{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,28]],"date-time":"2026-10-28T01:08:09Z","timestamp":1793149689125,"version":"4.5.0"},"reference-count":43,"publisher":"American Medical Association (AMA)","issue":"4","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JAMA Netw Open"],"abstract":"\n Importance<\/jats:title>\n Early detection of sepsis improves clinical outcomes, but the Early Detection of Sepsis Model, version 1 (Epic Systems Corp) has shown poor performance. Comparing sepsis models is complicated by varying outcome definitions and limited generalizability outside the development site.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n To evaluate the Early Detection of Sepsis Model, version 2 using multiple standard sepsis definitions.<\/jats:p>\n <\/jats:sec>\n \n Design, Setting, and Participants<\/jats:title>\n This diagnostic study included all adult (aged \u226518 years) encounters from emergency departments, inpatient units, intensive care units, and perioperative areas across 9 acute care hospitals between March 17 and August 31, 2024. The locally trained gradient-boosted tree ensemble sepsis model, incorporating patient demographics, vital signs, laboratory results, medication administration, and other clinical features, generated predictions every 15 minutes. Model performance was evaluated against 3 electronically computable sepsis definitions: the Third International Consensus Definitions for Sepsis and Septic Shock (Sepsis-3); Centers for Medicare &amp;amp; Medicaid Services Severe Sepsis and Septic Shock: Management Bundle (SEP-1); and the Centers for Disease Control and Prevention Adult Sepsis Event (ASE).<\/jats:p>\n <\/jats:sec>\n \n Exposure<\/jats:title>\n Silent deployment of the sepsis model.<\/jats:p>\n <\/jats:sec>\n \n Main Outcomes and Measures<\/jats:title>\n Model performance metrics included discrimination, as measured using the area under the receiver operating characteristic curve (AUROC), and precision, as measured by the area under the precision-recall curve (AUPRC). Test characteristics and potential lead-time warning were evaluated over a range of model score thresholds.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n Among 198\u202f494 patient encounters (median [IQR] age, 55 [36-71] years; 54.8% female) the incidence of sepsis varied by outcome definition. A total of 5832 encounters (2.9%) met the Sepsis-3 definition, 2366 (1.2%) met the SEP-1 definition, and 3881 (2.0%) met the ASE definition. The AUROC and AUPRC were, respectively, 0.89 (95% CI, 0.89-0.90) and 0.24 (95% CI, 0.23-0.25) for Sepsis-3, 0.94 (95% CI, 0.94-0.94) and 0.16 (95% CI, 0.15-0.17) for SEP-1, and 0.85 (95% CI, 0.85-0.86) and 0.11 (95% CI, 0.11-0.12) for ASE. In the overall study population, the Youden top left threshold for the Sepsis-3 outcome definition was 9, which yielded a positive predictive (PPV) of 11.4% (95% CI, 11.1%-11.7%) and median lead time of 3.4 hours (IQR, 0.9-22.3 hours). The SEP-1 had a PPV of 6.8 (95% CI, 6.6-7.1 9.9) and median (IQR) lead time of 4.5 (4.3-23.1) hours, and the ASE had a PPV of 5.9 (95% CI, 5.7-6.0) and median (IQR) lead time of 1.4 (0.5-14.8) hours.<\/jats:p>\n <\/jats:sec>\n \n Conclusions and Relevance<\/jats:title>\n This cohort study found that the locally trained sepsis model showed moderate predictive performance, with discrimination, precision, and lead time varying considerably by the sepsis definition applied. Although the model provided some advance warning before sepsis onset, a high false-positive rate may limit its clinical utility without careful threshold selection and tailored implementation.