{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T14:35:53Z","timestamp":1777905353583,"version":"3.51.4"},"reference-count":40,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T00:00:00Z","timestamp":1769558400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Med."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Childhood pneumonia is a leading cause of hospitalization and death in children under 5 years globally. Its prognosis varies individually and is affected by multiple clinical indicators, while traditional assessment lacks quantitative risk stratification tools. Machine learning (ML) enables comprehensive analysis of high-dimensional clinical data, making it valuable for identifying key prognostic factors and building robust prediction models to optimize clinical decision-making.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      A total of 582 hospitalized children (1 month\u20135 years) with community-acquired pneumonia were retrospectively enrolled (January 2022\u2013June 2025). Demographic, laboratory (WBC, CRP, PCT, LYM%, serum albumin), vital sign, and underlying disease data were collected. Adverse prognosis was defined as a composite of prolonged hospitalization (&amp;gt;7 days), PICU admission, or in-hospital death. Patients were randomly split into training (\n                      <jats:italic>n<\/jats:italic>\n                      = 407) and validation (\n                      <jats:italic>n<\/jats:italic>\n                      = 175) sets (7:3). XGBoost, Random Forest (RF), and Logistic Regression (LR) models were constructed, with performance evaluated by AUC, accuracy, sensitivity, and specificity. Class imbalance was addressed using stratified random sampling during dataset splitting to maintain consistent adverse prognosis rates between training and validation sets. SHAP values analyzed indicator importance. Missing data (all &amp;lt; 5%) were imputed via mean imputation; a sensitivity analysis comparing mean imputation with multiple imputation confirmed no significant impact on model performance.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      Adverse prognosis occurred in 121 (20.8%) children. The XGBoost model outperformed RF and LR, with validation-set AUC 0.84 (95% CI: 0.78\u223c0.90), accuracy 81.1%, sensitivity 78.6%, and specificity 82.3%. Model calibration was verified via Hosmer-Lemeshow test (\n                      <jats:italic>p<\/jats:italic>\n                      = 0.312), indicating good agreement between predicted and observed risks. Top 5 key indicators were admission PCT, CRP, respiratory rate, age &amp;lt; 6 months, and blood oxygen saturation. PCT &amp;gt; 2 ng\/mL (OR = 3.95) and CRP &amp;gt; 40 mg\/L (OR = 3.52) significantly increased adverse prognosis risk. Etiological data (viral, bacterial, mixed infection) were unavailable in 41.2% (240\/582) of cases; among available data (342\/582), 58.5% (200\/342) were viral (including 12 cases of COVID-19), 32.2% (110\/342) bacterial, and 9.3% (32\/342) mixed infections. Sensitivity analysis excluding COVID-19 cases (\n                      <jats:italic>n<\/jats:italic>\n                      = 12) showed no substantial change in model performance (AUC = 0.83, 95% CI: 0.77\u223c0.89).\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The XGBoost-based model effectively identifies high-risk children with pneumonia, with PCT, CRP, and respiratory rate as key predictors. It provides a practical tool for clinical risk stratification and personalized management. The model\u2019s cutoffs for PCT (&amp;gt;2 ng\/mL) and CRP (&amp;gt;40 mg\/L) align with existing pediatric pneumonia predictive scores (e.g., PRIEST score) but offer improved discriminative power by integrating multi-dimensional indicators and ML-driven interactions.