{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T08:09:20Z","timestamp":1772525360392,"version":"3.50.1"},"reference-count":39,"publisher":"Oxford University Press (OUP)","issue":"3","license":[{"start":{"date-parts":[[2020,1,17]],"date-time":"2020-01-17T00:00:00Z","timestamp":1579219200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000272","name":"National Institute for Health Research","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000272","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100009362","name":"South London and Maudsley NHS Foundation Trust","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100009362","id-type":"DOI","asserted-by":"publisher"}]},{"name":"King\u2019s College London and University College London Hospitals"},{"name":"Health Data Research UK"},{"DOI":"10.13039\/501100000265","name":"Medical Research Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000265","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Economic and Social Research Council, Department of Health and Social Care"},{"name":"Chief Scientist Office of the Scottish Government Health and Social Care Directorates, Health and Social Care Research"},{"name":"Development Division"},{"DOI":"10.13039\/501100001626","name":"Public Health Agency","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100001626","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100000274","name":"British Heart Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000274","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100010269","name":"Wellcome Trust","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100010269","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000265","name":"MRC","doi-asserted-by":"publisher","award":["MR\/S004149\/1"],"award-info":[{"award-number":["MR\/S004149\/1"]}],"id":[{"id":"10.13039\/501100000265","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000265","name":"MRC","doi-asserted-by":"publisher","award":["MC_PC_18029"],"award-info":[{"award-number":["MC_PC_18029"]}],"id":[{"id":"10.13039\/501100000265","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,3,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Objectives<\/jats:title>\n                  <jats:p>Current machine learning models aiming to predict sepsis from electronic health records (EHR) do not account 20 for the heterogeneity of the condition despite its emerging importance in prognosis and treatment. This work demonstrates the added value of stratifying the types of organ dysfunction observed in patients who develop sepsis in the intensive care unit (ICU) in improving the ability to recognize patients at risk of sepsis from their EHR data.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Materials and Methods<\/jats:title>\n                  <jats:p>Using an ICU dataset of 13 728 records, we identify clinically significant sepsis subpopulations with distinct organ dysfunction patterns. We perform classification experiments with random forest, gradient boost trees, and support vector machines, using the identified subpopulations to distinguish patients who develop sepsis in the ICU from those who do not.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>The classification results show that features selected using sepsis subpopulations as background knowledge yield a superior performance in distinguishing septic from non-septic patients regardless of the classification model used. The improved performance is especially pronounced in specificity, which is a current bottleneck in sepsis prediction machine learning models.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Conclusion<\/jats:title>\n                  <jats:p>Our findings can steer machine learning efforts toward more personalized models for complex conditions including sepsis.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/jamia\/ocz211","type":"journal-article","created":{"date-parts":[[2019,12,6]],"date-time":"2019-12-06T12:43:55Z","timestamp":1575636235000},"page":"437-443","source":"Crossref","is-referenced-by-count":61,"title":["On classifying sepsis heterogeneity in the ICU: insight using machine learning"],"prefix":"10.1093","volume":"27","author":[{"given":"Zina M","family":"Ibrahim","sequence":"first","affiliation":[{"name":"Department of Biostatistics & Health Informatics, King\u2019s College London, London, UK"},{"name":"Institute of Health Informatics, University College London, London, UK"},{"name":"Health Data Research UK, University College London, London, UK"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0213-5668","authenticated-orcid":false,"given":"Honghan","family":"Wu","sequence":"additional","affiliation":[{"name":"Usher Institute of Population Health Sciences and Informatics, University of