{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T01:21:38Z","timestamp":1792027298102,"version":"4.4.0"},"reference-count":31,"publisher":"Public Library of Science (PLoS)","issue":"3","license":[{"start":{"date-parts":[[2022,3,25]],"date-time":"2022-03-25T00:00:00Z","timestamp":1648166400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100004332","name":"Seoul National University Hospital","doi-asserted-by":"publisher","award":["042019021"],"award-info":[{"award-number":["042019021"]}],"id":[{"id":"10.13039\/501100004332","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:p>Serious bacterial infection (SBI) in children, such as bacterial meningitis or sepsis, is an important condition that can lead to fatal outcomes. Therefore, since it is very important to accurately diagnose SBI, SBI prediction tools such as \u2018Refined Lab-score\u2019 or \u2018clinical prediction rule\u2019 have been developed and used. However, these tools can predict SBI only when there are values of all factors used in the tool, and if even one of them is missing, the tools become useless. Therefore, the purpose of this study was to develop and validate a machine learning-driven model to predict SBIs among febrile children, even with missing values. This was a multicenter retrospective observational study including febrile children &lt;6 years of age who visited Emergency departments (EDs) of 3 different tertiary hospitals from 2016 to 2018. The SBI prediction model was trained with a derivation cohort (data from two hospitals) and externally tested with a validation cohort (data from a third hospital). A total of 11,973 and 2,858 patient records were included in the derivation and validation cohorts, respectively. In the derivation cohort, the area under the receiver operating characteristic curve (AUROC) of the RF model was 0.964 (95% confidence interval [CI], 0.943\u20130.986), and the area under the precision-recall curve (AUPRC) was 0.753 (95% CI, 0.681\u20130.824). The conventional LR (CLR) model showed corresponding values of 0.902 (95% CI, 0.894\u20130.910) and 0.573 (95% CI, 0.560\u20130.586), respectively. In the validation cohort, the AUROC (95% CI) of the RF model was 0.950 (95% CI, 0.945\u20130.956), the AUPRC was 0.605 (95% CI, 0.593\u20130.616), and the CLR presented corresponding values of 0.815 (95% CI, 0.789\u20130.841) and 0.586 (95% CI, 0.553\u20130.619), respectively. We developed a machine learning-driven prediction model for SBI among febrile children, which works robustly despite missing values. And it showed superior performance compared to CLR in both internal validation and external validation.<\/jats:p>","DOI":"10.1371\/journal.pone.0265500","type":"journal-article","created":{"date-parts":[[2022,3,25]],"date-time":"2022-03-25T13:39:45Z","timestamp":1648215585000},"page":"e0265500","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":8,"title":["Development and validation of machine learning-driven prediction model for serious bacterial infection among febrile children in emergency departments"],"prefix":"10.1371","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7878-9644","authenticated-orcid":true,"given":"Bongjin","family":"Lee","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hyun Jung","family":"Chung","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hyun Mi","family":"Kang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6144-302X","authenticated-orcid":true,"given":"Do Kyun","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Young Ho","family":"Kwak","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2022,3,25]]},"reference":[{"issue":"10","key":"pone.0265500.ref001","doi-asserted-by":"crossref","first-page":"1222","DOI":"10.3346\/jkms.2012.27.10.1222","article-title":"Utilization of emergency department by children in Korea","volume":"27","author":"YH Kwak","year":"2012","journal-title":"Journal of Korean medical science"},{"issue":"2","key":"pone.0265500.ref002","doi-asserted-by":"crossref","first-page":"228","DOI":"10.1542\/peds.2009-1070","article-title":"Performance of low-risk criteria in the evaluation of young infants with fever: review of the literature","volume":"125","author":"AR Huppler","year":"2010","journal-title":"Pediatrics"},{"issue":"10","key":"pone.0265500.ref003","doi-asserted-by":"crossref","first-page":"745","DOI":"10.3109\/00365548.2012.689846","article-title":"Clinical and laboratory variables identifying bacterial infection and bacteraemia in the emergency department","volume":"44","author":"P Gille-Johnson","year":"2012","journal-title":"Scand J Infect