<\/jats:p>\n <\/jats:sec>","DOI":"10.1001\/jamanetworkopen.2026.5599","type":"journal-article","created":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T15:00:35Z","timestamp":1775574035000},"page":"e265599","source":"Crossref","is-referenced-by-count":5,"title":["Performance of a Sepsis Prediction Model Across Different Sepsis Definitions"],"prefix":"10.1001","volume":"9","author":[{"given":"Sayon","family":"Dutta","sequence":"first","affiliation":[{"name":"Department of Emergency Medicine, Massachusetts General Hospital, Boston"},{"name":"Mass General Brigham Digital Health, Boston, Massachusetts"},{"name":"Harvard Medical School, Boston, Massachusetts"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Reid","family":"McMurry","sequence":"additional","affiliation":[{"name":"Department of Emergency Medicine, Boston Medical Center, Boston, Massachusetts"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael C.","family":"Tasi","sequence":"additional","affiliation":[{"name":"Department of Emergency Medicine, Massachusetts General Hospital, Boston"},{"name":"Harvard Medical School, Boston, Massachusetts"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lisette","family":"Dunham","sequence":"additional","affiliation":[{"name":"Mass General Brigham Digital Health, Boston, Massachusetts"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dustin S.","family":"McEvoy","sequence":"additional","affiliation":[{"name":"Mass General Brigham Digital Health, Boston, Massachusetts"},{"name":"Trinity Health, Grand Rapids, Michigan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Timothy","family":"Stump","sequence":"additional","affiliation":[{"name":"Mass General Brigham Digital Health, Boston, Massachusetts"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael","family":"Filbin","sequence":"additional","affiliation":[{"name":"Department of Emergency Medicine, Massachusetts General Hospital, Boston"},{"name":"Harvard Medical School, Boston, Massachusetts"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chanu","family":"Rhee","sequence":"additional","affiliation":[{"name":"Harvard Medical School, Boston, Massachusetts"},{"name":"Division of Infectious Diseases, Department of Medicine, Brigham and Women\u2019s Hospital, Boston, Massachusetts"},{"name":"Department of Population Medicine, Harvard Medical School\/Harvard Pilgrim Health Care Institute, Boston, Massachusetts"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"10","published-online":{"date-parts":[[2026,4,7]]},"reference":[{"issue":"13","key":"zoi260200r1","doi-asserted-by":"publisher","first-page":"1241","DOI":"10.1001\/jama.2017.13836","article-title":"Incidence and trends of sepsis in US hospitals using clinical vs claims data, 2009-2014.","volume":"318","author":"Rhee","year":"2017","journal-title":"JAMA"},{"issue":"10219","key":"zoi260200r2","doi-asserted-by":"publisher","first-page":"200","DOI":"10.1016\/S0140-6736(19)32989-7","article-title":"Global, regional, and national sepsis incidence and mortality, 1990-2017: analysis for the Global Burden of Disease Study.","volume":"395","author":"Rudd","year":"2020","journal-title":"Lancet"},{"issue":"3","key":"zoi260200r3","doi-asserted-by":"publisher","first-page":"276","DOI":"10.1097\/CCM.0000000000004224","article-title":"Sepsis among Medicare beneficiaries: 1. the burdens of sepsis, 2012-2018.","volume":"48","author":"Buchman","year":"2020","journal-title":"Crit Care Med"},{"issue":"19","key":"zoi260200r4","doi-asserted-by":"publisher","first-page":"1368","DOI":"10.1056\/NEJMoa010307","article-title":"Early goal-directed therapy in the treatment of severe sepsis and septic shock.","volume":"345","author":"Rivers","year":"2001","journal-title":"N Engl J Med"},{"issue":"8","key":"zoi260200r5","doi-asserted-by":"publisher","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":"zoi260200r6","doi-asserted-by":"publisher","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":"5","key":"zoi260200r7","doi-asserted-by":"publisher","first-page":"759","DOI":"10.1097\/CCM.0000000000002264","article-title":"Delays