{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T14:54:08Z","timestamp":1785941648758,"version":"3.56.0"},"reference-count":30,"publisher":"Oxford University Press (OUP)","issue":"4","license":[{"start":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T00:00:00Z","timestamp":1784678400000},"content-version":"vor","delay-in-days":41,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Vicerrector\u00eda de Investigaci\u00f3n y Proyecci\u00f3n Social of the Universidad Surcolombiana","award":["4258"],"award-info":[{"award-number":["4258"]}]},{"name":"Divisi\u00f3n de Inmunolog\u00eda\u2014Medicina"},{"DOI":"10.13039\/501100020905","name":"Universidad Surcolombiana","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100020905","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,6,11]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Differentiating bacterial from viral infections in febrile young infants is challenging, particularly in dengue-hyperendemic regions. We developed and internally validated a clinical machine-learning model to enhance diagnostic accuracy in this risk population in Colombia. We retrospectively analyzed a pediatric infectious admission cohort (&amp;lt;18\u2009years) at a reference hospital in southern Colombia from 2007 to 2019. 4671 admissions (2251 bacterial and 2420 viral) were included. Nine clinical and laboratory variables were used to train an eXtreme Gradient Boosting (XGBoost) classifier. We divided the data into development (70%) and test (30%) sets, with Youden\u2019s J statistics defining the optimal threshold. Penalized logistic regression (LR) and single-marker rules [leukocytosis, C-reactive protein (CRP)] served as comparators. The young-infant XGBoost achieved an area under the receiver-operating characteristic curve (AUC) of 0.896, outperforming LR (0.790) and single markers (0.746\u20130.706). Sensitivity was 93.5%, specificity 76.1%, positive predictive value 87.9%, and negative predictive value 86.4% in the temporal validation cohort. Discrimination was highest in children aged 6\u201310\u2009years (AUC 0.967). CRP positivity, leukocytosis &amp;gt;16\u2009\u00d7\u200910\u00b3 \u00b5l\u22121, and thrombocytopenia &amp;lt;150\u2009\u00d7\u200910\u00b3 \u00b5l\u22121 were the most informative features. A nine-variable XGBoost model using routine clinical and hematologic variables accurately differentiated bacterial from viral infections in children from a low-resource dengue-endemic setting. Performance remained stable during temporal validation. Improved specificity with preserved sensitivity supports earlier targeted therapy and antibiotic stewardship. Multicenter studies and exploration of clinical challenges are the next steps for this kind of tool.<\/jats:p>","DOI":"10.1093\/tropej\/fmag050","type":"journal-article","created":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T11:54:38Z","timestamp":1783770878000},"source":"Crossref","is-referenced-by-count":0,"title":["A 13-year cohort study using clinical machine learning to differentiate bacterial and viral infections in young infants in a dengue hyperendemic region"],"prefix":"10.1093","volume":"72","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1271-2860","authenticated-orcid":false,"given":"Lucas J","family":"Cort\u00e9s-Guzm\u00e1n","sequence":"first","affiliation":[{"name":"Divisi\u00f3n de Inmunolog\u00eda, Programa de Medicina, Facultad de Ciencias de la Salud, Universidad Surcolombiana , Neiva, Huila, 41001,","place":["Colombia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Doris M","family":"Salgado","sequence":"additional","affiliation":[{"name":"\u00c1rea de Pediatr\u00eda, Departamento de Ciencias Cl\u00ednicas, Facultad de Ciencias de la Salud, Universidad Surcolombiana, Hospital Universitario de Neiva , Neiva, Huila, 41001,","place":["Colombia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0129-5210","authenticated-orcid":false,"given":"Carlos F","family":"Narv\u00e1ez","sequence":"additional","affiliation":[{"name":"Divisi\u00f3n de Inmunolog\u00eda, Programa de Medicina, Facultad de Ciencias de la Salud, Universidad Surcolombiana , Neiva, Huila, 41001,","place":["Colombia"]},{"name":"\u00c1rea de Pediatr\u00eda, Departamento de Ciencias Cl\u00ednicas, Facultad de Ciencias de la Salud, Universidad Surcolombiana, Hospital Universitario de Neiva , Neiva, Huila, 41001,","place":["Colombia"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,7,22]]},"reference":[{"key":"2026080510164109500_fmag050-B1","doi-asserted-by":"publisher","DOI":"10.7759\/cureus.58315","article-title":"Exploring acute febrile illness in children: clinical characteristics and diagnostic challenges","volume":"16","author":"Darishetty","year":"2024","journal-title":"Cureus"},{"key":"2026080510164109500_fmag050-B2","doi-asserted-by":"publisher","first-page":"e16\u20137","DOI":"10.1016\/S2214-109X(23)00496-5","article-title":"Global, regional, and national causes of death in children and adolescents younger than 20 years: an open data portal with estimates for 