Dis"},{"issue":"1","key":"pone.0265500.ref004","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1136\/archdischild-2015-308519","article-title":"Comparison of peripheral and central capillary refill time in febrile children presenting to a paediatric emergency department and its utility in identifying children with serious bacterial infection","volume":"102","author":"E de Vos-Kerkhof","year":"2017","journal-title":"Archives of disease in childhood"},{"issue":"11","key":"pone.0265500.ref005","doi-asserted-by":"crossref","first-page":"948","DOI":"10.1136\/emj.2009.087783","article-title":"Prediction of severe bacterial infection in children with an emergency department diagnosis of infection.","volume":"28","author":"C Vorwerk","year":"2011","journal-title":"Emergency medicine journal: EMJ."},{"issue":"1","key":"pone.0265500.ref006","doi-asserted-by":"crossref","first-page":"113","DOI":"10.1186\/s13613-020-00729-w","article-title":"Prognostic performance of endothelial biomarkers to early predict clinical deterioration of patients with suspected bacterial infection and sepsis admitted to the emergency department.","volume":"10","author":"T Lafon","year":"2020","journal-title":"Annals of intensive care."},{"issue":"5","key":"pone.0265500.ref007","doi-asserted-by":"crossref","first-page":"387","DOI":"10.1097\/INF.0000000000001915","article-title":"Refined Lab-score, a Risk Score Predicting Serious Bacterial Infection in Febrile Children Less Than 3 Years of Age.","volume":"37","author":"S Leroy","year":"2018","journal-title":"The Pediatric infectious disease journal"},{"issue":"4","key":"pone.0265500.ref008","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":"N Kuppermann","year":"2019","journal-title":"JAMA pediatrics"},{"issue":"12","key":"pone.0265500.ref009","doi-asserted-by":"crossref","first-page":"1463","DOI":"10.1111\/acem.13655","article-title":"A Machine Learning Approach to Predicting Need for Hospitalization for Pediatric Asthma Exacerbation at the Time of Emergency Department Triage.","volume":"25","author":"SJ Patel","year":"2018","journal-title":"Academic emergency medicine: official journal of the Society for Academic Emergency Medicine"},{"issue":"1","key":"pone.0265500.ref010","doi-asserted-by":"crossref","first-page":"5368","DOI":"10.1038\/s41598-017-05505-8","article-title":"Machine Learning Algorithms for Risk Prediction of Severe Hand-Foot-Mouth Disease in Children.","volume":"7","author":"B Zhang","year":"2017","journal-title":"Scientific reports."},{"key":"pone.0265500.ref011","doi-asserted-by":"crossref","first-page":"413","DOI":"10.3389\/fped.2019.00413","article-title":"Pediatric Severe Sepsis Prediction Using Machine Learning.","volume":"7","author":"S Le","year":"2019","journal-title":"Frontiers in pediatrics"},{"key":"pone.0265500.ref012","doi-asserted-by":"crossref","first-page":"128","DOI":"10.1016\/j.resuscitation.2019.06.006","article-title":"Outcome prediction of out-of-hospital cardiac arrest with presumed cardiac aetiology using an advanced machine learning technique.","volume":"141","author":"T Seki","year":"2019","journal-title":"Resuscitation"},{"issue":"2","key":"pone.0265500.ref013","doi-asserted-by":"crossref","first-page":"206","DOI":"10.7763\/IJFCC.2012.V1.54","article-title":"Missing value imputation method based on clustering and nearest neighbours","volume":"1","author":"S Gajawada","year":"2012","journal-title":"International Journal of Future Computer and Communication"},{"key":"pone.0265500.ref014","volume-title":"Techniques for dealing with missing values in classification1997","author":"WZ Liu"},{"issue":"5","key":"pone.0265500.ref015","doi-asserted-by":"crossref","first-page":"92","DOI":"10.1007\/s10916-018-0940-7","article-title":"Accurate diabetes risk stratification using machine learning: role of missing value and outliers.","volume":"42","author":"M Maniruzzaman","year":"2018","journal-title":"Journal of medical systems"},{"key":"pone.0265500.ref016","first-page":"245","volume-title":"Machine learning-based missing value imputation method for clinical datasets. IAENG transactions on engineering technologies","author":"MM Rahman","year":"2013"},{"issue":"7","key":"pone.0265500.ref017","doi-asserted-by":"crossref","first-page":"1","DOI":"10.18637\/jss.v023.i07","article-title":"Generalized additive models for location scale and shape (GAMLSS) in R.","volume":"23","author":"DM Stasinopoulos","year":"2007","journal-title":"Journal of Statistical Software."