{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,30]],"date-time":"2026-10-30T12:55:05Z","timestamp":1793364905985,"version":"4.5.0"},"reference-count":40,"publisher":"BMJ","issue":"1","license":[{"start":{"date-parts":[[2025,5,14]],"date-time":"2025-05-14T00:00:00Z","timestamp":1747180800000},"content-version":"unspecified","delay-in-days":13,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000272","name":"NIHR","doi-asserted-by":"crossref","award":["NIHR203295"],"award-info":[{"award-number":["NIHR203295"]}],"id":[{"id":"10.13039\/501100000272","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["bmjpo"],"accepted":{"date-parts":[[2025,5,4]]},"published-print":{"date-parts":[[2025,5]]},"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Early identification of children at risk of sepsis in emergency departments (EDs) is crucial for timely treatment and improved outcomes. Existing risk scores and criteria for paediatric sepsis are not well-suited for early diagnosis in ED.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>To develop and evaluate machine learning models to predict clinical interventions and patient outcomes in children with suspected sepsis.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Design<\/jats:title>\n                    <jats:p>Retrospective observational study.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Setting<\/jats:title>\n                    <jats:p>ED of a tertiary care hospital, UK.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Patients<\/jats:title>\n                    <jats:p>Electronic health records of children &lt;16 years of age attending between 1 January 2018 and 31 December 2019. Patients presenting with minor injuries were excluded.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Prediction models were developed and validated, using 15 key predictors from triage and post-blood test data. XGBoost, the best-performing machine learning model, integrated these predictors with triage note information extracted via Natural Language Processing.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Main outcomes<\/jats:title>\n                    <jats:p>(1) Administration of antibiotics; (2) critical care: antibiotics with fluid resuscitation above 20 mL\/kg or non-elective mechanical ventilation; (3) serious infection: hospital admission for antibiotics &gt;48\u2009hours.<\/jats:p>\n                    <jats:p>Model performance was evaluated using area under the receiver operating characteristic curve (AUC), likelihood ratios and positive and negative predictive values.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Triage model: predicted antibiotics at triage (n=35\u2009795; 3.2% with outcome) with an AUC of 0.80 (95% CI 0.76 to 0.84).<\/jats:p>\n                    <jats:p>Antibiotic model: predicted antibiotics post-blood tests (n=4700; 24.2%) with an AUC of 0.78 (95% CI 0.73 to 0.81).<\/jats:p>\n                    <jats:p>Critical care model: predicted critical care (n=4700; 3.3%) with an AUC of 0.78 (95% CI 0.72 to 084).<\/jats:p>\n                    <jats:p>Serious infection model: predicted serious infection (n=4700; 9.4%) with an AUC of 0.76 (95% CI 0.71 to 0.81).<\/jats:p>\n                    <jats:p>Key predictors included triage category, temperature, capillary refill time and C reactive protein.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Machine learning models demonstrated good accuracy in predicting antibiotic use following triage and moderate accuracy for critical care and serious infection. Further development and external validation are ongoing.