{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T18:49:02Z","timestamp":1783536542010,"version":"3.55.0"},"reference-count":32,"publisher":"Public Library of Science (PLoS)","issue":"7","license":[{"start":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T00:00:00Z","timestamp":1783468800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Suqian Municipal Health Commission","award":["ZD202409"],"award-info":[{"award-number":["ZD202409"]}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"\n Objective<\/jats:title>\n Early differentiation of pediatric acute respiratory infections in outpatient and emergency settings is often hindered by nonspecific clinical signs, leading to unnecessary empirical antibiotic use and avoidable radiation exposure. Therefore, this study aimed to develop and internally evaluate an early triage model to distinguish pediatric bronchopneumonia (BP) from uncomplicated upper respiratory tract infection using routine, cost-effective laboratory parameters analyzed with machine-learning algorithms.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n This retrospective study consecutively enrolled 532 pediatric patients who presented with mild respiratory symptoms at their initial visit, comprising 218 in the BP group and 314 in the Upper Respiratory Tract Infection (URTI) group. Core laboratory indicators were selected using a dual-dimensionality reduction strategy that integrated the Least Absolute Shrinkage and Selection Operator (LASSO) regression with the Boruta algorithm. Seven machine learning classifiers were then constructed and compared based on the resulting feature matrix. The Shapley Additive Explanations (SHAP) framework was subsequently applied to interpret the nonlinear predictive mechanisms of the optimal model.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n This study constructed seven machine learning models: Logistic Regression (LR), Decision Tree (DT), Random Forest (RF), Extreme Gradient Boosting (XGBoost), Lightweight Gradient Boosting Machine (LightGBM), Support Vector Machine (SVM), and Artificial Neural Network (ANN). In the internal validation set, the SVM model demonstrated favorable predictive performance, with an area under the curve (AUC) of 0.921 (95% confidence interval: 0.874\u20130.959). Based on Platt-scaled probability estimates, the SVM model showed the lowest Brier score among the evaluated models, with a Brier score of 0.112. Decision curve analysis confirmed this model\u2019s positive net clinical benefit across a broad range of threshold probabilities. SHAP analysis further elucidated the nonlinear contribution weights of multiple conventional parameters at specific physiological thresholds.<\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n The multidimensional SVM risk quantification model, based on nine routine laboratory parameters, provides an accurate and objective assessment of pediatric BP risk. This model holds significant potential for clinical translation as a noninvasive, cost-effective triage tool in emergency departments. Its application could effectively reduce unnecessary radiographic screening and excessive antibiotic use.<\/jats:p>\n <\/jats:sec>","DOI":"10.1371\/journal.pone.0351509","type":"journal-article","created":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T17:33:27Z","timestamp":1783532007000},"page":"e0351509","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Explainable machine learning for the early differentiation of pediatric bronchopneumonia using routine laboratory parameters"],"prefix":"10.1371","volume":"21","author":[{"given":"Jinxing","family":"Dai","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Qiu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liran","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qianjin","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kang","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qingkai","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-8414-4982","authenticated-orcid":true,"given":"Weibing","family":"Qiu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,7,8]]},"reference":[{"issue":"1","key":"pone.0351509.ref001","doi-asserted-by":"crossref","DOI":"10.1136\/bmjopen-2023-078489","article-title":"Incidence of community-acquired pneumonia among children under 5 years in Suzhou, China: a hospital-based cohort study","volume":"14","author":"C Qian","year":"2024","journal-title":"BMJ Open"},{"key":"pone.0351509.ref002","doi-asserted-by":"crossref","first-page":"10009","DOI":"10.7189\/jogh.12.10009","article-title":"Aetiology of childhood pneumonia in low- and middle-income countries in the era of vaccination: a systematic review","volume":"12","author":"C von Mollendorf","year":"2022","journal-title":"J Glob Health"},{"issue":"1","key":"pone.0351509.ref003","doi-asserted-by":"crossref","first-page":"545","DOI":"10.1186\/s12887-021-03018-y","article-title":"The