{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T23:03:44Z","timestamp":1792105424124,"version":"4.4.0"},"reference-count":32,"publisher":"BMJ","issue":"1","funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["BMJ Open"],"accepted":{"date-parts":[[2017,10,31]]},"published-print":{"date-parts":[[2018,1]]},"abstract":"<jats:sec>\n                    <jats:title>Objectives<\/jats:title>\n                    <jats:p>\n                      We validate a machine learning-based sepsis-prediction algorithm (\n                      <jats:italic>InSight<\/jats:italic>\n                      ) for the detection and prediction of three sepsis-related gold standards, using only six vital signs. We evaluate robustness to missing data, customisation to site-specific data using transfer learning and generalisability to new settings.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Design<\/jats:title>\n                    <jats:p>A machine-learning algorithm with gradient tree boosting. Features for prediction were created from combinations of six vital sign measurements and their changes over time.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Setting<\/jats:title>\n                    <jats:p>A mixed-ward retrospective dataset from the University of California, San Francisco (UCSF) Medical Center (San Francisco, California, USA) as the primary source, an intensive care unit dataset from the Beth Israel Deaconess Medical Center (Boston, Massachusetts, USA) as a transfer-learning source and four additional institutions\u2019 datasets to evaluate generalisability.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Participants<\/jats:title>\n                    <jats:p>684\u2009443 total encounters, with 90\u2009353 encounters from June 2011 to March 2016 at UCSF.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Interventions<\/jats:title>\n                    <jats:p>None.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Primary and secondary outcome measures<\/jats:title>\n                    <jats:p>Area under the receiver operating characteristic (AUROC) curve for detection and prediction of sepsis, severe sepsis and septic shock.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      For detection of sepsis and severe sepsis,\n                      <jats:italic>InSight<\/jats:italic>\n                      achieves an AUROC curve of 0.92 (95% CI 0.90 to 0.93) and 0.87 (95% CI 0.86 to 0.88), respectively. Four hours before onset,\n                      <jats:italic>InSight<\/jats:italic>\n                      predicts septic shock with an AUROC of 0.96 (95% CI 0.94 to 0.98) and severe sepsis with an AUROC of 0.85 (95% CI 0.79 to 0.91).\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>\n                      <jats:italic>InSight<\/jats:italic>\n                      outperforms existing sepsis scoring systems in identifying and predicting sepsis, severe sepsis and septic shock. This is the first sepsis screening system to exceed an AUROC of 0.90 using only vital sign inputs.\n                      <jats:italic>InSight<\/jats:italic>\n                      is robust to missing data, can be customised to novel hospital data using a small fraction of site data and retains strong discrimination across all institutions.\n                    <\/jats:p>\n                  <\/jats:sec>","DOI":"10.1136\/bmjopen-2017-017833","type":"journal-article","created":{"date-parts":[[2018,1,26]],"date-time":"2018-01-26T23:00:27Z","timestamp":1517007627000},"page":"e017833","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":295,"title":["Multicentre validation of a sepsis prediction algorithm using only vital sign data in the emergency department, general ward and ICU"],"prefix":"10.1136","volume":"8","author":[{"given":"Qingqing","family":"Mao","sequence":"first","affiliation":[{"name":"Dascena Inc., Hayward, California, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Melissa","family":"Jay","sequence":"additional","affiliation":[{"name":"Dascena Inc., Hayward, California, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7745-3900","authenticated-orcid":false,"given":"Jana L","family":"Hoffman","sequence":"additional","affiliation":[{"name":"Dascena Inc., Hayward, California, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jacob","family":"Calvert","sequence":"additional","affiliation":[{"name":"Dascena