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1136\/bmjpo-2024-003273","type":"journal-article","created":{"date-parts":[[2025,5,15]],"date-time":"2025-05-15T03:45:28Z","timestamp":1747280728000},"page":"e003273","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":9,"title":["Predicting sepsis treatment decisions in the paediatric emergency department using machine learning: the AiSEPTRON study"],"prefix":"10.1136","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0201-672X","authenticated-orcid":false,"given":"Sylvester","family":"Gomes","sequence":"first","affiliation":[{"name":"Evelina London Children\u2019s Hospital, London, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Harpreet","family":"Dhanoa","sequence":"additional","affiliation":[{"name":"Clinical Analytics, Guy's and St Thomas\u2019 NHS Foundation Trust, London, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Phil","family":"Assheton","sequence":"additional","affiliation":[{"name":"Clinical Analytics, Guy's and St Thomas\u2019 NHS Foundation Trust, London, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ewan","family":"Carr","sequence":"additional","affiliation":[{"name":"Department of Biostatistics & Health Informatics, King's College London, London, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9334-5144","authenticated-orcid":false,"given":"Damian","family":"Roland","sequence":"additional","affiliation":[{"name":"Health Sciences, University of Leicester, Leicester, UK"},{"name":"Paediatric Emergency Medicine Leicester Academic (PEMLA) Group, University Hospitals of Leicester NHS Trust, Leicester, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Akash","family":"Deep","sequence":"additional","affiliation":[{"name":"Paediatric Intensive Care, King\u2019s College Hospital, London, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"239","published-online":{"date-parts":[[2025,5,14]]},"reference":[{"key":"2026010702013209000_9.1.e003273.1","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(19)32989-7"},{"key":"2026010702013209000_9.1.e003273.2","doi-asserted-by":"publisher","DOI":"10.1097\/PCC.0000000000002198"},{"key":"2026010702013209000_9.1.e003273.3","doi-asserted-by":"crossref","first-page":"2262","DOI":"10.1111\/apa.16536","article-title":"Identification of sepsis in paediatric emergency departments: A scoping review","volume":"111","author":"Oruganti","year":"2022","journal-title":"Acta Paediatr"},{"key":"2026010702013209000_9.1.e003273.4","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2016.0287"},{"key":"2026010702013209000_9.1.e003273.5","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2024.0196"},{"key":"2026010702013209000_9.1.e003273.6","doi-asserted-by":"publisher","DOI":"10.1097\/01.PCC.0000149131.72248.E6"},{"key":"2026010702013209000_9.1.e003273.7","doi-asserted-by":"crossref","first-page":"650","DOI":"10.1001\/jama.2023.27988","article-title":"Transitioning From SIRS to Phoenix With the Updated Pediatric Sepsis Criteria-The Difficult Task of Simplifying the Complex","volume":"331","author":"Jabornisky","year":"2024","journal-title":"JAMA"},{"key":"2026010702013209000_9.1.e003273.8","doi-asserted-by":"crossref","first-page":"2135","DOI":"10.1001\/jama.2024.8447","article-title":"Society of Critical Care Medicine Pediatric Sepsis Definitions Task Force. Pediatric Phoenix Sepsis Score Validation Challenges in Low-Resource Settings and in the Emergency Department\u2014Reply","volume":"331","author":"Watson","year":"2024","journal-title":"JAMA"},{"key":"2026010702013209000_9.1.e003273.9","doi-asserted-by":"crossref","unstructured":"Venkatesan P . Updated criteria for paediatric sepsis and septic shock. Lancet Infect Dis 2024;24. doi:10.1016\/S1473-3099(24)00168-3","DOI":"10.1016\/S1473-3099(24)00168-3"},{"key":"2026010702013209000_9.1.e003273.10","first-page":"1129","article-title":"Prediction of Resuscitation for Pediatric Sepsis from Data Available at Triage","volume":"2021","author":"Stella","year":"2021","journal-title":"AMIA Annu Symp Proc"},{"key":"2026010702013209000_9.1.e003273.11","doi-asserted-by":"publisher","DOI":"10.1016\/j.ienj.2021.101109"},{"key":"2026010702013209000_9.1.e003273.12","doi-asserted-by":"crossref","DOI":"10.1001\/jamanetworkopen.2018.6937","article-title":"Machine Learning-Based Prediction of Clinical Outcomes for Children During Emergency Department Triage","volume":"2","author":"Goto","year":"2019","journal-title":"JAMA Netw Open"},{"key":"2026010702013209000_9.1.e003273.13","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0264184","article-title":"Machine learning-based prediction of critical illness in children visiting the emergency department","volume":"17","author":"Hwang","year":"2022","journal-title":"PLoS ONE"},{"key":"2026010702013209000_9.1.e003273.14","unstructured":"AiSEPTRON . Designing a paediatric sepsis prediction tool using machine learning. Available: https:\/\/www.aiseptron.co.uk [Accessed 12 Aug 2024]."