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fmed.2026.1747935","type":"journal-article","created":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T06:43:30Z","timestamp":1769582610000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Exploration of the correlation between clinical indicators and prognosis in hospitalized children with pneumonia and construction of a risk prediction model based on machine learning algorithms"],"prefix":"10.3389","volume":"13","author":[{"given":"Jin","family":"Xue","sequence":"first","affiliation":[{"name":"School of Medicine, Shaanxi University of International Trade and Commerce","place":["Xianyang, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guangzhong","family":"He","sequence":"additional","affiliation":[{"name":"School of Medicine, Shaanxi University of International Trade and Commerce","place":["Xianyang, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiaoying","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Medicine, Shaanxi University of International Trade and Commerce","place":["Xianyang, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2026,1,28]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"1129","DOI":"10.1007\/s00431-023-05366-6","article-title":"Childhood community-acquired pneumonia.","volume":"183","author":"Meyer Sauteur","year":"2024","journal-title":"Eur J Pediatr."},{"key":"B2","volume-title":"Guideline on Management of Pneumonia and Diarrhoea in Children up to 10 Years of Age.","year":"2024"},{"key":"B3","doi-asserted-by":"publisher","first-page":"8362","DOI":"10.1016\/j.vaccine.2020.11.004","article-title":"Incidence of community-acquired pneumonia in urban China: a national population-based study.","volume":"38","author":"Sun","year":"2020","journal-title":"Vaccine."},{"key":"B4","doi-asserted-by":"publisher","first-page":"6864","DOI":"10.3390\/jcm12216864","article-title":"Ten issues for updating in community-acquired pneumonia: an expert review.","volume":"12","author":"Candel","year":"2023","journal-title":"J Clin Med."},{"key":"B5","doi-asserted-by":"publisher","first-page":"32347","DOI":"10.1038\/s41598-025-14685-7","article-title":"Epidemiology and co-infection patterns of community-acquired pneumonia among children from 2015 to 2023 in Henan Province, China: longitudinal surveillance study.","volume":"15","author":"Li","year":"2025","journal-title":"Sci Rep."},{"key":"B6","doi-asserted-by":"publisher","first-page":"e47","DOI":"10.1016\/S2214-109X(18)30408-X","article-title":"Global, regional, and national estimates of pneumonia morbidity and mortality in children younger than 5 years between 2000 and 2015: a systematic analysis.","volume":"7","author":"Campbell","year":"2019","journal-title":"Lancet Glob Health."},{"key":"B7","doi-asserted-by":"publisher","first-page":"e208","DOI":"10.1097\/PEC.0000000000001179","article-title":"Assessing severity in pediatric pneumonia: predictors of the need for major medical interventions.","volume":"36","author":"Berg","year":"2020","journal-title":"Pediatr Emerg Care."},{"key":"B8","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1016\/j.prrv.2025.01.002","article-title":"Narrative review of clinical prediction models for paediatric community acquired pneumonia.","volume":"54","author":"Rees","year":"2025","journal-title":"Paediatr Respir Rev."},{"key":"B9","first-page":"1554","article-title":"Machine learning in medical diagnosis and treatment planning.","volume-title":"Proceedings of the 2024 1st International Conference on Advances in Computing, Communication and Networking (ICAC2N).","author":"Sharma","year":"2024"},{"key":"B10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10742-024-00324-7","article-title":"A machine learning approach for diagnostic and prognostic predictions, key risk factors and interactions.","volume":"25","author":"Nasir","year":"2025","journal-title":"Health Serv Outcomes Res Methodol."},{"key":"B11","doi-asserted-by":"publisher","first-page":"200121","DOI":"10.1016\/j.iswa.2022.200121","article-title":"Predictive analysis of cardiovascular disease using gradient boosting based learning and recursive feature elimination technique.","volume":"16","author":"Theerthagiri","year":"2022","journal-title":"Intell Syst Appl."},{"key":"B12","doi-asserted-by":"publisher","first-page":"121549","DOI":"10.1016\/j.eswa.2023.121549","article-title":"An improved random forest based on the classification accuracy and correlation measurement of decision trees.","volume":"237","author":"Sun","year":"2024","journal-title":"Exp Syst Appl."},{"key":"B13","doi-asserted-by":"publisher","first-page":"270","DOI":"10.1186\/s12859-018-2264-5","article-title":"Random forest versus logistic regression: a large-scale benchmark experiment.","volume":"19","author":"Couronn\u00e9","year":"2018","journal-title":"BMC Bioinform."