Inc., Hayward, California, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christopher","family":"Barton","sequence":"additional","affiliation":[{"name":"Department of Emergency Medicine, University of California San Francisco, San Francisco, California, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David","family":"Shimabukuro","sequence":"additional","affiliation":[{"name":"Department of Anesthesia and Perioperative Care, University of California San Francisco, San Francisco, California, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lisa","family":"Shieh","sequence":"additional","affiliation":[{"name":"Department of Medicine, Stanford University School of Medicine, Stanford, California, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Uli","family":"Chettipally","sequence":"additional","affiliation":[{"name":"Department of Emergency Medicine, University of California San Francisco, San Francisco, California, USA"},{"name":"Kaiser Permanente South San Francisco Medical Center, South San Francisco, California, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Grant","family":"Fletcher","sequence":"additional","affiliation":[{"name":"Division of Internal Medicine, University of Washington School of Medicine, Seattle, Washington, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yaniv","family":"Kerem","sequence":"additional","affiliation":[{"name":"Department of Clinical Informatics, Stanford University School of Medicine, Stanford, California, USA"},{"name":"Department of Emergency Medicine, Kaiser Permanente Redwood City Medical Center, Redwood City, California, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yifan","family":"Zhou","sequence":"additional","affiliation":[{"name":"Dascena Inc., Hayward, California, USA"},{"name":"Department of Statistics, University of California Berkeley, Berkeley, California, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ritankar","family":"Das","sequence":"additional","affiliation":[{"name":"Dascena Inc., Hayward, California, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"239","published-online":{"date-parts":[[2018,1,26]]},"reference":[{"key":"2025101814284978000_8.1.e017833.1","first-page":"1","article-title":"Deaths: final data for 2010","volume":"61","author":"Murphy","year":"2013","journal-title":"Natl Vital Stat Rep"},{"key":"2025101814284978000_8.1.e017833.2","doi-asserted-by":"publisher","DOI":"10.1097\/00003246-200107000-00002"},{"key":"2025101814284978000_8.1.e017833.3","doi-asserted-by":"publisher","DOI":"10.1097\/CCM.0000000000000026"},{"key":"2025101814284978000_8.1.e017833.4","unstructured":"Pfuntner A , Wier LM , Steiner C . Costs for Hospital Stays in the United States, 2010: Statistical Brief #146. In Healthcare Cost and Utilization Project (HCUP) Statistical Briefs: Cost H , Project U , Rockville; MDAgency for Healthcare Research and Quality USA, 2006. https:\/\/www.ncbi.nlm.nih.gov\/books\/NBK121966\/."},{"key":"2025101814284978000_8.1.e017833.5","unstructured":"O\u2019Brien J . The Cost of Sepsis. CDC Safe Healthcare Blog 2015 https:\/\/blogs.cdc.gov\/safehealthcare\/the-cost-of-sepsis\/#ref."},{"key":"2025101814284978000_8.1.e017833.6","doi-asserted-by":"publisher","DOI":"10.1097\/CCM.0b013e31827c09f8"},{"key":"2025101814284978000_8.1.e017833.7","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa010307"},{"key":"2025101814284978000_8.1.e017833.8","doi-asserted-by":"publisher","DOI":"10.1097\/01.CCM.0000259463.33848.3D"},{"key":"2025101814284978000_8.1.e017833.9","doi-asserted-by":"publisher","DOI":"10.1097\/01.CCM.0000217961.75225.E9"},{"key":"2025101814284978000_8.1.e017833.10","first-page":"530","article-title":"sccm\/esicm\/accp\/ats\/sis international sepsis definitions conference","volume":"2003","author":"Levy","year":"2001","journal-title":"Intensive Care Med"},{"key":"2025101814284978000_8.1.e017833.11","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2016.0287"},{"key":"2025101814284978000_8.1.e017833.12","doi-asserted-by":"publisher","DOI":"10.1136\/emj.2006.035816"},{"key":"2025101814284978000_8.1.e017833.13","doi-asserted-by":"publisher","DOI":"10.1001\/jama.1995.03520260039030"},{"key":"2025101814284978000_8.1.e017833.14","doi-asserted-by":"publisher","DOI":"10.1007\/BF01709751"},{"key":"2025101814284978000_8.1.e017833.15","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":"2025101814284978000_8.1.e017833.16","first-page":"391","article-title":"STRIDE--An integrated standards-based translational research informatics platform","volume":"2009","author":"Lowe","year":"2009","journal-title":"AMIA Annu Symp Proc"},{"key":"2025101814284978000_8.1.e017833.17","unstructured":"PostgreSQL Global Development Group. https:\/\/www.postgresql.org\/ (5 Oct 2017)."