Edinburgh, Edinburgh, UK"}]},{"given":"Ahmed","family":"Hamoud","sequence":"additional","affiliation":[{"name":"Department of Renal Medicine, East and North Hertfordshire NHS Trust, Stevenage, UK"}]},{"given":"Lukas","family":"Stappen","sequence":"additional","affiliation":[{"name":"Embedded Intelligence for Health Care and Wellbeing, University of Augsburg, Augsburg, Germany"}]},{"given":"Richard J B","family":"Dobson","sequence":"additional","affiliation":[{"name":"Department of Biostatistics & Health Informatics, King\u2019s College London, London, UK"},{"name":"Institute of Health Informatics, University College London, London, UK"},{"name":"Health Data Research UK, University College London, London, UK"}]},{"given":"Andrea","family":"Agarossi","sequence":"additional","affiliation":[{"name":"Department of Anaesthesia and Intensive Care, Luigi Sacco Hospital, Milan, Italy"}]}],"member":"286","published-online":{"date-parts":[[2020,1,17]]},"reference":[{"issue":"3","key":"2020110613091497800_ocz211-B1","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1164\/rccm.201504-0781OC","article-title":"Assessment of global incidence and mortality of hospital-treated sepsis. Current estimates and limitations","volume":"193","author":"Fleischmann","year":"2016","journal-title":"Am J Respir Crit Care Med"},{"issue":"5","key":"2020110613091497800_ocz211-B2","doi-asserted-by":"crossref","first-page":"1167","DOI":"10.1097\/CCM.0b013e31827c09f8","article-title":"Benchmarking the incidence and mortality of severe sepsis in the United States","volume":"41","author":"Gaieski","year":"2013","journal-title":"Crit Care Med"},{"issue":"2","key":"2020110613091497800_ocz211-B3","doi-asserted-by":"crossref","first-page":"165","DOI":"10.1007\/s00134-012-2769-8","article-title":"Surviving sepsis campaign: international guidelines for management of severe sepsis and septic shock","volume":"39","author":"Dellinger","year":"2013","journal-title":"Intensive Care Med"},{"issue":"8","key":"2020110613091497800_ocz211-B4","doi-asserted-by":"crossref","first-page":"1749","DOI":"10.1097\/CCM.0000000000000330","article-title":"Empiric antibiotic treatment reduces mortality in severe sepsis and septic shock from the first hour: results from a guideline-based performance improvement program","volume":"42","author":"Ferrer","year":"2014","journal-title":"Crit Care Med"},{"issue":"23","key":"2020110613091497800_ocz211-B5","doi-asserted-by":"crossref","first-page":"2235","DOI":"10.1056\/NEJMoa1703058","article-title":"Time to treatment and mortality during mandated emergency care for sepsis","volume":"376","author":"Seymour","year":"2017","journal-title":"N Engl J Med"},{"issue":"11","key":"2020110613091497800_ocz211-B6","doi-asserted-by":"crossref","first-page":"1123","DOI":"10.1016\/j.cmi.2018.03.032","article-title":"Accuracy of quick sequential organ failure assessment (qSOFA) score and systemic inflammatory response syndrome (SIRSs) criteria for predicting mortality in hospitalized patients with suspected infection: a meta-analysis of observational studies","volume":"24","author":"Maitra","year":"2018","journal-title":"Clin Microbiol Infect"},{"issue":"3","key":"2020110613091497800_ocz211-B7","doi-asserted-by":"crossref","first-page":"161","DOI":"10.1016\/S2213-2600(18)30072-9","article-title":"Crying wolf: the growing fatigue around sepsis alerts","volume":"6","year":"2018","journal-title":"Lancet Respir Med"},{"issue":"8","key":"2020110613091497800_ocz211-B8","doi-asserted-by":"crossref","first-page":"801","DOI":"10.1001\/jama.2016.0287","article-title":"The third international consensus definitions for sepsis and septic shock (sepsis-3)","volume":"315","author":"Singer","year":"2016","journal-title":"J Am Med Assoc"},{"issue":"1","key":"2020110613091497800_ocz211-B9","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1186\/s13049-017-0399-4","article-title":"Poor performance of quick-sofa (qSOFA) score in predicting severe sepsis and mortality-a prospective study of patients admitted with infection to the emergency department","volume":"25","author":"Askim","year":"2017","journal-title":"Scand J Trauma Resusc Emerg Med"},{"issue":"3","key":"2020110613091497800_ocz211-B10","doi-asserted-by":"crossref","first-page":"e000088","DOI":"10.1136\/bmjoq-2017-000088","article-title":"Data-driven approach to early warning score-based alert management","volume":"7","author":"Capan","year":"2018","journal-title":"BMJ Open Qual"},{"key":"2020110613091497800_ocz211-B11","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.cmpb.2018.12.027","article-title":"Prediction of sepsis patients using machine learning approach: a meta-analysis","volume":"170","author":"Islam","year":"2019","journal-title":"Comput Methods Programs