{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T03:54:08Z","timestamp":1788839648061,"version":"build-2803163510"},"reference-count":40,"publisher":"American Academy of Pediatrics (AAP)","issue":"3","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,9,1]]},"abstract":"<jats:sec><jats:title>BACKGROUND:<\/jats:title><jats:p>Recent decision rules for the management of febrile infants support the identification of infants at higher risk of serious bacterial infections (SBIs) without the performance of routine lumbar puncture. We derive and validate a model to identify febrile infants \u226460 days of age at low risk for SBIs using supervised machine learning approaches.<\/jats:p><\/jats:sec><jats:sec><jats:title>METHODS:<\/jats:title><jats:p>We conducted a secondary analysis of a multicenter prospective study performed between December 2008 and May 2013 of febrile infants. Our outcome was SBI, (culture-positive urinary tract infection, bacteremia, and\/or bacterial meningitis). We developed and validated 4 supervised learning models: logistic regression, random forest, support vector machine, and a single-hidden layer neural network.<\/jats:p><\/jats:sec><jats:sec><jats:title>RESULTS:<\/jats:title><jats:p>A total of 1470 patients were included (1014 &amp;gt;28 days old). One hundred thirty-eight (9.3%) had SBIs (122 urinary tract infections, 20 bacteremia, and 8 meningitis; 11 with concurrent SBIs). Using 4 features (urinalysis, white blood cell count, absolute neutrophil count, and procalcitonin), we demonstrated with the random forest model the highest specificity (74.9, 95% confidence interval: 71.5%\u201378.2%) with a sensitivity of 98.6% (95% confidence interval: 92.2%\u2013100.0%) in the validation cohort. One patient with bacteremia was misclassified. Among 1240 patients who received a lumbar puncture, this model could have prevented 849 (68.5%) such procedures.<\/jats:p><\/jats:sec><jats:sec><jats:title>CONCLUSIONS:<\/jats:title><jats:p>We derived and internally validated a supervised learning model for the risk-stratification of febrile infants. Although computationally complex, lacking parameter cutoffs, and in need of external validation, this strategy may allow for reductions in unnecessary procedures, hospitalizations, and antibiotics while maintaining excellent sensitivity.<\/jats:p><\/jats:sec>","DOI":"10.1542\/peds.2019-4096","type":"journal-article","created":{"date-parts":[[2020,8,27]],"date-time":"2020-08-27T12:25:17Z","timestamp":1598531117000},"source":"Crossref","is-referenced-by-count":75,"title":["Machine Learning To Predict Serious Bacterial Infections in Young Febrile Infants"],"prefix":"10.1542","volume":"146","author":[{"given":"Sriram","family":"Ramgopal","sequence":"first","affiliation":[{"name":"Division of Emergency Medicine, Department of Pediatrics, Ann & Robert H. Lurie Children\u2019s Hospital of Chicago and Feinberg School of Medicine, Northwestern University, Chicago, Illinois;"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christopher M.","family":"Horvat","sequence":"additional","affiliation":[{"name":"Division of Pediatric Critical Care Medicine, Department of Critical Care Medicine, University of Pittsburgh School of Medicine, Pittsburgh, Pennsylvania;"},{"name":"Division of Health Informatics, Department of Pediatrics, UPMC Children\u2019s Hospital of Pittsburgh, Pittsburgh, Pennsylvania; and"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Naveena","family":"Yanamala","sequence":"additional","affiliation":[{"name":"Institute for Software Research, Carnegie Mellon University, Pittsburgh, Pennsylvania"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Elizabeth R.","family":"Alpern","sequence":"additional","affiliation":[{"name":"Division of Emergency Medicine, Department of Pediatrics, Ann & Robert H. Lurie Children\u2019s Hospital of Chicago and Feinberg School of Medicine, Northwestern University, Chicago, Illinois;"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"417","published-online":{"date-parts":[[2020,9,1]]},"reference":[{"issue":"4","key":"2021120912573271200_B1","doi-asserted-by":"crossref","first-page":"866","DOI":"10.1542\/peds.108.4.866","article-title":"Enhanced urinalysis