{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T06:05:10Z","timestamp":1780380310846,"version":"3.54.1"},"reference-count":47,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T00:00:00Z","timestamp":1780358400000},"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. Pharmacol."],"abstract":"<jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>Linezolid is a crucial agent for treating drug-resistant Gram-positive bacterial infections in critically ill pediatric patients. However, its pharmacokinetics exhibit high inter-individual variability, making standard dosing regimens susceptible to underexposure or overexposure. This study aimed to explore the integration of population pharmacokinetics (PopPK) and machine learning (ML) algorithms to build a best-performing model for predicting individual linezolid plasma concentrations in critically ill children, thereby guiding personalized dosing.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Based on data from a retrospective cohort of 145 critically ill pediatric patients (213 samples), 32 features (including PK parameters) and the target variable (linezolid plasma concentration) were included. A PopPK model was established, and Monte Carlo simulations were conducted to optimize dosing regimens. After systematically evaluating 7\u00a0ML algorithms, the best predictive model was identified. Its interpretation was then performed with SHapley Additive exPlanations (SHAP).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      A one-compartment model with first-order elimination adequately described the pharmacokinetics of linezolid. Monte Carlo simulations for minimum inhibitory concentration (MIC) values between 0.5 and 2\u00a0mg\/L, most renal function levels achieved a probability of target attainment (PTA) &amp;gt; 90% through dose adjustments. When MIC reached 4\u00a0mg\/L, a PTA &amp;gt; 90% was achieved only in patients with severe renal impairment using 20\u00a0mg\/kg q8h, yet with high safety risk, indicating the need for alternative antimicrobial agents. The LightGBM algorithm was best-performing among the seven algorithms evaluated, with testing set R\n                      <jats:sup>2<\/jats:sup>\n                      = 0.777 and external validation set R\n                      <jats:sup>2<\/jats:sup>\n                      = 0.686. However, these R\n                      <jats:sup>2<\/jats:sup>\n                      values were optimistic, biased estimates inflated by the EBE-derived CL and V, which have been estimated using all available concentrations per patient, rather than conventional predictive performance. SHAP analysis revealed that clearance, time after dose, daily dose, weight, and serum creatinine were the top five most important features.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>This exploratory study integrated PK parameters into ML models for predicting linezolid plasma concentrations in critically ill pediatric patients, providing preliminary insights for future research as a proof of concept. However, the reported metrics could not support clinical deployment without leakage-free re-estimation using time-constrained or sequential validation.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fphar.2026.1817282","type":"journal-article","created":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T05:41:58Z","timestamp":1780378918000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Machine learning combined with population pharmacokinetics: a hybrid model for predicting the plasma concentration of linezolid in critically ill pediatric patients"],"prefix":"10.3389","volume":"17","author":[{"given":"Yanping","family":"Zhang","sequence":"first","affiliation":[{"name":"Department of Clinical Pharmacy, Children\u2019s Hospital of Fudan University, National Children\u2019s Medical Center","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lin","family":"Zhu","sequence":"additional","affiliation":[{"name":"Department of Clinical Pharmacy, Children\u2019s Hospital of Fudan University, National Children\u2019s Medical Center","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Shen","sequence":"additional","affiliation":[{"name":"Department of Clinical Pharmacy, Children\u2019s Hospital of Fudan University, National Children\u2019s Medical Center","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guangfei","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Clinical Pharmacy, Children\u2019s Hospital of Fudan University, National Children\u2019s Medical Center","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junqi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Clinical Pharmacy, Children\u2019s Hospital of Fudan University, National Children\u2019s Medical Center","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Clinical Pharmacy, Children\u2019s Hospital of Fudan University, National Children\u2019s Medical Center","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Neurology, Children\u2019s Hospital of Fudan University, National Children\u2019s Medical Center","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiping","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Clinical Pharmacy, Children\u2019s Hospital of Fudan University, National Children\u2019s Medical Center","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,6,2]]},"reference":[{"key":"B1","doi-asserted-by":"crossref","first-page":"1127","DOI":"10.1007\/s00134-020-06050-1","article-title":"Antimicrobial therapeutic drug monitoring in critically ill adult patients: a position paper","volume":"46","author":"Abdul-Aziz","year":"2020","journal-title":"Intensive Care Med."