2000\u201321","volume":"12","author":"Villavicencio","year":"2024","journal-title":"Lancet Glob Heal"},{"key":"2026080510164109500_fmag050-B3","doi-asserted-by":"publisher","first-page":"e0012932","DOI":"10.1371\/journal.pntd.0012932","article-title":"Assessing the global dengue burden: incidence, mortality, and disability trends over three decades","volume":"19","author":"Zhang","year":"2025","journal-title":"PLoS Negl Trop Dis"},{"key":"2026080510164109500_fmag050-B4","doi-asserted-by":"publisher","first-page":"2391","DOI":"10.3201\/eid3011.241031","article-title":"Dengue outbreak caused by multiple virus serotypes and lineages, Colombia, 2023-2024","volume":"30","author":"Grubaugh","year":"2024","journal-title":"Emerg Infect Dis"},{"key":"2026080510164109500_fmag050-B5","first-page":"26","volume":"33","author":"Instituto Nacional de Salud de Colombia","year":"2025","journal-title":"Bolet\u00edn Epidemiol\u00f3gico Semana"},{"key":"2026080510164109500_fmag050-B6","doi-asserted-by":"publisher","first-page":"120","DOI":"10.1007\/s12519-022-00611-8","article-title":"Fever without a source in children: international comparison of guidelines","volume":"19","author":"Graaf","year":"2023","journal-title":"World J Pediatr"},{"key":"2026080510164109500_fmag050-B7","first-page":"48","article-title":"Fiabilidad de los biomarcadores procalcitonina y prote\u00edna C reactiva Para diferenciar el origen v\u00edrico o bacteriano de las infecciones pedi\u00e1tricas","volume":"78","author":"Bayle-S\u00e1nchez","year":"2020","journal-title":"Acta Pediatr Espa\u00f1ola"},{"key":"2026080510164109500_fmag050-B8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2018\/4869329","article-title":"Approach to neonates and young infants with fever without a source who are at risk for severe bacterial infection","volume":"2018","author":"Esposito","year":"2018","journal-title":"Mediators Inflamm"},{"key":"2026080510164109500_fmag050-B9","doi-asserted-by":"publisher","first-page":"358","DOI":"10.1016\/S2352-4642(24)00021-X","article-title":"Diagnostic test accuracy of procalcitonin and C-reactive protein for predicting invasive and serious bacterial infections in young febrile infants: a systematic review and meta-analysis","volume":"8","author":"Norman-Bruce","year":"2024","journal-title":"Lancet Child Adolesc Heal"},{"key":"2026080510164109500_fmag050-B10","doi-asserted-by":"publisher","first-page":"e29372","DOI":"10.1016\/j.heliyon.2024.e29372","article-title":"Differentiating viral and bacterial infections: a machine learning model based on routine blood test values","volume":"10","author":"Gun\u010dar","year":"2024","journal-title":"Heliyon"},{"key":"2026080510164109500_fmag050-B11","volume-title":"Algoritmos Para El manejo cl\u00ednico de los casos de dengue","author":"Organizaci\u00f3n Panamericana de la Salud (OPS)","year":"2020"},{"key":"2026080510164109500_fmag050-B12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1093\/ejcts\/ezaf142","article-title":"Statistical primer: sample size considerations for developing and validating clinical prediction models","volume":"67","author":"Martin","year":"2025","journal-title":"Eur J Cardio-Thoracic Surg"},{"key":"2026080510164109500_fmag050-B13","doi-asserted-by":"publisher","first-page":"190","DOI":"10.1093\/jpids\/piw016","article-title":"Challenges in the etiology and diagnosis of acute febrile illness in children in low- and middle-income countries","volume":"5","author":"Iroh Tam","year":"2016","journal-title":"J Pediatric Infect Dis Soc"},{"key":"2026080510164109500_fmag050-B14","doi-asserted-by":"publisher","first-page":"158","DOI":"10.1016\/j.afjem.2020.09.015","article-title":"Infants 21\u201390 days presenting with a possible serious bacterial infection\u2013are evaluation algorithms from high income countries applicable in the South African public health sector?","volume":"11","author":"Lishman","year":"2021","journal-title":"African J Emerg Med"},{"key":"2026080510164109500_fmag050-B15","doi-asserted-by":"publisher","first-page":"e361\u201372","DOI":"10.1016\/S2214-109X(22)00514-9","article-title":"Early diagnostic indicators of dengue versus other febrile illnesses in Asia and Latin America (IDAMS study): a multicentre, prospective, observational study","volume":"11","author":"Rosenberger","year":"2023","journal-title":"Lancet Glob Heal"},{"key":"2026080510164109500_fmag050-B16","doi-asserted-by":"publisher","first-page":"178","DOI":"10.1097\/INF.0000000000004163","article-title":"NS1-specific antibody response facilitates the identification of children with dengue and zika in hyperendemic areas","volume":"43","author":"Castro-Trujillo","year":"2024","journal-title":"Pediatr Infect Dis J"},{"key":"2026080510164109500_fmag050-B17","doi-asserted-by":"publisher","first-page":"e0013260","DOI":"10.1371\/journal.pntd.0013260","article-title":"Clinical, virological, and antibody profiles of overlapping dengue and chikungunya virus infections in children from Southern Colombia","volume":"19","author":"Polan\u00eda-Espinosa","year":"2025","journal-title":"PLoS Negl Trop