{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T01:47:09Z","timestamp":1783734429473,"version":"3.55.0"},"reference-count":36,"publisher":"Oxford University Press (OUP)","issue":"6","license":[{"start":{"date-parts":[[2022,3,10]],"date-time":"2022-03-10T00:00:00Z","timestamp":1646870400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["K01HL136687"],"award-info":[{"award-number":["K01HL136687"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R01 HL158626"],"award-info":[{"award-number":["R01 HL158626"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R01 LM013325"],"award-info":[{"award-number":["R01 LM013325"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"name":"University of Michigan Precision Health Award"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,5,11]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Objective<\/jats:title>\n                  <jats:p>When patients develop acute respiratory failure (ARF), accurately identifying the underlying etiology is essential for determining the best treatment. However, differentiating between common medical diagnoses can be challenging in clinical practice. Machine learning models could improve medical diagnosis by aiding in the diagnostic evaluation of these patients.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Materials and Methods<\/jats:title>\n                  <jats:p>Machine learning models were trained to predict the common causes of ARF (pneumonia, heart failure, and\/or chronic obstructive pulmonary disease [COPD]). Models were trained using chest radiographs and clinical data from the electronic health record (EHR) and applied to an internal and external cohort.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>The internal cohort of 1618 patients included 508 (31%) with pneumonia, 363 (22%) with heart failure, and 137 (8%) with COPD based on physician chart review. A model combining chest radiographs and EHR data outperformed models based on each modality alone. Models had similar or better performance compared to a randomly selected physician reviewer. For pneumonia, the combined model area under the receiver operating characteristic curve (AUROC) was 0.79 (0.77\u20130.79), image model AUROC was 0.74 (0.72\u20130.75), and EHR model AUROC was 0.74 (0.70\u20130.76). For heart failure, combined: 0.83 (0.77\u20130.84), image: 0.80 (0.71\u20130.81), and EHR: 0.79 (0.75\u20130.82). For COPD, combined: AUROC\u2009=\u20090.88 (0.83\u20130.91), image: 0.83 (0.77\u20130.89), and EHR: 0.80 (0.76\u20130.84). In the external cohort, performance was consistent for heart failure and increased for COPD, but declined slightly for pneumonia.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Conclusions<\/jats:title>\n                  <jats:p>Machine learning models combining chest radiographs and EHR data can accurately differentiate between common causes of ARF. Further work is needed to determine how these models could act as a diagnostic aid to clinicians in clinical settings.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/jamia\/ocac030","type":"journal-article","created":{"date-parts":[[2022,2,23]],"date-time":"2022-02-23T20:14:46Z","timestamp":1645647286000},"page":"1060-1068","source":"Crossref","is-referenced-by-count":35,"title":["Combining chest X-rays and electronic health record (EHR) data using machine learning to diagnose acute respiratory failure"],"prefix":"10.1093","volume":"29","author":[{"given":"Sarah","family":"Jabbour","sequence":"first","affiliation":[{"name":"Department of Electrical Engineering and Computer Science, Division of Computer Science and Engineering, University of Michigan, Ann Arbor, Michigan, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David","family":"Fouhey","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering and Computer Science, Division of Computer Science and Engineering, University of Michigan, Ann Arbor, Michigan, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ella","family":"Kazerooni","sequence":"additional","affiliation":[{"name":"Department of Radiology, University of Michigan Medical School, Ann Arbor, Michigan, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jenna","family":"Wiens","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering and Computer Science, Division of Computer Science and Engineering, University of Michigan, Ann Arbor, Michigan, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael W","family":"Sjoding","sequence":"additional","affiliation":[{"name":"Pulmonary and Critical Care Medicine, Department of Internal Medicine, University of Michigan Medical School, Ann Arbor, Michigan, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2022,3,10]]},"reference":[{"issue":"6","key":"2022051112235298900_ocac030-B1","doi-asserted-by":"crossref","first-page":"e0128","DOI":"10.1097\/CCE.0000000000000128","article-title":"The epidemiology of respiratory failure in the United States 2002-2017: a serial cross-sectional study","volume":"2","author":"Kempker","year":"2020","journal-title":"Crit Care