improves identification of febrile infants ages 60 days and younger at low risk for serious bacterial illness","volume":"108","author":"Herr","year":"2001","journal-title":"Pediatrics"},{"issue":"20","key":"2021120912573271200_B2","doi-asserted-by":"crossref","first-page":"1437","DOI":"10.1056\/NEJM199311113292001","article-title":"Outpatient management without antibiotics of fever in selected infants","volume":"329","author":"Baker","year":"1993","journal-title":"N Engl J Med"},{"issue":"3","key":"2021120912573271200_B3","doi-asserted-by":"crossref","first-page":"390","DOI":"10.1542\/peds.94.3.390","article-title":"Febrile infants at low risk for serious bacterial infection--an appraisal of the Rochester criteria and implications for management","volume":"94","author":"Jaskiewicz","year":"1994","journal-title":"Pediatrics"},{"issue":"1","key":"2021120912573271200_B4","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1016\/S0022-3476(05)80591-8","article-title":"Outpatient treatment of febrile infants 28 to 89 days of age with intramuscular administration of ceftriaxone","volume":"120","author":"Baskin","year":"1992","journal-title":"J Pediatr"},{"issue":"6","key":"2021120912573271200_B5","doi-asserted-by":"crossref","first-page":"855","DOI":"10.1016\/S0022-3476(85)80175-X","article-title":"Identification of infants unlikely to have serious bacterial infection although hospitalized for suspected sepsis","volume":"107","author":"Dagan","year":"1985","journal-title":"J Pediatr"},{"issue":"1","key":"2021120912573271200_B6","doi-asserted-by":"crossref","first-page":"e20183604","DOI":"10.1542\/peds.2018-3604","article-title":"A prediction model to identify febrile infants \u226460 days at low risk of invasive bacterial infection","volume":"144","author":"Aronson","year":"2019","journal-title":"Pediatrics"},{"issue":"4","key":"2021120912573271200_B7","doi-asserted-by":"crossref","first-page":"342","DOI":"10.1001\/jamapediatrics.2018.5501","article-title":"A clinical prediction rule to identify febrile infants 60 days and younger at low risk for serious bacterial infections","volume":"173","author":"Kuppermann","year":"2019","journal-title":"JAMA Pediatr"},{"issue":"2","key":"2021120912573271200_B8","doi-asserted-by":"crossref","first-page":"e20154381","DOI":"10.1542\/peds.2015-4381","article-title":"Validation of the \u201cStep-by-Step\u201d approach in the management of young febrile infants","volume":"138","author":"Gomez","year":"2016","journal-title":"Pediatrics"},{"issue":"1","key":"2021120912573271200_B9","doi-asserted-by":"crossref","first-page":"62","DOI":"10.1001\/jamapediatrics.2015.3210","article-title":"Use of procalcitonin assays to predict serious bacterial infection in young febrile infants","volume":"170","author":"Milcent","year":"2016","journal-title":"JAMA Pediatr"},{"issue":"2","key":"2021120912573271200_B12","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1111\/acem.12316","article-title":"Procalcitonin as a marker of serious bacterial infections in febrile children younger than 3 years old","volume":"21","author":"Mahajan","year":"2014","journal-title":"Acad Emerg Med"},{"issue":"9","key":"2021120912573271200_B10","doi-asserted-by":"crossref","first-page":"884","DOI":"10.1136\/archdischild-2019-317143","article-title":"Immature neutrophils in young febrile infants","volume":"104","author":"Ramgopal","year":"2019","journal-title":"Arch Dis Child"},{"issue":"7","key":"2021120912573271200_B13","first-page":"665","article-title":"Invasive bacterial infections in young afebrile infants with a history of fever","volume":"103","author":"Mintegi","year":"2018","journal-title":"Arch Dis Child"},{"issue":"6","key":"2021120912573271200_B14","doi-asserted-by":"crossref","first-page":"595","DOI":"10.1097\/INF.0000000000000225","article-title":"The changing epidemiology of serious bacterial infections in young infants","volume":"33","author":"Greenhow","year":"2014","journal-title":"Pediatr Infect Dis J"},{"issue":"8","key":"2021120912573271200_B16","doi-asserted-by":"crossref","first-page":"717","DOI":"10.1136\/archdischild-2013-305736","article-title":"Parental perspectives on evaluation and management of fever in young infants: an interview