},{"key":"B14","doi-asserted-by":"publisher","first-page":"1582426","DOI":"10.3389\/fmed.2025.1582426","article-title":"Machine learning-based prognostic prediction model of pneumonia-associated acute respiratory distress syndrome.","volume":"12","author":"Lv","year":"2025","journal-title":"Front Med."},{"key":"B15","doi-asserted-by":"publisher","first-page":"3239","DOI":"10.1109\/ICORIS63540.2024.10903882","article-title":"Detection and classification of lung diseases for pneumonia and Covid-19 using machine and deep learning techniques.","volume":"14","author":"Goyal","year":"2023","journal-title":"J Ambient Intell Human Comput."},{"key":"B16","doi-asserted-by":"publisher","first-page":"920","DOI":"10.3760\/cma.j.cn112140-20240728-00523","article-title":"[Guidelines for the management of community-acquired pneumonia in children (2024 revision)].","volume":"62","year":"2024","journal-title":"Zhonghua Er Ke Za Zhi."},{"key":"B17","doi-asserted-by":"publisher","first-page":"18","DOI":"10.25236\/AJMHS.2025.060803","article-title":"Multifactorial model-based risk assessment and predictive biomarker analysis in pediatric severe pneumonia.","volume":"6","author":"Mingcan","year":"2025","journal-title":"Acad J Med Health Sci."},{"key":"B18","doi-asserted-by":"publisher","first-page":"114317","DOI":"10.1016\/j.intimp.2025.114317","article-title":"Assessing severe pneumonia risk in children via clinical prognostic model based on laboratory markers.","volume":"151","author":"Cao","year":"2025","journal-title":"Intern Immunopharmacol."},{"key":"B19","doi-asserted-by":"publisher","first-page":"1538","DOI":"10.21037\/jtd.2017.05.44","article-title":"Discordance of physician clinical judgment vs. pneumonia severity index (PSI) score to admit patients with low risk community-acquired pneumonia: a prospective multicenter study.","volume":"9","author":"Marcos","year":"2017","journal-title":"J Thoracic Dis."},{"key":"B20","doi-asserted-by":"publisher","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":"Gong","year":"2024","journal-title":"Front Pediatr."},{"key":"B21","doi-asserted-by":"publisher","first-page":"6969","DOI":"10.21037\/jtd-24-1417","article-title":"Epidemiological characteristics of severe community-acquired pneumonia in children admitted to two tertiary hospitals in Shihezi, Xinjiang Region, China in 2023: a cross-sectional analysis.","volume":"16","author":"Ma","year":"2024","journal-title":"J Thoracic Dis."},{"key":"B22","doi-asserted-by":"publisher","first-page":"1364854","DOI":"10.3389\/fpubh.2024.1364854","article-title":"Economic burden and influence factors among hospitalized children with bronchiolitis or pneumonia: a multiregional study in China.","volume":"12","author":"Hu","year":"2024","journal-title":"Front Public Health."},{"key":"B23","doi-asserted-by":"publisher","first-page":"e001165","DOI":"10.1136\/bmjresp-2021-001165","article-title":"Implementation of prognostic machine learning algorithms in paediatric chronic respiratory conditions: a scoping review.","volume":"9","author":"Filipow","year":"2022","journal-title":"BMJ Open Respir Res."},{"key":"B24","doi-asserted-by":"publisher","first-page":"822","DOI":"10.1515\/cclm-2022-1072","article-title":"How to best use procalcitonin to diagnose infections and manage antibiotic treatment.","volume":"61","author":"Schuetz","year":"2023","journal-title":"Clin Chem Lab Med (CCLM)."},{"key":"B25","doi-asserted-by":"publisher","first-page":"e13013","DOI":"10.7717\/peerj.13013","article-title":"Reliability and validity of the multi-point method and the 2-point method\u2019s variations of estimating the one-repetition maximum for deadlift and back squat exercises.","volume":"10","author":"\u00c7etin","year":"2022","journal-title":"PeerJ."},{"key":"B26","doi-asserted-by":"publisher","first-page":"e1851","DOI":"10.1128\/JCM.01851-19","article-title":"Utility of procalcitonin as a biomarker for sepsis in children.","volume":"58","author":"Downes","year":"2020","journal-title":"J Clin Microbiol."},{"key":"B27","doi-asserted-by":"publisher","first-page":"236","DOI":"10.1056\/NEJMoa1802670","article-title":"Procalcitonin-Guided use of antibiotics for lower respiratory tract infection.","volume":"379","author":"Huang","year":"2018","journal-title":"New Engl J Med."},{"key":"B28","doi-asserted-by":"publisher","first-page":"e0277401","DOI":"10.1371\/journal.pone.0277401","article-title":"Differentiating between bacterial and viral infections by estimated CRP velocity.","volume":"17","author":"Largman-Chalamish","year":"2022","journal-title":"PLoS One."