Explor"},{"issue":"2","key":"2022051112235298900_ocac030-B2","doi-asserted-by":"crossref","first-page":"76","DOI":"10.1002\/jhm.2004","article-title":"Epidemiology and outcomes of acute respiratory failure in the United States, 2001 to 2009: a national survey","volume":"8","author":"Stefan","year":"2013","journal-title":"J Hosp Med"},{"key":"2022051112235298900_ocac030-B3","year":"2021"},{"key":"2022051112235298900_ocac030-B4","doi-asserted-by":"crossref","first-page":"h910","DOI":"10.1136\/bmj.h910","article-title":"The diagnostic accuracy of the natriuretic peptides in heart failure: systematic review and diagnostic meta-analysis in the acute care setting","volume":"350","author":"Roberts","year":"2015","journal-title":"BMJ"},{"issue":"1","key":"2022051112235298900_ocac030-B5","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1016\/S1388-9842(01)00200-8","article-title":"Heart failure in frail elderly patients: diagnostic difficulties, co-morbidities, polypharmacy and treatment dilemmas","volume":"4","author":"Lien","year":"2002","journal-title":"Eur J Heart Fail"},{"issue":"5","key":"2022051112235298900_ocac030-B6","doi-asserted-by":"crossref","first-page":"999","DOI":"10.1016\/j.ahj.2005.10.011","article-title":"How obesity affects the cut-points for B-type natriuretic peptide in the diagnosis of acute heart failure. Results from the Breathing Not Properly Multinational Study","volume":"151","author":"Daniels","year":"2006","journal-title":"Am Heart J"},{"issue":"1","key":"2022051112235298900_ocac030-B7","doi-asserted-by":"crossref","first-page":"R3","DOI":"10.1186\/cc6764","article-title":"Diagnostic utility of B-type natriuretic peptide in critically ill patients with pulmonary edema: a prospective cohort study","volume":"12","author":"Levitt","year":"2008","journal-title":"Crit Care"},{"key":"2022051112235298900_ocac030-B8","doi-asserted-by":"crossref","first-page":"149","DOI":"10.1097\/ACM.0b013e31823f71e6","article-title":"Relating faults in diagnostic reasoning with diagnostic errors and patient harm","volume":"87","author":"Zwaan","year":"2012","journal-title":"Acad Med"},{"key":"2022051112235298900_ocac030-B9","volume-title":"Improving Diagnosis in Health Care","year":"2015"},{"key":"2022051112235298900_ocac030-B10","doi-asserted-by":"crossref","first-page":"590","DOI":"10.1609\/aaai.v33i01.3301590","article-title":"Chexpert: a large chest radiograph dataset with uncertainty labels and expert comparison","volume":"33","author":"Irvin","year":"2019","journal-title":"AAAI"},{"key":"2022051112235298900_ocac030-B11","doi-asserted-by":"crossref","first-page":"136","DOI":"10.1038\/s41746-020-00341-z","article-title":"Fusion of medical imaging and electronic health records using deep learning: a systematic review and implementation guidelines","volume":"3","author":"Huang","year":"2020","journal-title":"NPJ Digit Med"},{"key":"2022051112235298900_ocac030-B12","author":"Johnson","year":"2020"},{"issue":"1","key":"2022051112235298900_ocac030-B13","doi-asserted-by":"crossref","first-page":"317","DOI":"10.1038\/s41597-019-0322-0","article-title":"MIMIC-CXR, a de-identified publicly available database of chest radiographs with free-text reports","volume":"6","author":"Johnson","year":"2019","journal-title":"Sci Data"},{"key":"2022051112235298900_ocac030-B14","author":"Johnson","year":"2019"},{"issue":"23","key":"2022051112235298900_ocac030-B15","doi-asserted-by":"crossref","first-page":"e215","DOI":"10.1161\/01.CIR.101.23.e215","article-title":"PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals","volume":"101","author":"Goldberger","year":"2000","journal-title":"Circulation"},{"issue":"10","key":"2022051112235298900_ocac030-B16","doi-asserted-by":"crossref","first-page":"913","DOI":"10.1056\/NEJMoa1203830","article-title":"Pulmonary arterial enlargement and acute exacerbations of COPD","volume":"367","author":"Wells","year":"2012","journal-title":"N Engl J Med"},{"issue":"1","key":"2022051112235298900_ocac030-B17","doi-asserted-by":"crossref","first-page":"159","DOI":"10.2307\/2529310","article-title":"The measurement of observer agreement for categorical data","volume":"33","author":"Landis","year":"1977","journal-title":"Biometrics"},{"issue":"6","key":"2022051112235298900_ocac030-B18","doi-asserted-by":"crossref","first-page":"543","DOI":"10.1016\/0895-4356(90)90158-L","article-title":"High agreement but low kappa: I. The problems of two paradoxes","volume":"43","author":"Feinstein","year":"1990","journal-title":"J Clin Epidemiol"},{"issue":"12","key":"2022051112235298900_ocac030-B19","doi-asserted-by":"crossref","first-page":"1921","DOI":"10.1093\/jamia\/ocaa139","article-title":"Democratizing EHR analyses with FIDDLE: a flexible data-driven preprocessing pipeline for structured clinical data","volume":"27","author":"Tang","year":"2020","journal-title":"J Am Med Inform Assoc"},{"key":"2022051112235298900_ocac030-B20","first-page":"4700","author":"Huang"},{"issue":"10","key":"2022051112235298900_ocac030-B21","doi-asserted-by":"crossref","first-page":"1345","DOI":"10.1109\/TKDE.2009.191","article-title":"A