},{"issue":"4","key":"pone.0265500.ref018","first-page":"1125","article-title":"Using Super-Imposition by Translation And Rotation (SITAR) to relate pubertal growth to bone health in later life: the Medical Research Council (MRC) National Survey of Health and Development.","volume":"45","author":"TJ Cole","year":"2016","journal-title":"Int J Epidemiol."},{"key":"pone.0265500.ref019","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1016\/j.resuscitation.2019.07.020","article-title":"Prediction of good neurological recovery after out-of-hospital cardiac arrest: A machine learning analysis.","volume":"142","author":"JH Park","year":"2019","journal-title":"Resuscitation"},{"key":"pone.0265500.ref020","first-page":"2825","article-title":"Scikit-learn: Machine learning in Python.","volume":"12","author":"F Pedregosa","year":"2011","journal-title":"the Journal of machine Learning research"},{"key":"pone.0265500.ref021","doi-asserted-by":"crossref","first-page":"567","DOI":"10.1016\/j.entcs.2019.08.050","article-title":"Minimization of Gini Impurity: NP-completeness and Approximation Algorithm via Connections with the k-means Problem","volume":"346","author":"E Laber","year":"2019","journal-title":"Electronic Notes in Theoretical Computer Science"},{"key":"pone.0265500.ref022","doi-asserted-by":"crossref","unstructured":"Chang H-K, Wu C-T, Liu J-H, Lim WS, Wang H-C, Chiu S-I, et al., editors. Early Detecting In-Hospital Cardiac Arrest Based on Machine Learning on Imbalanced Data. 2019 IEEE International Conference on Healthcare Informatics (ICHI); 2019: IEEE.","DOI":"10.1109\/ICHI.2019.8904504"},{"key":"pone.0265500.ref023","doi-asserted-by":"crossref","unstructured":"Stanescu A, Caragea D, editors. Ensemble-based semi-supervised learning approaches for imbalanced splice site datasets. 2014 IEEE International Conference on Bioinformatics and Biomedicine (BIBM); 2014: IEEE.","DOI":"10.1109\/BIBM.2014.6999196"},{"key":"pone.0265500.ref024","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v31i1.10837","volume-title":"A Framework of Online Learning with Imbalanced Streaming Data","author":"Y Yan","year":"2017"},{"issue":"3","key":"pone.0265500.ref025","doi-asserted-by":"crossref","DOI":"10.1542\/peds.2019-4096","article-title":"Machine Learning To Predict Serious Bacterial Infections in Young Febrile Infants","volume":"146","author":"S Ramgopal","year":"2020","journal-title":"Pediatrics"},{"issue":"5","key":"pone.0265500.ref026","article-title":"Using Machine Learning to Predict Bacteremia in Febrile Children Presented to the Emergency Department.","volume":"10","author":"CM Tsai","year":"2020","journal-title":"Diagnostics (Basel)."},{"issue":"11","key":"pone.0265500.ref027","doi-asserted-by":"crossref","first-page":"e273","DOI":"10.1097\/INF.0000000000000466","article-title":"C-reactive protein, procalcitonin and the lab-score for detecting serious bacterial infections in febrile children at the emergency department: a prospective observational study","volume":"33","author":"RG Nijman","year":"2014","journal-title":"The Pediatric infectious disease journal"},{"key":"pone.0265500.ref028","volume-title":"Experimental comparison of orthogonal moments as feature extraction methods for character recognition. Iberoamerican Congress on Pattern Recognition","author":"MA Duval","year":"2010"},{"issue":"9","key":"pone.0265500.ref029","article-title":"Reliable Recurrence Algorithm for High-Order Krawtchouk Polynomials.","volume":"23","author":"KA Al-Utaibi","year":"2021","journal-title":"Entropy (Basel)."},{"issue":"6","key":"pone.0265500.ref030","doi-asserted-by":"crossref","first-page":"2225","DOI":"10.1007\/s11554-021-01093-z","article-title":"Fast and efficient recursive algorithm of Meixner polynomials","volume":"18","author":"SH Abdulhussain","year":"2021","journal-title":"Journal of Real-Time Image Processing"},{"issue":"6","key":"pone.0265500.ref031","doi-asserted-by":"crossref","first-page":"895","DOI":"10.3346\/jkms.2010.25.6.895","article-title":"The causative organisms of bacterial meningitis in Korean children in 1996\u20132005","volume":"25","author":"HK Cho","year":"2010","journal-title":"Journal of Korean medical science"}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0265500","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,29]],"date-time":"2023-01-29T23:32:22Z","timestamp":1675035142000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0265500"}},"subtitle":[],"editor":[{"given":"Vijayalakshmi","family":"Kakulapati","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2022,3,25]]},"references-count":31,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2022,3,25]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0265500","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,3,25]]}}}