study","volume":"99","author":"De","year":"2014","journal-title":"Arch Dis Child"},{"issue":"4","key":"2021120912573271200_B17","doi-asserted-by":"crossref","first-page":"667","DOI":"10.1542\/peds.2014-1382","article-title":"Variation in care of the febrile young infant &lt;90 days in US pediatric emergency departments","volume":"134","author":"Aronson","year":"2014","journal-title":"Pediatrics"},{"key":"2021120912573271200_B18","first-page":"3","volume-title":"Supervised and Unsupervised Learning for Data Science. Unsupervised and Semi-Supervised Learning","author":"Alloghani","year":"2019"},{"issue":"e2","key":"2021120912573271200_B19","doi-asserted-by":"crossref","first-page":"e212","DOI":"10.1136\/amiajnl-2013-001962","article-title":"Developing and evaluating an automated appendicitis risk stratification algorithm for pediatric patients in the emergency department","volume":"20","author":"Deleger","year":"2013","journal-title":"J Am Med Inform Assoc"},{"issue":"1","key":"2021120912573271200_B20","doi-asserted-by":"crossref","first-page":"e186937","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"},{"issue":"7","key":"2021120912573271200_B21","doi-asserted-by":"crossref","first-page":"648","DOI":"10.1001\/jamapediatrics.2019.1068","article-title":"Comparison of machine learning optimal classification trees with the pediatric emergency care applied research network head trauma decision rules","volume":"173","author":"Bertsimas","year":"2019","journal-title":"JAMA Pediatr"},{"issue":"9696","key":"2021120912573271200_B22","doi-asserted-by":"crossref","first-page":"1160","DOI":"10.1016\/S0140-6736(09)61558-0","article-title":"Identification of children at very low risk of clinically-important brain injuries after head trauma: a prospective cohort study","volume":"374","author":"Kuppermann","year":"2009","journal-title":"Lancet"},{"key":"2021120912573271200_B23","unstructured":"PECARN . Study datasets. Available at: http:\/\/www.pecarn.org\/studyDatasets\/StudyDetails?studyID=20. Accessed November 5, 2017"},{"issue":"1","key":"2021120912573271200_B24","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1097\/PEC.0000000000000324","article-title":"RNA transcriptional biosignature analysis for identifying febrile infants with serious bacterial infections in the emergency department: a feasibility study","volume":"31","author":"Mahajan","year":"2015","journal-title":"Pediatr Emerg Care"},{"issue":"4","key":"2021120912573271200_B25","doi-asserted-by":"crossref","first-page":"701","DOI":"10.1542\/peds.2007-3503","article-title":"Procalcitonin in young febrile infants for the detection of serious bacterial infections","volume":"122","author":"Maniaci","year":"2008","journal-title":"Pediatrics"},{"issue":"5","key":"2021120912573271200_B26","doi-asserted-by":"crossref","first-page":"815","DOI":"10.1542\/peds.2011-3575","article-title":"Diagnostic value of procalcitonin in well-appearing young febrile infants","volume":"130","author":"Gomez","year":"2012","journal-title":"Pediatrics"},{"key":"2021120912573271200_B27","unstructured":"Mahajan\u2008P, Ramilo\u2008O, Kuppermann\u2008N. Application of transcriptional signatures for diagnosis of febrile infants within the pediatric emergency care applied research network (PECARN): protocol number 022. 2012. Available at: http:\/\/pecarn.org\/studyDatasets\/documents\/Biosignatures_Protocol_v2.3_9.24.2012.pdf. Accessed September 13, 2018"},{"issue":"3","key":"2021120912573271200_B28","doi-asserted-by":"crossref","first-page":"453","DOI":"10.1093\/biomet\/58.3.453","article-title":"The biplot graphic display of matrices with application to principal component analysis","volume":"58","author":"Gabriel","year":"1971","journal-title":"Biometrika"},{"key":"2021120912573271200_B29","volume-title":"Machine Learning with R","author":"Lantz","year":"2019","edition":"3rd ed"},{"key":"2021120912573271200_B30","article-title":"Multiple imputation with large proportions of missing data: how much is too much?","author":"Lee"},{"issue":"9","key":"2021120912573271200_B31","doi-asserted-by":"crossref","first-page":"1489","DOI":"10.1513\/AnnalsATS.201704-306RL","article-title":"Procalcitonin test availability: a survey of acute care