value of lymphocyte-to-monocyte ratio and neutrophil-to-lymphocyte ratio in differentiating pneumonia from upper respiratory tract infection (URTI) in children: a cross-sectional study","volume":"21","author":"J Wu","year":"2021","journal-title":"BMC Pediatr"},{"issue":"1","key":"pone.0351509.ref004","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1177\/00099228241254153","article-title":"Community-Acquired Pneumonia Diagnosis Following Emergency Department Visits for Respiratory Illness","volume":"64","author":"AT Geanacopoulos","year":"2025","journal-title":"Clin Pediatr (Phila)"},{"issue":"4","key":"pone.0351509.ref005","doi-asserted-by":"crossref","first-page":"103839","DOI":"10.1016\/j.bjid.2024.103839","article-title":"Evaluation of children\u2019s antibiotics use for outpatient pneumonia treatment in Vietnam","volume":"28","author":"TVL Thi","year":"2024","journal-title":"Braz J Infect Dis"},{"issue":"2","key":"pone.0351509.ref006","doi-asserted-by":"crossref","first-page":"80","DOI":"10.3345\/cep.2022.01452","article-title":"Community-acquired pneumonia in children: updated perspectives on its etiology, diagnosis, and treatment","volume":"67","author":"KW Yun","year":"2024","journal-title":"Clin Exp Pediatr"},{"issue":"31","key":"pone.0351509.ref007","doi-asserted-by":"crossref","first-page":"17040","DOI":"10.1021\/acs.analchem.5c02762","article-title":"Metabolism-driven colorimetric \u201cread-to-answer\u201d sensor array for bacterial discrimination and antimicrobial susceptibility testing","volume":"97","author":"X Lin","year":"2025","journal-title":"Anal Chem"},{"key":"pone.0351509.ref008","first-page":"30","article-title":"Isothermal Nucleic Acid Amplification Technologies and CRISPR\u2010Cas\u2010Based Nucleic Acid Detection Strategies for Infectious Diseases Diagnostics","volume-title":"Manual of Molecular Microbiology","author":"BM Liu","year":"2025"},{"issue":"1","key":"pone.0351509.ref009","doi-asserted-by":"crossref","first-page":"97","DOI":"10.3390\/biom14010097","article-title":"Biomarkers for Serious Bacterial Infections in Febrile Children","volume":"14","author":"L Bernardi","year":"2024","journal-title":"Biomolecules"},{"issue":"7","key":"pone.0351509.ref010","doi-asserted-by":"crossref","DOI":"10.1128\/JCM.01851-19","article-title":"Utility of Procalcitonin as a Biomarker for Sepsis in Children","volume":"58","author":"KJ Downes","year":"2020","journal-title":"J Clin Microbiol"},{"issue":"11","key":"pone.0351509.ref011","first-page":"1070","article-title":"Novel Biomarkers Differentiating Viral from Bacterial Infection in Febrile Children: Future Perspectives for Management in Clinical Praxis","volume":"8","author":"S Rhedin","year":"2021","journal-title":"Children (Basel)"},{"key":"pone.0351509.ref012","article-title":"Role of C reactive protein and procalcitonin in the diagnosis of lower respiratory tract infection in children in the outpatient setting","volume":"373","author":"A P\u00e9rez-L\u00f3pez","year":"2021","journal-title":"BMJ"},{"issue":"10","key":"pone.0351509.ref013","article-title":"Application value of systemic immune-inflammation index in predicting severe Mycoplasma pneumoniae pneumonia","volume":"20","author":"X Guo","year":"2025","journal-title":"PLoS One"},{"key":"pone.0351509.ref014","doi-asserted-by":"crossref","first-page":"10545","DOI":"10.2147\/JIR.S528341","article-title":"Routine Laboratory Markers-Based Machine Learning Model for Predicting Severe Kawasaki Disease in Pediatric Patients","volume":"18","author":"M Wu","year":"2025","journal-title":"J Inflamm Res"},{"issue":"1","key":"pone.0351509.ref015","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1186\/s12931-021-01722-y","article-title":"Nutritional immunity: the impact of metals on lung immune cells and the airway microbiome during chronic respiratory disease","volume":"22","author":"C Healy","year":"2021","journal-title":"Respir Res"},{"issue":"6","key":"pone.0351509.ref016","doi-asserted-by":"crossref","first-page":"2091","DOI":"10.1007\/s10753-022-01680-7","article-title":"The Lactate and the Lactate Dehydrogenase in Inflammatory Diseases and Major Risk Factors in COVID-19 Patients","volume":"45","author":"GS Gupta","year":"2022","journal-title":"Inflammation"},{"issue":"2","key":"pone.0351509.ref017","doi-asserted-by":"crossref","first-page":"278","DOI":"10.1093\/infdis\/jiaa451","article-title":"Reliability of self-sampling for accurate assessment of respiratory virus viral and immunologic kinetics","volume":"226","author":"A Waghmare","year":"2022","journal-title":"J Infect Dis"},{"issue":"6","key":"pone.0351509.ref018","doi-asserted-by":"crossref","first-page":"1105","DOI":"10.1515\/cclm-2022-1077","article-title":"LMS-based continuous reference percentiles for 14 laboratory parameters in the CALIPER cohort of healthy children and adolescents","volume":"61","author":"SM Wilson","year":"2023","journal-title":"Clin Chem Lab