Biomed"},{"issue":"1","key":"2020110613091497800_ocz211-B12","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1097\/NCQ.0000000000000198","article-title":"Predicting sepsis risk using the \u201csniffer\u201d algorithm in the electronic medical record","volume":"32","author":"Olenick","year":"2017","journal-title":"J Nurs Care Qual"},{"issue":"1","key":"2020110613091497800_ocz211-B13","doi-asserted-by":"crossref","first-page":"248","DOI":"10.1016\/j.compbiomed.2017.08.015","article-title":"Learning representations for the early detection of sepsis with deep neural networks","volume":"89","author":"Kam","year":"2017","journal-title":"Comput Biol Med"},{"issue":"1","key":"2020110613091497800_ocz211-B14","doi-asserted-by":"crossref","first-page":"e017833","DOI":"10.1136\/bmjopen-2017-017833","article-title":"Multicentre validation of a sepsis prediction algorithm using only vital sign data in the emergency department, general ward and ICU","volume":"8","author":"Mao","year":"2018","journal-title":"BMJ Open"},{"issue":"3","key":"2020110613091497800_ocz211-B15","doi-asserted-by":"crossref","first-page":"e28","DOI":"10.2196\/medinform.5909","article-title":"Prediction of sepsis in the intensive care unit with minimal electronic health record data: a machine learning approach","volume":"4","author":"Desautels","year":"2016","journal-title":"JMIR Med Inform"},{"issue":"5","key":"2020110613091497800_ocz211-B16","doi-asserted-by":"crossref","first-page":"814","DOI":"10.1007\/s00134-015-3764-7","article-title":"Phenotypic clusters within sepsis-associated multiple organ dysfunction syndrome","volume":"41","author":"Knox","year":"2015","journal-title":"Intensive Care Med"},{"issue":"5","key":"2020110613091497800_ocz211-B17","doi-asserted-by":"crossref","first-page":"e1002022","DOI":"10.1371\/journal.pmed.1002022","article-title":"The clinical challenge of sepsis identification and monitoring","volume":"13","author":"Vincent","year":"2016","journal-title":"PLoS Med"},{"issue":"11","key":"2020110613091497800_ocz211-B18","doi-asserted-by":"crossref","first-page":"1805","DOI":"10.1097\/CCM.0000000000002648","article-title":"Investigating the impact of different suspicion of infection criteria on the accuracy of quick sepsis-related organ failure assessment, systemic inflammatory response syndrome, and early warning scores","volume":"45","author":"Churpek","year":"2017","journal-title":"Crit Care Med"},{"issue":"2","key":"2020110613091497800_ocz211-B19","doi-asserted-by":"crossref","first-page":"e000158","DOI":"10.1136\/bmjoq-2017-000158","article-title":"Reducing patient mortality, length of stay and readmissions through machine learning-based sepsis prediction in the emergency department, intensive care unit and hospital floor units","volume":"6","author":"McCoy","year":"2017","journal-title":"BMJ Open Qual"},{"issue":"9","key":"2020110613091497800_ocz211-B20","doi-asserted-by":"crossref","first-page":"762","DOI":"10.1136\/bmjqs-2018-008765","article-title":"Electronic health record-based clinical decision support alert for severe sepsis: a randomised evaluation","volume":"28","author":"Downing","year":"2019","journal-title":"BMJ Qual Saf"},{"issue":"20","key":"2020110613091497800_ocz211-B21","doi-asserted-by":"crossref","first-page":"2003","DOI":"10.1001\/jama.2019.5791","article-title":"Derivation, validation, and potential treatment implications of novel clinical phenotypes for sepsis","volume":"321","author":"Seymour","year":"2019","journal-title":"J Am Med Assoc"},{"issue":"1","key":"2020110613091497800_ocz211-B22","doi-asserted-by":"crossref","first-page":"160035","DOI":"10.1038\/sdata.2016.35","article-title":"MIMIC-III, a freely accessible critical care database","volume":"3","author":"Johnson","year":"2016","journal-title":"Sci Data"},{"key":"2020110613091497800_ocz211-B23","author":"Johnson"},{"issue":"9","key":"2020110613091497800_ocz211-B24","doi-asserted-by":"crossref","first-page":"1464","DOI":"10.1109\/5.58325","article-title":"The self-organizing map","volume":"78","author":"Kohonen","year":"1990","journal-title":"Proc IEEE"},{"key":"2020110613091497800_ocz211-B25","first-page":"407","article-title":"Anomaly detection using self-organizing maps-based k-nearest neighbor algorithm","author":"Tian","year":"2014"},{"issue":"5","key":"2020110613091497800_ocz211-B26","doi-asserted-by":"crossref","first-page":"403","DOI":"10.1016\/j.medengphy.2004.09.008","article-title":"Classification of motor commands using a modified self-organising feature map","volume":"27","author":"Sebelius","year":"2005","journal-title":"Med Eng Phys"},{"issue":"8-9","key":"2020110613091497800_ocz211-B27","doi-asserted-by":"crossref","first-page":"953","DOI":"10.1016\/S0893-6080(02)00070-9","article-title":"Analysis and visualization of gene expression data using