from first medical contact to antibiotic administration for sepsis.","volume":"45","author":"Seymour","year":"2017","journal-title":"Crit Care Med"},{"issue":"11","key":"zoi260200r8","doi-asserted-by":"publisher","first-page":"e1063","DOI":"10.1097\/CCM.0000000000005337","article-title":"Surviving Sepsis Campaign: international guidelines for management of sepsis and septic shock 2021.","volume":"49","author":"Evans","year":"2021","journal-title":"Crit Care Med"},{"issue":"18","key":"zoi260200r9","doi-asserted-by":"publisher","first-page":"1683","DOI":"10.1056\/NEJMoa1401602","article-title":"A randomized trial of protocol-based care for early septic shock.","volume":"370","author":"Yealy","year":"2014","journal-title":"N Engl J Med"},{"key":"zoi260200r10","doi-asserted-by":"publisher","DOI":"10.1056\/AIoa2300032","article-title":"Evaluation of sepsis prediction models before onset of treatment.","author":"Kamran","year":"2024","journal-title":"NEJM AI"},{"issue":"1","key":"zoi260200r11","doi-asserted-by":"publisher","DOI":"10.1136\/bmjhci-2019-100109","article-title":"Effect of a sepsis prediction algorithm on patient mortality, length of stay and readmission: a prospective multicentre clinical outcomes evaluation of real-world patient data from US hospitals.","volume":"27","author":"Burdick","year":"2020","journal-title":"BMJ Health Care Inform"},{"issue":"8","key":"zoi260200r12","doi-asserted-by":"publisher","first-page":"1065","DOI":"10.1001\/jamainternmed.2021.2626","article-title":"External validation of a widely implemented proprietary sepsis prediction model in hospitalized patients.","volume":"181","author":"Wong","year":"2021","journal-title":"JAMA Intern Med"},{"issue":"11","key":"zoi260200r13","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2021.35286","article-title":"Quantification of sepsis model alerts in 24 US hospitals before and during the COVID-19 pandemic.","volume":"4","author":"Wong","year":"2021","journal-title":"JAMA Netw Open"},{"issue":"4","key":"zoi260200r14","doi-asserted-by":"publisher","DOI":"10.1093\/jamiaopen\/ooae133","article-title":"External validation of the Epic sepsis predictive model in 2 county emergency departments.","volume":"7","author":"Ostermayer","year":"2024","journal-title":"JAMIA Open"},{"issue":"5","key":"zoi260200r15","doi-asserted-by":"publisher","first-page":"584","DOI":"10.1016\/j.jemermed.2023.02.025","article-title":"Clinical impact of a sepsis alert system plus electronic sepsis navigator using the epic sepsis prediction model in the emergency department.","volume":"64","author":"Schertz","year":"2023","journal-title":"J Emerg Med"},{"key":"zoi260200r16","doi-asserted-by":"publisher","first-page":"147","DOI":"10.1016\/j.ajem.2025.07.056","article-title":"External validation of a widely available, localizable sepsis early detection model in the emergency department setting.","volume":"97","author":"Currey","year":"2025","journal-title":"Am J Emerg Med"},{"issue":"8","key":"zoi260200r17","doi-asserted-by":"publisher","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":"JAMA"},{"issue":"3","key":"zoi260200r19","doi-asserted-by":"publisher","first-page":"e122","DOI":"10.1097\/CCM.0000000000001724","article-title":"Application of a framework to assess the usefulness of alternative sepsis criteria.","volume":"44","author":"Seymour","year":"2016","journal-title":"Crit Care Med"},{"key":"zoi260200r20","doi-asserted-by":"publisher","DOI":"10.1056\/AIoa2400867","article-title":"FDA-authorized AI\/ML tool for sepsis prediction: development and validation.","author":"Bhargava","year":"2024","journal-title":"NEJM AI"},{"issue":"2","key":"zoi260200r22","doi-asserted-by":"publisher","first-page":"163","DOI":"10.1017\/ice.2015.264","article-title":"Objective sepsis surveillance using