},{"key":"2025101814284978000_8.1.e017833.18","unstructured":"Van Rossum G . The Python Language Reference Manual: Network Theory Ltd, 2003. https:\/\/www.python.org\/."},{"key":"2025101814284978000_8.1.e017833.19","doi-asserted-by":"publisher","DOI":"10.1126\/scitranslmed.aab3719"},{"key":"2025101814284978000_8.1.e017833.20","doi-asserted-by":"publisher","DOI":"10.1016\/j.resuscitation.2012.01.004"},{"key":"2025101814284978000_8.1.e017833.21","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-009-5152-4"},{"key":"2025101814284978000_8.1.e017833.22","doi-asserted-by":"crossref","first-page":"69","DOI":"10.1016\/j.compbiomed.2016.05.003","article-title":"A computational approach to early sepsis detection","volume":"74","author":"Calvert","year":"2016","journal-title":"Comput Biol Med"},{"key":"2025101814284978000_8.1.e017833.23","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"},{"key":"2025101814284978000_8.1.e017833.24","doi-asserted-by":"crossref","first-page":"50","DOI":"10.1016\/j.amsu.2016.04.023","article-title":"High-performance detection and early prediction of septic shock for alcohol-use disorder patients","volume":"8","author":"Calvert","year":"2016","journal-title":"Ann Med Surg"},{"key":"2025101814284978000_8.1.e017833.25","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocw014"},{"key":"2025101814284978000_8.1.e017833.26","doi-asserted-by":"crossref","first-page":"74","DOI":"10.1016\/j.compbiomed.2016.05.015","article-title":"A computational approach to mortality prediction of alcohol use disorder inpatients","volume":"75","author":"Calvert","year":"2016","journal-title":"Comput Biol Med"},{"key":"2025101814284978000_8.1.e017833.27","doi-asserted-by":"crossref","first-page":"52","DOI":"10.1016\/j.amsu.2016.09.002","article-title":"Using electronic health record collected clinical variables to predict medical intensive care unit mortality","volume":"11","author":"Calvert","year":"2016","journal-title":"Ann Med Surg"},{"key":"2025101814284978000_8.1.e017833.28","doi-asserted-by":"publisher","DOI":"10.1097\/MLR.0b013e318268ac86"},{"key":"2025101814284978000_8.1.e017833.29","doi-asserted-by":"publisher","DOI":"10.1136\/amiajnl-2013-001815"},{"key":"2025101814284978000_8.1.e017833.30","doi-asserted-by":"crossref","unstructured":"Brause R , Hamker F , Paetz J . Septic shock diagnosis by neural networks and rule based systems. In: Schmitt M , Teodorescu HN , Jain A , eds. et alComputational intelligence techniques in medical diagnosis and prognosis. New York: Springer, 2002:323\u201356.","DOI":"10.1007\/978-3-7908-1788-1_12"},{"key":"2025101814284978000_8.1.e017833.31","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1002\/jhm.530","article-title":"Early Prediction of Septic Shock","volume":"1","author":"Thiel","year":"2010","journal-title":"J. Hosp. Med"},{"key":"2025101814284978000_8.1.e017833.32","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0174708","article-title":"Creating an automated trigger for sepsis clinical decision support at emergency department triage using machine learning","volume":"12","author":"Horng","year":"2017","journal-title":"PLoS One"}],"container-title":["BMJ Open"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/bmjopen-2017-017833","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,18]],"date-time":"2025-10-18T21:28:58Z","timestamp":1760822938000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmjopen.bmj.com\/lookup\/doi\/10.1136\/bmjopen-2017-017833"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,1]]},"references-count":32,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2018,1,26]]},"published-print":{"date-parts":[[2018,1]]}},"alternative-id":["10.1136\/bmjopen-2017-017833"],"URL":"https:\/\/doi.org\/10.1136\/bmjopen-2017-017833","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/243964","asserted-by":"object"}]},"ISSN":["2044-6055","2044-6055"],"issn-type":[{"value":"2044-6055","type":"print"},{"value":"2044-6055","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,1]]}}}