hospitals in Massachusetts","volume":"14","author":"Fisher","year":"2017","journal-title":"Ann Am Thorac Soc"},{"issue":"3","key":"2021120912573271200_B32","doi-asserted-by":"crossref","first-page":"e142","DOI":"10.1093\/pch\/pxy126","article-title":"Emergency department and inpatient clinical decision tools for the management of febrile young infants among tertiary paediatric centres across Canada","volume":"24","author":"Burstein","year":"2019","journal-title":"Paediatr Child Health"},{"issue":"10","key":"2021120912573271200_B33","doi-asserted-by":"crossref","first-page":"921","DOI":"10.1197\/j.aem.2005.06.006","article-title":"Reappraisal of criteria used to predict serious bacterial illness in febrile infants less than 8 weeks of age","volume":"12","author":"Garra","year":"2005","journal-title":"Acad Emerg Med"},{"issue":"5","key":"2021120912573271200_B34","doi-asserted-by":"crossref","first-page":"e20163268","DOI":"10.1542\/peds.2016-3268","article-title":"Epidemiology of cerebrospinal fluid cultures and time to detection in term infants","volume":"139","author":"Leazer","year":"2017","journal-title":"Pediatrics"},{"key":"2021120912573271200_B35","doi-asserted-by":"crossref","first-page":"113","DOI":"10.1016\/j.ins.2013.07.007","article-title":"An insight into classification with imbalanced data: empirical results and current trends on using data intrinsic characteristics","volume":"250","author":"L\u00f3pez","year":"2013","journal-title":"Inf Sci (Ny)"},{"issue":"6","key":"2021120912573271200_B36","doi-asserted-by":"crossref","first-page":"550","DOI":"10.1001\/jamapediatrics.2018.0217","article-title":"Development and validation of a calculator for estimating the probability of urinary tract infection in young febrile children","volume":"172","author":"Shaikh","year":"2018","journal-title":"JAMA Pediatr"},{"key":"2021120912573271200_B37","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"},{"issue":"3","key":"2021120912573271200_B38","doi-asserted-by":"crossref","first-page":"269","DOI":"10.1111\/acem.12876","article-title":"Prediction of in-hospital mortality in emergency department patients with sepsis: a local big data-driven, machine learning approach","volume":"23","author":"Taylor","year":"2016","journal-title":"Acad Emerg Med"},{"issue":"4","key":"2021120912573271200_B39","doi-asserted-by":"crossref","first-page":"e0174708","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"},{"issue":"9","key":"2021120912573271200_B40","doi-asserted-by":"crossref","first-page":"826","DOI":"10.1016\/S0895-4356(03)00207-5","article-title":"External validation is necessary in prediction research: a clinical example","volume":"56","author":"Bleeker","year":"2003","journal-title":"J Clin Epidemiol"},{"key":"2021120912573271200_B41","article-title":"Challenges to the reproducibility of machine learning models in health care [published online ahead of print January 6, 2020]","author":"Beam","journal-title":"JAMA"},{"key":"2021120912573271200_B43","first-page":"374","volume-title":"Encyclopedia of Bioinformatics and Computational Biology: ABC of Bioinformatics","author":"Fratello","year":"2018"}],"container-title":["Pediatrics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/publications.aap.org\/pediatrics\/article-pdf\/doi\/10.1542\/peds.2019-4096\/1080207\/peds_20194096.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/publications.aap.org\/pediatrics\/article-pdf\/doi\/10.1542\/peds.2019-4096\/1080207\/peds_20194096.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,10]],"date-time":"2022-11-10T10:57:16Z","timestamp":1668077836000},"score":1,"resource":{"primary":{"URL":"https:\/\/publications.aap.org\/pediatrics\/article\/146\/3\/e20194096\/36717\/Machine-Learning-To-Predict-Serious-Bacterial"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,9,1]]},"references-count":40,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2020,9,1]]},"published-print":{"date-parts":[[2020,9,1]]}},"URL":"https:\/\/doi.org\/10.1542\/peds.2019-4096","relation":{},"ISSN":["0031-4005","1098-4275"],"issn-type":[{"value":"0031-4005","type":"print"},{"value":"1098-4275","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,9,1]]},"article-number":"e20194096"}}