{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T17:46:47Z","timestamp":1790876807315,"version":"4.1.0"},"reference-count":22,"publisher":"American Academy of Pediatrics (AAP)","issue":"6","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,1]]},"abstract":"<jats:sec>\n                    <jats:title>OBJECTIVE<\/jats:title>\n                    <jats:p>The medical community recently experienced a severe shortage of blood culture media bottles. Rates of blood stream infection (BSI) among critically ill children are low. We sought to design a machine learning (ML) model able to identify children at low risk for BSI to improve blood culture diagnostic stewardship.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>METHODS<\/jats:title>\n                    <jats:p>We developed and validated an extreme gradient-boosting ML classifier using an existing dataset of retrospective pediatric intensive care unit (PICU) patients from a single institution. Data from children aged 3\u00a0months to 18\u00a0years who had a blood culture collected within 24\u00a0hours of PICU admission were included. The first 80% of patients (1\/1\/2011-12\/21\/2018) were used for model training and the last 20% (12\/22\/2018-12\/25\/2020) for testing (temporal validation). All 121 variables from the original dataset (vital sign, laboratory, and other clinical data) were included as predictors. Negative predictive value (NPV) was the primary evaluation metric.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>RESULTS<\/jats:title>\n                    <jats:p>Of the 3121 blood cultures obtained during 2320 PICU admissions (2100 unique children), 205 (6.6%) were positive. Model NPV was 0.997 in the training set and identified 667\/2321 (28.7%) of negative cultures. NPV was 0.993 in the test set and identified 151\/595 (25.4%) of negative cultures. The number needed to harm was 151 (151 negative blood cultures could be avoided for each false negative prediction). Key predictors included central line presence, temperature rate of change, and mean platelet volume.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>CONCLUSIONS<\/jats:title>\n                    <jats:p>We trained and validated an ML model that accurately predicted &amp;gt;25% of subsequently negative blood cultures. If implemented prospectively, such models could help reduce unnecessary blood cultures among low-risk children.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1542\/hpeds.2024-008235","type":"journal-article","created":{"date-parts":[[2025,5,21]],"date-time":"2025-05-21T20:02:53Z","timestamp":1747857773000},"page":"e240-e244","source":"Crossref","is-referenced-by-count":1,"title":["Diagnostic Stewardship of Blood Cultures in the Pediatric ICU Using Machine Learning"],"prefix":"10.1542","volume":"15","author":[{"given":"Blake","family":"Martin","sequence":"first","affiliation":[{"name":"1Section of Critical Care Medicine, Department of Pediatrics, University of Colorado School of Medicine, Aurora, Colorado"},{"name":"2Department of Biomedical Informatics, University of Colorado School of Medicine, Aurora, Colorado"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peter E.","family":"DeWitt","sequence":"additional","affiliation":[{"name":"2Department of Biomedical Informatics, University of Colorado School of Medicine, Aurora, Colorado"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marisa","family":"Payan","sequence":"additional","affiliation":[{"name":"3Research Informatics and Data Science, Children\u2019s Hospital Colorado, Aurora, Colorado"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christopher H.","family":"Greer","sequence":"additional","affiliation":[{"name":"4Precision Medicine Institute, Children\u2019s Hospital Colorado, Aurora, Colorado"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Seth","family":"Russell","sequence":"additional","affiliation":[{"name":"2Department of Biomedical Informatics, University of Colorado School of Medicine, Aurora, Colorado"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Charlotte","family":"Gray","sequence":"additional","affiliation":[{"name":"2Department of Biomedical Informatics, University of Colorado School of Medicine, Aurora, Colorado"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sara J.","family":"Deakyne Davies","sequence":"additional","affiliation":[{"name":"3Research Informatics and Data Science, Children\u2019s Hospital Colorado, Aurora, Colorado"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Charlotte