Med"},{"issue":"5","key":"pone.0351509.ref019","doi-asserted-by":"crossref","DOI":"10.1016\/j.heliyon.2023.e16068","article-title":"Comparison of linear and non-linear machine learning models for time-dependent readmission or mortality prediction among hospitalized heart failure patients","volume":"9","author":"R Tong","year":"2023","journal-title":"Heliyon"},{"issue":"1","key":"pone.0351509.ref020","article-title":"Applied machine learning for the risk-stratification and clinical decision support of hospitalised patients with dengue in Vietnam","volume":"1","author":"DK Ming","year":"2022","journal-title":"PLOS Digit Health"},{"issue":"1","key":"pone.0351509.ref021","doi-asserted-by":"crossref","first-page":"4419","DOI":"10.1038\/s41598-025-34441-1","article-title":"XGBoost based machine learning prediction model for major adverse cardiovascular events after PCI in STEMI patients","volume":"16","author":"N Zhang","year":"2026","journal-title":"Sci Rep"},{"issue":"6","key":"pone.0351509.ref022","doi-asserted-by":"crossref","first-page":"1146","DOI":"10.1542\/peds.2013-3260","article-title":"Principles of judicious antibiotic prescribing for upper respiratory tract infections in pediatrics","volume":"132","author":"AL Hersh","year":"2013","journal-title":"Pediatrics"},{"issue":"7","key":"pone.0351509.ref023","doi-asserted-by":"crossref","DOI":"10.1093\/cid\/cir625","article-title":"The management of community-acquired pneumonia in infants and children older than 3 months of age: clinical practice guidelines by the Pediatric Infectious Diseases Society and the Infectious Diseases Society of America","volume":"53","author":"JS Bradley","year":"2011","journal-title":"Clin Infect Dis"},{"key":"pone.0351509.ref024","article-title":"Advances in the diagnosis of pneumonia in children","volume":"358","author":"HJ Zar","year":"2017","journal-title":"BMJ"},{"issue":"1","key":"pone.0351509.ref025","doi-asserted-by":"crossref","DOI":"10.1542\/peds.2021-051405","article-title":"A Prediction Model for Pediatric Radiographic Pneumonia","volume":"149","author":"S Ramgopal","year":"2022","journal-title":"Pediatrics"},{"issue":"1","key":"pone.0351509.ref026","doi-asserted-by":"crossref","first-page":"96","DOI":"10.1097\/PCC.0000000000002167","article-title":"Provider Consensus on Factors Affecting Psychosocial Outcomes: A First Step Toward a Multifaceted Approach to Caring for Children and Families After an ICU Stay","volume":"21","author":"W Morrison","year":"2020","journal-title":"Pediatr Crit Care Med"},{"issue":"16","key":"pone.0351509.ref027","doi-asserted-by":"crossref","first-page":"9010","DOI":"10.3390\/ijms25169010","article-title":"Sepsis Biomarkers: Advancements and Clinical Applications-A Narrative Review","volume":"25","author":"R-R He","year":"2024","journal-title":"Int J Mol Sci"},{"key":"pone.0351509.ref028","doi-asserted-by":"crossref","first-page":"1417644","DOI":"10.3389\/fped.2024.1417644","article-title":"Research progress of biomarkers in evaluating the severity and prognostic value of severe pneumonia in children","volume":"12","author":"W Gong","year":"2024","journal-title":"Front Pediatr"},{"key":"pone.0351509.ref029","doi-asserted-by":"crossref","first-page":"1564217","DOI":"10.3389\/fped.2025.1564217","article-title":"Association between Gustave Roussy Immune Score and delay in discharge among children and adolescents with mycoplasma pneumoniae pneumonia: a retrospective cohort study","volume":"13","author":"X Zhou","year":"2025","journal-title":"Front Pediatr"},{"issue":"1","key":"pone.0351509.ref030","doi-asserted-by":"crossref","DOI":"10.1128\/msystems.01335-24","article-title":"Proteomic profiling of the local and systemic immune response to pediatric respiratory viral infections","volume":"10","author":"E Lydon","year":"2025","journal-title":"mSystems"},{"issue":"2","key":"pone.0351509.ref031","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1007\/s40520-020-01775-x","article-title":"Infection, atherothrombosis and thromboembolism beyond the COVID-19 disease: what similar in physiopathology and researches","volume":"33","author":"M Correale","year":"2021","journal-title":"Aging Clin Exp Res"},{"key":"pone.0351509.ref032","article-title":"Predicting Escalation of Care for Childhood Pneumonia Using Machine Learning: Retrospective Analysis and Model Development","volume":"6","author":"O Serin","year":"2025","journal-title":"JMIRx Med"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0351509","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T17:33:33Z","timestamp":1783532013000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0351509"}},"subtitle":[],"editor":[{"given":"Benjamin M.","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,7,8]]},"references-count":32,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2026,7,8]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0351509","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,8]]}}}