self-organizing maps","volume":"15","author":"Nikkil\u00e4","year":"2002","journal-title":"Neural Netw"},{"issue":"5","key":"2020110613091497800_ocz211-B28","doi-asserted-by":"crossref","first-page":"550","DOI":"10.1164\/rccm.201301-0156OC","article-title":"Ten-year follow-up of cluster-based asthma phenotypes in adults: a pooled analysis of three cohorts","volume":"188","author":"Boudier","year":"2013","journal-title":"Am J Respir Crit Care Med"},{"issue":"7","key":"2020110613091497800_ocz211-B29","doi-asserted-by":"crossref","first-page":"728","DOI":"10.1164\/rccm.201209-1665OC","article-title":"Clusters of comorbidities based on validated objective measurements and systemic inflammation in patients with chronic obstructive pulmonary disease","volume":"187","author":"Vanfleteren","year":"2013","journal-title":"Am J Respir Crit Care Med"},{"issue":"5","key":"2020110613091497800_ocz211-B30","doi-asserted-by":"crossref","first-page":"921","DOI":"10.1016\/j.jbi.2013.07.010","article-title":"A machine- learned knowledge discovery method for associating complex phenotypes with complex genotypes application to pain","volume":"46","author":"L\u00f6tsch","year":"2013","journal-title":"J Biomed Inform"},{"issue":"7","key":"2020110613091497800_ocz211-B31","doi-asserted-by":"crossref","first-page":"1","DOI":"10.18637\/jss.v087.i07","article-title":"Flexible self-organizing maps in Kohonen 3.0","volume":"87","author":"Wehrens","year":"2018","journal-title":"J Stat Softw"},{"issue":"6","key":"2020110613091497800_ocz211-B32","doi-asserted-by":"crossref","first-page":"1","DOI":"10.18637\/jss.v061.i06","article-title":"NbClust: an R package for determining the relevant number of clusters in a data set","volume":"61","author":"Charrad","year":"2014","journal-title":"J Stat Softw"},{"issue":"1","key":"2020110613091497800_ocz211-B33","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach Learn"},{"issue":"1","key":"2020110613091497800_ocz211-B34","doi-asserted-by":"crossref","first-page":"307","DOI":"10.1186\/1471-2105-9-307","article-title":"Conditional variable importance for random forests","volume":"9","author":"Strobl","year":"2008","journal-title":"BMC Bioinformatics"},{"issue":"1","key":"2020110613091497800_ocz211-B35","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1186\/1471-2105-8-25","article-title":"Bias in random forest variable importance measures: illustrations, sources, and a solution","volume":"8","author":"Strobl","year":"2007","journal-title":"BMC Bioinformatics"},{"issue":"170","key":"2020110613091497800_ocz211-B36","first-page":"1","article-title":"MLR: machine learning in R","volume":"17","author":"Bischl","year":"2016","journal-title":"J Mach Learn Res"},{"key":"2020110613091497800_ocz211-B37","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1016\/j.jcrc.2016.11.037","article-title":"Sepsis as 2 problems: identifying sepsis at admission and predicting onset in the hospital using an electronic medical record-based acuity score","volume":"38","author":"Rothman","year":"2017","journal-title":"J Crit Care"},{"issue":"6","key":"2020110613091497800_ocz211-B38","doi-asserted-by":"crossref","first-page":"739","DOI":"10.1016\/j.jelectrocard.2017.08.013","article-title":"Early sepsis detection in critical care patients using multiscale blood pressure and heart rate dynamics","volume":"50","author":"Shashikumar","year":"2017","journal-title":"J Electrocardiol"},{"issue":"6","key":"2020110613091497800_ocz211-B39","doi-asserted-by":"crossref","first-page":"e39","DOI":"10.1097\/MLR.0b013e318268ac86","article-title":"Identifying patients with severe sepsis using administrative claims: patient-level validation of the Angus implementation of the international consensus conference definition of severe sepsis","volume":"52","author":"Iwashyna","year":"2014","journal-title":"Med Care"}],"container-title":["Journal of the American Medical Informatics Association"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/jamia\/article-pdf\/27\/3\/437\/34153319\/ocz211.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"http:\/\/academic.oup.com\/jamia\/article-pdf\/27\/3\/437\/34153319\/ocz211.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,11,6]],"date-time":"2020-11-06T19:26:11Z","timestamp":1604690771000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jamia\/article\/27\/3\/437\/5709027"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,1,17]]},"references-count":39,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2020,1,17]]},"published-print":{"date-parts":[[2020,3,1]]}},"URL":"https:\/\/doi.org\/10.1093\/jamia\/ocz211","relation":{},"ISSN":["1527-974X"],"issn-type":[{"value":"1527-974X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2020,3]]},"published":{"date-parts":[[2020,1,17]]}}}