Z.","family":"Woods-Hill","sequence":"additional","affiliation":[{"name":"5Department of Anesthesiology and Critical Care Medicine, The Children\u2019s Hospital of Philadelphia, Philadelphia, Pennsylvania"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Halden F.","family":"Scott","sequence":"additional","affiliation":[{"name":"6Section of Emergency Medicine, Department of Pediatrics, University of Colorado School of Medicine, Aurora, Colorado"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sarah","family":"Parker","sequence":"additional","affiliation":[{"name":"7Section of Infectious Disease, Department of Pediatrics, University of Colorado School of Medicine, Aurora, Colorado"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David","family":"Albers","sequence":"additional","affiliation":[{"name":"2Department of Biomedical Informatics, University of Colorado School of Medicine, Aurora, Colorado"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tellen D.","family":"Bennett","sequence":"additional","affiliation":[{"name":"1Section of Critical Care Medicine, Department of Pediatrics, University of Colorado School of Medicine, Aurora, Colorado"},{"name":"2Department of Biomedical Informatics, University of Colorado School of Medicine, Aurora, Colorado"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"417","published-online":{"date-parts":[[2025,5,22]]},"reference":[{"key":"2026042102215973600_r1","article-title":"Disruptions in Availability of BD BACTEC Blood Culture Bottles: Current Situation","author":"Centers for Disease Control and Prevention","year":"2024"},{"issue":"4","key":"2026042102215973600_r2","doi-asserted-by":"crossref","first-page":"569","DOI":"10.1007\/s15010-020-01439-y","article-title":"Blood culture sampling rate in hospitalised children as a quality indicator for diagnostic stewardship","volume":"48","author":"Araujo da Silva","year":"2020","journal-title":"Infection."},{"issue":"2 Pt 1","key":"2026042102215973600_r3","doi-asserted-by":"crossref","first-page":"251","DOI":"10.1542\/peds.106.2.251","article-title":"Outpatient pediatric blood cultures: time to positivity","volume":"106","author":"McGowan","year":"2000","journal-title":"Pediatrics."},{"issue":"9","key":"2026042102215973600_r4","doi-asserted-by":"crossref","first-page":"953","DOI":"10.1542\/hpeds.2021-005873","article-title":"Time to blood culture positivity by pathogen and primary service","volume":"11","author":"MacBrayne","year":"2021","journal-title":"Hosp Pediatr."},{"issue":"10","key":"2026042102215973600_r5","doi-asserted-by":"crossref","first-page":"836","DOI":"10.1542\/hpeds.2020-0146","article-title":"Impact of contaminated blood cultures on children, families, and the health care system","volume":"10","author":"Farrell","year":"2020","journal-title":"Hosp Pediatr."},{"issue":"1","key":"2026042102215973600_r6","doi-asserted-by":"crossref","first-page":"144","DOI":"10.1186\/s12911-020-01165-3","article-title":"How good is our diagnostic intuition? Clinician prediction of bacteremia in critically ill children","volume":"20","author":"Hoops","year":"2020","journal-title":"BMC Med Inform Decis Mak."},{"issue":"3","key":"2026042102215973600_r7","doi-asserted-by":"crossref","first-page":"364","DOI":"10.1097\/PCC.0b013e3181a31bb7","article-title":"Utility of blood cultures in postoperative pediatric intensive care unit patients","volume":"10","author":"Kiragu","year":"2009","journal-title":"Pediatr Crit Care Med."},{"issue":"3","key":"2026042102215973600_r8","doi-asserted-by":"crossref","first-page":"144","DOI":"10.1055\/s-0038-1676993","article-title":"Epidemiology of blood culture utilization in a cohort of critically ill children","volume":"8","author":"Tran","year":"2019","journal-title":"J Pediatr Intensive Care."},{"issue":"8","key":"2026042102215973600_r9","doi-asserted-by":"crossref","first-page":"670","DOI":"10.1097\/PCC.0000000000003256","article-title":"A novel comprehensive algorithm for evaluation of PICU patients with new fever or instability","volume":"24","author":"Sick-Samuels","year":"2023","journal-title":"Pediatr Crit Care Med."},{"issue":"2","key":"2026042102215973600_r10","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1001\/jamapediatrics.2016.3153","article-title":"Association of a clinical practice guideline with blood culture use in critically ill children","volume":"171","author":"Woods-Hill","year":"2017","journal-title":"JAMA Pediatr."