electronic clinical data.","volume":"37","author":"Rhee","year":"2016","journal-title":"Infect Control Hosp Epidemiol"},{"issue":"19","key":"zoi260200r23","doi-asserted-by":"publisher","first-page":"1724","DOI":"10.1001\/jama.2025.2526","article-title":"Concordance of 30-day mortality and in-hospital mortality or hospice discharge after sepsis.","volume":"333","author":"Prescott","year":"2025","journal-title":"JAMA"},{"issue":"9","key":"zoi260200r24","doi-asserted-by":"publisher","first-page":"880","DOI":"10.1017\/ice.2025.10218","article-title":"Evaluating potential modifications to the Centers for Disease Control and Prevention\u2019s adult sepsis event definition: impact on sepsis incidence, outcomes, and clinical validity.","volume":"46","author":"Millham","year":"2025","journal-title":"Infect Control Hosp Epidemiol"},{"key":"zoi260200r25","doi-asserted-by":"publisher","DOI":"10.1136\/bmj-2023-078378","article-title":"TRIPOD+AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods.","volume":"385","author":"Collins","year":"2024","journal-title":"BMJ"},{"issue":"19","key":"zoi260200r26","doi-asserted-by":"publisher","first-page":"4230","DOI":"10.1002\/sim.9025","article-title":"Minimum sample size for external validation of a clinical prediction model with a binary outcome.","volume":"40","author":"Riley","year":"2021","journal-title":"Stat Med"},{"key":"zoi260200r27","doi-asserted-by":"publisher","DOI":"10.1136\/bmj-2021-068576","article-title":"Early identification of patients admitted to hospital for COVID-19 at risk of clinical deterioration: model development and multisite external validation study.","volume":"376","author":"Kamran","year":"2022","journal-title":"BMJ"},{"issue":"6","key":"zoi260200r28","doi-asserted-by":"publisher","first-page":"738","DOI":"10.1016\/j.annemergmed.2022.11.012","article-title":"Prospective external validation of a commercial model predicting the likelihood of inpatient admission from the emergency department.","volume":"81","author":"Dadabhoy","year":"2023","journal-title":"Ann Emerg Med"},{"key":"zoi260200r29","doi-asserted-by":"publisher","DOI":"10.1056\/AIoa2300099","article-title":"External validation of a commercial acute kidney injury predictive model.","author":"Dutta","year":"2024","journal-title":"NEJM AI"},{"issue":"12","key":"zoi260200r30","doi-asserted-by":"publisher","DOI":"10.1016\/j.landig.2025.100916","article-title":"Evaluation of performance measures in predictive artificial intelligence models to support medical decisions: overview and guidance.","volume":"7","author":"Calster","year":"2025","journal-title":"Lancet Digit Health"},{"issue":"43","key":"zoi260200r31","doi-asserted-by":"publisher","first-page":"1686","DOI":"10.21105\/joss.01686","article-title":"Welcome to the Tidyverse.","volume":"4","author":"Wickham","year":"2019","journal-title":"J Open Source Softw"},{"issue":"7","key":"zoi260200r32","doi-asserted-by":"publisher","first-page":"e673","DOI":"10.1097\/CCM.0000000000004968","article-title":"Determining the electronic signature of infection in electronic health record data.","volume":"49","author":"Churpek","year":"2021","journal-title":"Crit Care Med"},{"issue":"4","key":"zoi260200r33","doi-asserted-by":"publisher","first-page":"305","DOI":"10.1136\/bmjqs-2018-008331","article-title":"Using objective clinical data to track progress on preventing and treating sepsis: CDC\u2019s new \u2018adult sepsis event\u2019 surveillance strategy.","volume":"28","author":"Rhee","year":"2019","journal-title":"BMJ Qual Saf"},{"key":"zoi260200r34","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2021.106288","article-title":"The importance of being external. methodological insights for the external validation of machine learning models in medicine.","volume":"208","author":"Cabitza","year":"2021","journal-title":"Comput