Dis"},{"key":"2026080510164109500_fmag050-B18","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3389\/fcimb.2024.1429309","article-title":"Dengue and SARS-CoV-2 co-circulation and overlapping infections in hospitalized patients","volume":"14","author":"Santos","year":"2024","journal-title":"Front Cell Infect Microbiol"},{"key":"2026080510164109500_fmag050-B19","doi-asserted-by":"publisher","first-page":"792","DOI":"10.1097\/INF.0000000000003990","article-title":"Unique immune blood markers between severe dengue and sepsis in children","volume":"42","author":"Salgado","year":"2023","journal-title":"Pediatr Infect Dis J"},{"key":"2026080510164109500_fmag050-B20","doi-asserted-by":"publisher","first-page":"583","DOI":"10.1097\/INF.0000000000005148","article-title":"Prolonged fever in pediatric dengue is associated with clinical severity and immune dysregulation","volume":"45","author":"Segura","year":"2026","journal-title":"Pediatr Infect Dis J"},{"key":"2026080510164109500_fmag050-B21","doi-asserted-by":"publisher","first-page":"450","DOI":"10.18203\/2349-3291.ijcp20170687","article-title":"Correlation of C-reactive protein and neutrophil counts as early indicators of severe dengue in children","volume":"4","author":"Atukuri","year":"2017","journal-title":"Int J Contemp Pediatr"},{"key":"2026080510164109500_fmag050-B22","doi-asserted-by":"publisher","first-page":"998","DOI":"10.1001\/jamapediatrics.2019.2656","article-title":"Efficacy of a clinical prediction rule to identify febrile young infants at low risk for serious bacterial infections\u2014reply","volume":"173","author":"Kuppermann","year":"2019","journal-title":"JAMA Pediatr"},{"key":"2026080510164109500_fmag050-B23","doi-asserted-by":"publisher","first-page":"e0008960","DOI":"10.1371\/journal.pntd.0008960","article-title":"Assessing the risk of dengue severity using demographic information and laboratory test results with machine learning","volume":"14","author":"Huang","year":"2020","journal-title":"PLoS Negl Trop Dis"},{"key":"2026080510164109500_fmag050-B24","doi-asserted-by":"publisher","first-page":"e003548","DOI":"10.1136\/bmjpo-2025-003548","article-title":"Development of a machine learning-based prediction model for serious bacterial infections in febrile young infants","volume":"9","author":"Park","year":"2025","journal-title":"BMJ Paediatr Open"},{"key":"2026080510164109500_fmag050-B25","doi-asserted-by":"publisher","first-page":"1283","DOI":"10.1101\/2024.11.13.24317272","article-title":"Machine learning for improved dengue diagnosis in Puerto Rico","volume":"30","author":"Madewell"},{"key":"2026080510164109500_fmag050-B26","doi-asserted-by":"publisher","first-page":"192","DOI":"10.1016\/j.jpeds.2020.12.079","article-title":"Using clinical history factors to identify bacterial infections in young febrile infants","volume":"232","author":"Yaeger","year":"2021","journal-title":"J Pediatr"},{"key":"2026080510164109500_fmag050-B27","doi-asserted-by":"publisher","first-page":"893","DOI":"10.1002\/jhm.12956","article-title":"Derivation of a clinical-based model to detect invasive bacterial infections in febrile infants","volume":"17","author":"Yaeger","year":"2022","journal-title":"J Hosp Med"},{"key":"2026080510164109500_fmag050-B28","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2022\/6902321","article-title":"Modern machine-learning predictive models for diagnosing infectious diseases","volume":"2022","author":"Alqaissi","year":"2022","journal-title":"Comput Math Methods Med"},{"key":"2026080510164109500_fmag050-B29","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1186\/s13756-018-0459-1","article-title":"Assessing the social cost and benefits of a national requirement establishing antibiotic stewardship programs to prevent Clostridioides difficile infection in US hospitals","volume":"8","author":"Scott","year":"2019","journal-title":"Antimicrob Resist Infect Control"},{"key":"2026080510164109500_fmag050-B30","doi-asserted-by":"publisher","first-page":"n2281","DOI":"10.1136\/bmj.n2281","article-title":"Risk of bias in studies on prediction models developed using supervised machine learning techniques: systematic review","volume":"375","author":"Andaur Navarro","year":"2021","journal-title":"Br Med J"}],"container-title":["Journal of Tropical Pediatrics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/tropej\/article-pdf\/72\/4\/fmag050\/69763780\/fmag050.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/tropej\/article-pdf\/72\/4\/fmag050\/69763780\/fmag050.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T14:16:51Z","timestamp":1785939411000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/tropej\/article\/doi\/10.1093\/tropej\/fmag050\/8739574"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,11]]},"references-count":30,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2026,6,11]]}},"URL":"https:\/\/doi.org\/10.1093\/tropej\/fmag050","relation":{},"ISSN":["0142-6338","1465-3664"],"issn-type":[{"value":"0142-6338","type":"print"},{"value":"1465-3664","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,8]]},"published":{"date-parts":[[2026,6,11]]},"article-number":"fmag050"}}