},{"key":"B29","doi-asserted-by":"publisher","first-page":"e084144","DOI":"10.1136\/bmjopen-2024-084144","article-title":"Cost-effectiveness of C-reactive protein point of care testing for safely reducing antibiotic consumption for acute exacerbations of chronic obstructive pulmonary disease as part of the multicentre, parallel-arm, open, individually randomised, controlled PACE trial.","volume":"14","author":"Sewell","year":"2024","journal-title":"BMJ Open."},{"key":"B30","doi-asserted-by":"publisher","first-page":"386","DOI":"10.1186\/s12890-021-01756-4","article-title":"Usefulness of procalcitonin (PCT), C-reactive protein (CRP), and white blood cell (WBC) levels in the differential diagnosis of acute bacterial, viral, and mycoplasmal respiratory tract infections in children.","volume":"21","author":"Li","year":"2021","journal-title":"BMC Pulmonary Med."},{"key":"B31","doi-asserted-by":"publisher","first-page":"2041","DOI":"10.1002\/ppul.24853","article-title":"Respiratory rate is an early predictor of clinical deterioration in children.","volume":"55","author":"Daw","year":"2020","journal-title":"Pediatr Pulmonol."},{"key":"B32","doi-asserted-by":"publisher","first-page":"e0303888","DOI":"10.1371\/journal.pone.0303888","article-title":"The contribution of energy systems during 30-second lower body Wingate anaerobic test in combat sports athletes: intermittent versus single forms and gender comparison.","volume":"19","author":"Tortu","year":"2024","journal-title":"PLoS One."},{"key":"B33","doi-asserted-by":"publisher","first-page":"766","DOI":"10.4103\/ijpm.ijpm_700_23","article-title":"Pediatric pneumonia\u2013A clinico-pathological study.","volume":"67","author":"Sathe","year":"2024","journal-title":"Ind J Pathol Microbiol."},{"key":"B34","doi-asserted-by":"publisher","first-page":"267","DOI":"10.1053\/j.ro.2024.03.001","article-title":"Respiratory distress in children: review and update of imaging assessment.","volume":"59","author":"Lee","year":"2024","journal-title":"Sem Roentgenol."},{"key":"B35","doi-asserted-by":"publisher","first-page":"641","DOI":"10.1016\/j.jaip.2020.11.016","article-title":"The influence of immune immaturity on outcome after virus infections.","volume":"9","author":"Shaw","year":"2021","journal-title":"J Allergy Clin Immunol Pract."},{"key":"B36","doi-asserted-by":"publisher","first-page":"e348","DOI":"10.1016\/S2214-109X(21)00586-6","article-title":"Prevalence of hypoxaemia in children with pneumonia in low-income and middle-income countries: a systematic review and meta-analysis.","volume":"10","author":"Rahman","year":"2022","journal-title":"Lancet Glob Health."},{"key":"B37","doi-asserted-by":"publisher","first-page":"1024","DOI":"10.1007\/s13312-021-2367-3","article-title":"Role of clinical criteria and Oxygen saturation monitoring in diagnosis of childhood pneumonia in children aged 2 to 59 months.","volume":"58","author":"Das","year":"2021","journal-title":"Ind Pediatr."},{"key":"B38","doi-asserted-by":"crossref","first-page":"785","DOI":"10.1145\/2939672.2939785","article-title":"Xgboost: a scalable tree boosting system.","volume-title":"Proceedings of the 22nd ACM Sigkdd International Conference on Knowledge Discovery and Data Mining.","author":"Chen","year":"2016"},{"key":"B39","doi-asserted-by":"publisher","first-page":"e37367","DOI":"10.1016\/j.heliyon.2024.e37367","article-title":"Development and validation of machine learning-based prediction model for severe pneumonia: a multicenter cohort study.","volume":"10","author":"Yang","year":"2024","journal-title":"Heliyon."},{"key":"B40","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-16399-0","article-title":"Clinical prediction models: a practical approach to development, validation, and updating.","volume-title":"Springer Series Statistics for Biology and Health.","author":"Steyerberg","year":"2019"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1747935\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T06:43:32Z","timestamp":1769582612000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1747935\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,28]]},"references-count":40,"alternative-id":["10.3389\/fmed.2026.1747935"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2026.1747935","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,28]]},"article-number":"1747935"}}