20261023","doi-asserted-by":"crossref","first-page":"361","DOI":"10.1016\/j.chest.2017.11.037","article-title":"Interobserver reliability of the Berlin ARDS definition and strategies to improve the reliability of ARDS diagnosis.","volume":"153","author":"Sjoding","year":"2018","journal-title":"Chest"},{"key":"R8-20261023","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1164\/ajrccm.161.1.9809003","article-title":"Interobserver variation in interpreting chest radiographs for the diagnosis of acute respiratory distress syndrome.","volume":"161","author":"Meade","year":"2000","journal-title":"Am J Respir Crit Care Med"},{"key":"R9-20261023","doi-asserted-by":"crossref","first-page":"2100043","DOI":"10.1183\/13993003.00043-2021","article-title":"Shifting the paradigm: Unilateral infiltrates and ARDS?","volume":"57","author":"Torres","year":"2021","journal-title":"Eur Respir J"},{"issue":"5 Suppl 1","key":"R10-20261023","doi-asserted-by":"crossref","first-page":"S23","DOI":"10.1097\/PCC.0000000000000432","article-title":"Pediatric acute respiratory distress syndrome: Definition, incidence, and epidemiology: Proceedings from the Pediatric Acute Lung Injury Consensus Conference.","volume":"16","author":"Khemani","year":"2015","journal-title":"Pediatr Crit Care Med"},{"issue":"12 Suppl 2","key":"R11-20261023","doi-asserted-by":"crossref","first-page":"S87","DOI":"10.1097\/PCC.0000000000003161","article-title":"Definition, incidence, and epidemiology of pediatric acute respiratory distress syndrome: From the second pediatric acute lung injury consensus Conference.","volume":"24","author":"Yehya","year":"2023","journal-title":"Pediatr Crit Care Med"},{"key":"R12-20261023","doi-asserted-by":"crossref","first-page":"840","DOI":"10.1136\/thoraxjnl-2017-211280","article-title":"Severity scoring of lung oedema on the chest radiograph is associated with clinical outcomes in ARDS.","volume":"73","author":"Warren","year":"2018","journal-title":"Thorax"},{"key":"R13-20261023","doi-asserted-by":"crossref","first-page":"e340","DOI":"10.1016\/S2589-7500(21)00056-X","article-title":"Deep learning to detect acute respiratory distress syndrome on chest radiographs: A retrospective study with external validation.","volume":"3","author":"Sjoding","year":"2021","journal-title":"Lancet Digit Health"},{"key":"R14-20261023","doi-asserted-by":"crossref","first-page":"62","DOI":"10.1038\/s41746-023-00797-9","article-title":"Collaborative strategies for deploying artificial intelligence to complement physician diagnoses of acute respiratory distress syndrome.","volume":"6","author":"Farzaneh","year":"2023","journal-title":"NPJ Digit Med"},{"key":"R15-20261023","doi-asserted-by":"crossref","first-page":"1211","DOI":"10.1513\/AnnalsATS.202007-772OC","article-title":"Validating measures of disease severity in acute respiratory distress syndrome.","volume":"18","author":"Sedhai","year":"2021","journal-title":"Ann Am Thorac Soc"},{"key":"R17-20261023","doi-asserted-by":"crossref","first-page":"333","DOI":"10.1164\/rccm.201804-0692OC","article-title":"Physiologic analysis and clinical performance of the ventilatory ratio in acute respiratory distress syndrome.","volume":"199","author":"Sinha","year":"2019","journal-title":"Am J Respir Crit Care Med"},{"key":"R18-20261023","doi-asserted-by":"crossref","first-page":"4051","DOI":"10.1002\/sim.8281","article-title":"The Integrated Calibration Index (ICI) and related metrics for quantifying the calibration of logistic regression models.","volume":"38","author":"Austin","year":"2019","journal-title":"Stat Med"},{"key":"R19-20261023","doi-asserted-by":"crossref","first-page":"496","DOI":"10.1080\/01621459.1999.10474144","article-title":"A proportional hazards model for the subdistribution of a competing risk.","volume":"94","author":"Fine","year":"1999","journal-title":"J Am Stat Assoc"},{"key":"R20-20261023","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1186\/s41512-019-0064-7","article-title":"A simple, step-by-step guide to interpreting decision curve analysis.","volume":"3","author":"Vickers","year":"2019","journal-title":"Diagn Progn Res"},{"key":"R21-20261023","doi-asserted-by":"crossref","first-page":"222","DOI":"10.1016\/j.jcrc.2020.01.012","article-title":"The evolution of radiographic edema in ARDS and its association with clinical outcomes: A prospective cohort study in adult patients.","volume":"56","author":"Kotok","year":"2020","journal-title":"J Crit Care"},{"key":"R22-20261023","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1148\/radiol.2373041515","article-title":"Prediction of prognosis for acute respiratory distress syndrome with thin-section CT: Validation in 44 cases.","volume":"238","author":"Ichikado","year":"2006","journal-title":"Radiology"},{"key":"R23-20261023","doi-asserted-by":"crossref","first-page":"62","DOI":"10.1186\/s12890-023-02826-5","article-title":"Lung ultrasound score and in-hospital mortality of adults with acute respiratory distress syndrome: A meta-analysis.","volume":"24","author":"Wang","year":"2024","journal-title":"BMC Pulm Med"},{"key":"R24-20261023","doi-asserted-by":"crossref","first-page":"268","DOI":"10.1186\/s12931-024-02893-0","article-title":"Associations of early changes in lung ultrasound aeration scores and mortality in invasively ventilated patients: A post hoc analysis.","volume":"25","author":"Sinnige","year":"2024","journal-title":"Respir Res"},{"key":"R25-20261023","doi-asserted-by":"crossref","first-page":"870","DOI":"10.1016\/S2213-2600(19)30138-9","article-title":"Personalised mechanical ventilation tailored to lung morphology versus low positive end-expiratory pressure for patients with acute respiratory distress syndrome in France (the LIVE study): A multicentre, single-blind, randomised controlled trial.","volume":"7","author":"Constantin","year":"2019","journal-title":"Lancet Respir Med"}],"container-title":["Critical Care Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.ovid.com\/10.1097\/CCM.0000000000007384","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T04:00:22Z","timestamp":1792728022000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ovid.com\/10.1097\/CCM.0000000000007384"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,23]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1097\/ccm.0000000000007384","relation":{},"ISSN":["0090-3493","1530-0293"],"issn-type":[{"value":"0090-3493","type":"print"},{"value":"1530-0293","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,23]]}}}