},{"key":"2026010702013209000_9.1.e003273.15","doi-asserted-by":"crossref","DOI":"10.1542\/peds.2020-1434","article-title":"Development of a Quality Improvement Learning Collaborative to Improve Pediatric Sepsis Outcomes","volume":"147","author":"Larsen","year":"2021","journal-title":"Pediatrics"},{"key":"2026010702013209000_9.1.e003273.16","doi-asserted-by":"publisher","DOI":"10.1136\/fn.87.1.F25"},{"key":"2026010702013209000_9.1.e003273.17","unstructured":"Ensor J , Martin E , Riley R . pmsampsize: sample size for development of a prediction model. 2023. Available: https:\/\/CRAN.R-project.org\/package=pmsampsize [Accessed 09 Dec 2024]."},{"key":"2026010702013209000_9.1.e003273.18","doi-asserted-by":"publisher","DOI":"10.1136\/emermed-2019-208746"},{"key":"2026010702013209000_9.1.e003273.19","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0244810","article-title":"PERFORM consortium: Personalised Risk assessment in febrile children to optimise Real-life Management across the European Union. Variation in hospital admission in febrile children evaluated at the Emergency Department (ED) in Europe: PERFORM, a multicentre prospective observational study","volume":"16","author":"Borensztajn","year":"2021","journal-title":"PLoS ONE"},{"key":"2026010702013209000_9.1.e003273.20","doi-asserted-by":"publisher","DOI":"10.1016\/j.cpc.2010.04.018"},{"key":"2026010702013209000_9.1.e003273.21","doi-asserted-by":"crossref","unstructured":"van\u00a0Buuren S , Groothuis-Oudshoorn K . mice: Multivariate Imputation by Chained Equations in R. J Stat Softw 2011. doi:10.18637\/jss.v045.i03","DOI":"10.18637\/jss.v045.i03"},{"key":"2026010702013209000_9.1.e003273.22","doi-asserted-by":"crossref","first-page":"160","DOI":"10.1093\/jamiaopen\/ooaa022","article-title":"Generating contextual embeddings for emergency department chief complaints","volume":"3","author":"Chang","year":"2020","journal-title":"JAMIA Open"},{"key":"2026010702013209000_9.1.e003273.23","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1111\/j.2517-6161.1958.tb00292.x","article-title":"The Regression Analysis of Binary Sequences","volume":"20","author":"Cox","year":"1958","journal-title":"J R Stat Soc Series B Stat Methodol"},{"key":"2026010702013209000_9.1.e003273.24","doi-asserted-by":"crossref","unstructured":"Ho TK . Random decision forests. Proceedings of 3rd International Conference on Document Analysis and Recognition; 1995 doi:10.1109\/ICDAR.1995.598994","DOI":"10.1109\/ICDAR.1995.598994"},{"key":"2026010702013209000_9.1.e003273.25","doi-asserted-by":"crossref","unstructured":"Chen T , Guestrin C . XGBoost: a scalable tree boosting system. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining; 2016 doi:10.1145\/2939672.2939785","DOI":"10.1145\/2939672.2939785"},{"key":"2026010702013209000_9.1.e003273.26","doi-asserted-by":"crossref","unstructured":"Bishop CM , Bishop H . Deep learning: foundations and concepts. Springer International Publishing, 2023.","DOI":"10.1007\/978-3-031-45468-4"},{"key":"2026010702013209000_9.1.e003273.27","doi-asserted-by":"publisher","DOI":"10.5662\/wjm.v13.i5.373"},{"key":"2026010702013209000_9.1.e003273.28","doi-asserted-by":"publisher","DOI":"10.1111\/acem.12814"},{"key":"2026010702013209000_9.1.e003273.29","doi-asserted-by":"crossref","DOI":"10.1186\/1471-2105-12-77","article-title":"pROC: an open-source package for R and S+ to analyze and compare ROC curves","volume":"12","author":"Robin","year":"2011","journal-title":"BMC Bioinformatics"},{"key":"2026010702013209000_9.1.e003273.30","unstructured":"Canty A , Ripley B . boot: Bootstrap R (S-Plus) functions. R package version 1.3-28. 