Methods Programs Biomed"},{"issue":"7","key":"zoi260200r35","doi-asserted-by":"publisher","DOI":"10.1097\/CCE.0000000000000941","article-title":"Epic sepsis model inpatient predictive analytic tool: a validation study.","volume":"5","author":"Cull","year":"2023","journal-title":"Crit Care Explor"},{"issue":"1","key":"zoi260200r36","doi-asserted-by":"publisher","first-page":"11760","DOI":"10.1038\/s41598-023-38858-4","article-title":"Predicting sepsis onset using a machine learned causal probabilistic network algorithm based on electronic health records data.","volume":"13","author":"Valik","year":"2023","journal-title":"Sci Rep"},{"key":"zoi260200r37","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2021.102036","article-title":"DeepAISE - an interpretable and recurrent neural survival model for early prediction of sepsis.","volume":"113","author":"Shashikumar","year":"2021","journal-title":"Artif Intell Med"},{"issue":"3","key":"zoi260200r38","doi-asserted-by":"publisher","first-page":"383","DOI":"10.1007\/s00134-019-05872-y","article-title":"Machine learning for the prediction of sepsis: a systematic review and meta-analysis of diagnostic test accuracy.","volume":"46","author":"Fleuren","year":"2020","journal-title":"Intensive Care Med"},{"key":"zoi260200r39","doi-asserted-by":"publisher","DOI":"10.3389\/fmed.2024.1491358","article-title":"Early detection of sepsis using machine learning algorithms: a systematic review and network meta-analysis.","volume":"11","author":"Yadgarov","year":"2024","journal-title":"Front Med (Lausanne)"},{"issue":"1","key":"zoi260200r40","doi-asserted-by":"publisher","first-page":"283","DOI":"10.1186\/s12911-023-02383-1","article-title":"Machine learning for the prediction of sepsis-related death: a systematic review and meta-analysis.","volume":"23","author":"Zhang","year":"2023","journal-title":"BMC Med Inform Decis Mak"},{"key":"zoi260200r41","doi-asserted-by":"publisher","first-page":"S89","DOI":"10.21037\/jtd.2019.12.51","article-title":"Sepsis trends: increasing incidence and decreasing mortality, or changing denominator?","volume":"12","author":"Rhee","year":"2020","journal-title":"J Thorac Dis"},{"key":"zoi260200r42","first-page":"109","article-title":"A prospective comparison of large language models for early prediction of sepsis.","volume":"30","author":"Shashikumar","year":"2025","journal-title":"Pac Symp Biocomput"},{"key":"zoi260200r43","doi-asserted-by":"publisher","DOI":"10.2196\/49784","article-title":"Sepsis prediction at emergency department triage using natural language processing: retrospective cohort study.","volume":"3","author":"Brann","year":"2024","journal-title":"JMIR AI"},{"key":"zoi260200r18","unstructured":"Cognitive computing model brief: Early Detection of Sepsis (Version 2). Accessed January 15, 2026. https:\/\/galaxy.epic.com\/?#Browse\/page=1!68!50!100170819&from=Galaxy-Redirect"},{"key":"zoi260200r21","unstructured":"Hospital toolkit for adult sepsis surveillance. Centers for Disease Control and Prevention. May 1, 2018. Accessed May 14, 2025. https:\/\/stacks.cdc.gov\/view\/cdc\/132387"}],"container-title":["JAMA Network Open"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/jamanetwork.com\/journals\/jamanetworkopen\/articlepdf\/2847396\/dutta_2026_oi_260200_1774906631.3945.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T15:00:38Z","timestamp":1775574038000},"score":1,"resource":{"primary":{"URL":"https:\/\/jamanetwork.com\/journals\/jamanetworkopen\/fullarticle\/2847396"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,7]]},"references-count":43,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2026,4,1]]}},"URL":"https:\/\/doi.org\/10.1001\/jamanetworkopen.2026.5599","relation":{},"ISSN":["2574-3805"],"issn-type":[{"value":"2574-3805","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,7]]}}}