survey on transfer learning","volume":"22","author":"Pan","year":"2010","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"2022051112235298900_ocac030-B22","author":"Naeini"},{"issue":"11","key":"2022051112235298900_ocac030-B23","doi-asserted-by":"crossref","first-page":"665","DOI":"10.1038\/s42256-020-00257-z","article-title":"Shortcut learning in deep neural networks","volume":"2","author":"Geirhos","year":"2020","journal-title":"Nat Mach Intell"},{"key":"2022051112235298900_ocac030-B24","first-page":"618","author":"Selvaraju"},{"issue":"10","key":"2022051112235298900_ocac030-B25","doi-asserted-by":"crossref","first-page":"1340","DOI":"10.1093\/bioinformatics\/btq134","article-title":"Permutation importance: a corrected feature importance measure","volume":"26","author":"Altmann","year":"2010","journal-title":"Bioinformatics"},{"key":"2022051112235298900_ocac030-B26","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1016\/j.rmed.2018.08.006","article-title":"Accuracy of diagnosis of COPD and factors associated with misdiagnosis in primary care setting. E-DIAL (Early DIAgnosis of obstructive lung disease) study group","volume":"143","author":"Nardini","year":"2018","journal-title":"Respir Med"},{"issue":"7","key":"2022051112235298900_ocac030-B27","doi-asserted-by":"crossref","first-page":"1041","DOI":"10.1016\/j.amjcard.2016.12.010","article-title":"Probability of accurate heart failure diagnosis and the implications for hospital readmissions","volume":"119","author":"Carey","year":"2017","journal-title":"Am J Cardiol"},{"issue":"2","key":"2022051112235298900_ocac030-B28","doi-asserted-by":"crossref","first-page":"343","DOI":"10.1378\/chest.110.2.343","article-title":"Interobserver reliability of the chest radiograph in community-acquired pneumonia. PORT Investigators","volume":"110","author":"Albaum","year":"1996","journal-title":"Chest"},{"key":"2022051112235298900_ocac030-B29","doi-asserted-by":"crossref","first-page":"775","DOI":"10.1097\/00001888-200308000-00003","article-title":"The importance of cognitive errors in diagnosis and strategies to minimize them","volume":"78","author":"Croskerry","year":"2003","journal-title":"Acad Med"},{"issue":"6","key":"2022051112235298900_ocac030-B30","doi-asserted-by":"crossref","first-page":"532","DOI":"10.1164\/rccm.200703-456SO","article-title":"Global strategy for the diagnosis, management, and prevention of chronic obstructive pulmonary disease: GOLD executive summary","volume":"176","author":"Rabe","year":"2007","journal-title":"Am J Respir Crit Care Med"},{"issue":"2","key":"2022051112235298900_ocac030-B31","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1007\/s11547-013-0318-3","article-title":"Saber-sheath trachea as a marker of severe airflow obstruction in chronic obstructive pulmonary disease","volume":"119","author":"Ciccarese","year":"2014","journal-title":"Radiol Med"},{"issue":"2","key":"2022051112235298900_ocac030-B32","doi-asserted-by":"crossref","first-page":"514","DOI":"10.1148\/radiol.2018180887","article-title":"Chest radiographs in congestive heart failure: visualizing neural network learning","volume":"290","author":"Seah","year":"2019","journal-title":"Radiology"},{"issue":"3","key":"2022051112235298900_ocac030-B33","doi-asserted-by":"crossref","first-page":"R82","DOI":"10.1186\/cc4926","article-title":"Acute respiratory failure in the elderly: etiology, emergency diagnosis and prognosis","volume":"10","author":"Ray","year":"2006","journal-title":"Crit Care"},{"issue":"9","key":"2022051112235298900_ocac030-B34","doi-asserted-by":"crossref","first-page":"1337","DOI":"10.1038\/s41591-019-0548-6","article-title":"Do no harm: a roadmap for responsible machine learning for health care","volume":"25","author":"Wiens","year":"2019","journal-title":"Nat Med"},{"issue":"5 Pt 2","key":"2022051112235298900_ocac030-B35","doi-asserted-by":"crossref","first-page":"1620","DOI":"10.1111\/j.1475-6773.2005.00444.x","article-title":"Measuring diagnoses: ICD code accuracy","volume":"40","author":"O'Malley","year":"2005","journal-title":"Health Serv Res"},{"key":"2022051112235298900_ocac030-B36","first-page":"11293","author":"Wang"}],"container-title":["Journal of the American Medical Informatics Association"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/jamia\/article-pdf\/29\/6\/1060\/43674435\/ocac030.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jamia\/article-pdf\/29\/6\/1060\/43674435\/ocac030.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,11]],"date-time":"2022-05-11T19:23:05Z","timestamp":1652296985000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jamia\/article\/29\/6\/1060\/6546605"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,3,10]]},"references-count":36,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2022,3,10]]},"published-print":{"date-parts":[[2022,5,11]]}},"URL":"https:\/\/doi.org\/10.1093\/jamia\/ocac030","relation":{},"ISSN":["1527-974X"],"issn-type":[{"value":"1527-974X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2022,6,1]]},"published":{"date-parts":[[2022,3,10]]}}}