2021."},{"key":"2026010702013209000_9.1.e003273.31","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2024.0179"},{"key":"2026010702013209000_9.1.e003273.32","doi-asserted-by":"crossref","first-page":"e338","DOI":"10.1016\/S2589-7500(23)00070-5","article-title":"Clinical ground truth in machine learning for early sepsis diagnosis","volume":"5","author":"Lindner","year":"2023","journal-title":"Lancet Digit Health"},{"key":"2026010702013209000_9.1.e003273.33","doi-asserted-by":"crossref","DOI":"10.1016\/j.eclinm.2023.102124","article-title":"Predicting sepsis using deep learning across international sites: a retrospective development and validation study","volume":"62","author":"Moor","year":"2023","journal-title":"EClinicalMedicine"},{"key":"2026010702013209000_9.1.e003273.34","unstructured":"National Institute for Health and Care Excellence (NICE) . Sepsis: recognition, diagnosis and early management. NICE guideline [NG51]. 2016."},{"key":"2026010702013209000_9.1.e003273.35","doi-asserted-by":"crossref","DOI":"10.3389\/fped.2020.548154","article-title":"Management of Children With Fever at Risk for Pediatric Sepsis: A Prospective Study in Pediatric Emergency Care","volume":"8","author":"Nijman","year":"2020","journal-title":"Front Pediatr"},{"key":"2026010702013209000_9.1.e003273.36","doi-asserted-by":"crossref","DOI":"10.1136\/bmjopen-2022-061431","article-title":"Validation of a paediatric sepsis screening tool to identify children with sepsis in the emergency department: a statewide prospective cohort study in Queensland, Australia","volume":"13","author":"Gilholm","year":"2023","journal-title":"BMJ Open"},{"key":"2026010702013209000_9.1.e003273.37","doi-asserted-by":"crossref","DOI":"10.1016\/j.lanepe.2021.100173","article-title":"A NICE combination for predicting hospitalisation at the Emergency Department: a European multicentre observational study of febrile children","volume":"8","author":"Borensztajn","year":"2021","journal-title":"Lancet Reg Health Eur"},{"key":"2026010702013209000_9.1.e003273.38","doi-asserted-by":"crossref","DOI":"10.1001\/jamanetworkopen.2020.0265","article-title":"Evaluation of Combined Artificial Intelligence and Radiologist Assessment to Interpret Screening Mammograms","volume":"3","author":"Schaffter","year":"2020","journal-title":"JAMA Netw Open"},{"key":"2026010702013209000_9.1.e003273.39","doi-asserted-by":"crossref","first-page":"243","DOI":"10.1007\/s11908-023-00818-4","article-title":"The Opportunities and Challenges for Artificial Intelligence to Improve Sepsis Outcomes in the Paediatric Intensive Care Unit","volume":"25","author":"Aslan","year":"2023","journal-title":"Curr Infect Dis Rep"},{"key":"2026010702013209000_9.1.e003273.40","doi-asserted-by":"crossref","first-page":"e651","DOI":"10.1016\/S2589-7500(24)00141-9","article-title":"Digital solutions in paediatric sepsis: current state, challenges, and opportunities to improve care around the world","volume":"6","author":"Sanchez-Pinto","year":"2024","journal-title":"Lancet Digit Health"}],"container-title":["BMJ Paediatrics Open"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/bmjpo-2024-003273","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,7]],"date-time":"2026-01-07T10:02:51Z","timestamp":1767780171000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmjpaedsopen.bmj.com\/lookup\/doi\/10.1136\/bmjpo-2024-003273"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5]]},"references-count":40,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,5,14]]},"published-print":{"date-parts":[[2025,5]]}},"alternative-id":["10.1136\/bmjpo-2024-003273"],"URL":"https:\/\/doi.org\/10.1136\/bmjpo-2024-003273","relation":{},"ISSN":["2399-9772"],"issn-type":[{"value":"2399-9772","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5]]}}}