},{"issue":"6","key":"2026042102215973600_r11","doi-asserted-by":"crossref","first-page":"590","DOI":"10.1542\/hpeds.2021-005998","article-title":"Machine learning approach to predicting absence of serious bacterial infection at PICU admission","volume":"12","author":"Martin","year":"2022","journal-title":"Hosp Pediatr."},{"issue":"1","key":"2026042102215973600_r12","doi-asserted-by":"crossref","first-page":"199","DOI":"10.1186\/1471-2431-14-199","article-title":"Pediatric complex chronic conditions classification system version 2: updated for ICD-10 and complex medical technology dependence and transplantation","volume":"14","author":"Feudtner","year":"2014","journal-title":"BMC Pediatr."},{"issue":"6","key":"2026042102215973600_r13","doi-asserted-by":"crossref","first-page":"596","DOI":"10.1001\/jamapediatrics.2018.0256","article-title":"R package for pediatric complex chronic condition classification","volume":"172","author":"Feinstein","year":"2018","journal-title":"JAMA Pediatr."},{"key":"2026042102215973600_r14","volume-title":"xgboost: Extreme Gradient Boosting","author":"Chen","year":"2025"},{"issue":"4","key":"2026042102215973600_r15","doi-asserted-by":"crossref","first-page":"e237489","DOI":"10.1001\/jamanetworkopen.2023.7489","article-title":"Use of machine learning to differentiate children with Kawasaki disease from other febrile children in a pediatric emergency department","volume":"6","author":"Tsai","year":"2023","journal-title":"JAMA Netw Open."},{"issue":"1","key":"2026042102215973600_r16","doi-asserted-by":"crossref","first-page":"8956","DOI":"10.1038\/s41598-022-13152-x","article-title":"Outcome prediction for acute kidney injury among hospitalized children via eXtreme Gradient Boosting algorithm","volume":"12","author":"Deng","year":"2022","journal-title":"Sci Rep."},{"key":"2026042102215973600_r17","doi-asserted-by":"crossref","first-page":"107980","DOI":"10.1016\/j.cmpb.2023.107980","article-title":"Machine learning for hospital readmission prediction in pediatric population","volume":"244","author":"Silva","year":"2024","journal-title":"Comput Methods Programs Biomed."},{"key":"2026042102215973600_r18","article-title":"Consistent individualized feature attribution for tree ensembles","author":"Lundberg","year":"2018","journal-title":"arXiv."},{"issue":"7","key":"2026042102215973600_r19","doi-asserted-by":"crossref","first-page":"690","DOI":"10.1001\/jamapediatrics.2022.1024","article-title":"Association of diagnostic stewardship for blood cultures in critically ill children with culture rates, antibiotic use, and patient outcomes: results of the Bright STAR Collaborative","volume":"176","author":"Woods-Hill","year":"2022","journal-title":"JAMA Pediatr."},{"issue":"1","key":"2026042102215973600_r20","first-page":"92","article-title":"Mean platelet volume (MPV) and plasma lactate level in the diagnosis and prognosis of neonatal bacteremia","volume":"3","author":"EL-Ashry MA.","year":"2022","journal-title":"Microbes Infect Dis."},{"issue":"3","key":"2026042102215973600_r21","doi-asserted-by":"crossref","first-page":"e0119437","DOI":"10.1371\/journal.pone.0119437","article-title":"An increase in mean platelet volume from baseline is associated with mortality in patients with severe sepsis or septic shock","volume":"10","author":"Kim","year":"2015","journal-title":"PLoS One."},{"issue":"8","key":"2026042102215973600_r22","doi-asserted-by":"crossref","first-page":"675","DOI":"10.1001\/jama.2024.0196","article-title":"Development and validation of the Phoenix criteria for pediatric sepsis and septic shock","volume":"331","author":"Sanchez-Pinto","year":"2024","journal-title":"JAMA."}],"container-title":["Hospital Pediatrics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/publications.aap.org\/hospitalpediatrics\/article-pdf\/15\/6\/e240\/1812545\/hosppeds.2024008235.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/publications.aap.org\/hospitalpediatrics\/article-pdf\/15\/6\/e240\/1812545\/hosppeds.2024008235.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T06:22:07Z","timestamp":1776752527000},"score":1,"resource":{"primary":{"URL":"https:\/\/publications.aap.org\/hospitalpediatrics\/article\/15\/6\/e240\/201937\/Diagnostic-Stewardship-of-Blood-Cultures-in-the"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,22]]},"references-count":22,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2025,5,22]]},"published-print":{"date-parts":[[2025,6,1]]}},"URL":"https:\/\/doi.org\/10.1542\/hpeds.2024-008235","relation":{},"ISSN":["2154-1663","2154-1671"],"issn-type":[{"value":"2154-1663","type":"print"},{"value":"2154-1671","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,22]]}}}