},{"key":"B2","doi-asserted-by":"publisher","first-page":"7432","DOI":"10.3390\/ma15217432","article-title":"Prediction of ecofriendly concrete compressive strength using gradient boosting regression tree combined with GridSearchCV hyperparameter-optimization techniques","volume":"15","author":"Alhakeem","year":"2022","journal-title":"Materials"},{"key":"B3","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1007\/s40262-021-01050-w","article-title":"An update on population pharmacokinetic analyses of vancomycin, part II: in pediatric patients","volume":"61","author":"Aljutayli","year":"2022","journal-title":"Clin. Pharmacokinet."},{"key":"B4","doi-asserted-by":"publisher","first-page":"259","DOI":"10.3390\/pharmaceutics11060259","article-title":"Application of size and maturation functions to population pharmacokinetic modeling of pediatric patients","volume":"11","author":"Back","year":"2019","journal-title":"Pharmaceutics"},{"key":"B5","doi-asserted-by":"publisher","first-page":"789","DOI":"10.1007\/s40262-022-01125-2","article-title":"A review of population pharmacokinetic analyses of linezolid","volume":"61","author":"Band\u00edn-Vilar","year":"2022","journal-title":"Clin. Pharmacokinet."},{"key":"B6","doi-asserted-by":"publisher","first-page":"481","DOI":"10.1023\/a:1012299115260","article-title":"Ways to fit a PK model with some data below the quantification limit","volume":"28","author":"Beal","year":"2001","journal-title":"J. Pharmacokinet. Pharmacodyn."},{"key":"B7","doi-asserted-by":"publisher","first-page":"e0049925","DOI":"10.1128\/spectrum.00499-25","article-title":"Machine learning and population pharmacokinetics: a hybrid approach for optimizing vancomycin therapy in sepsis patients","volume":"13","author":"Chen","year":"2025","journal-title":"Microbiol. Spectr."},{"key":"B8","doi-asserted-by":"publisher","first-page":"1975","DOI":"10.1016\/S0140-6736(01)06964-1","article-title":"Oxazolidinone antibiotics","volume":"358","author":"Diekema","year":"2001","journal-title":"Lancet (Lond. Engl.)"},{"key":"B9","doi-asserted-by":"publisher","first-page":"439","DOI":"10.1097\/MCC.0000000000001187","article-title":"Antibiotic dose optimisation in the critically ill: targets, evidence and future strategies","volume":"30","author":"Dyer","year":"2024","journal-title":"Curr. Opin. Crit. Care"},{"key":"B10","doi-asserted-by":"publisher","first-page":"101","DOI":"10.12793\/tcp.2017.25.2.101","article-title":"Relationship between body weight and postmenstrual age in a Korean pediatric population","volume":"25","author":"Guk","year":"2017","journal-title":"Transl. Clin. Pharmacol."},{"key":"B11","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1007\/s00228-022-03446-4","article-title":"Linezolid pharmacokinetics: a systematic review for the best clinical practice","volume":"79","author":"Heidari","year":"2023","journal-title":"Eur. J. Clin. Pharmacol."},{"key":"B12","doi-asserted-by":"publisher","first-page":"745","DOI":"10.1016\/j.ijantimicag.2018.01.021","article-title":"Population pharmacokinetics\/pharmacodynamics of linezolid in sepsis patients with and without continuous renal replacement therapy","volume":"51","author":"Ide","year":"2018","journal-title":"Int. J. Antimicrob. Agents"},{"key":"B13","doi-asserted-by":"publisher","first-page":"272","DOI":"10.1093\/jpids\/piu035","article-title":"Linezolid-associated thrombocytopenia in children with renal impairment","volume":"4","author":"Jones","year":"2015","journal-title":"J. Pediatr. Infect. Dis. Soc."},{"key":"B14","doi-asserted-by":"publisher","first-page":"S153","DOI":"10.1097\/01.inf.0000086954.43010.63","article-title":"Linezolid pharmacokinetics in pediatric patients: an overview","volume":"22","author":"Jungbluth","year":"2003","journal-title":"Pediatr. Infect. Dis. J."},{"key":"B15","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1056\/NEJMoa1611391","article-title":"Epidemiology of acute kidney injury in critically ill children and young adults","volume":"376","author":"Kaddourah","year":"2017","journal-title":"N. Engl. J. Med."},{"key":"B16","doi-asserted-by":"publisher","first-page":"e00131","DOI":"10.1002\/prp2.131","article-title":"Incorporation of concentration data below the limit of quantification in population pharmacokinetic analyses","volume":"3","author":"Keizer","year":"2015","journal-title":"Pharmacol. Res. Perspect."},{"key":"B17","doi-asserted-by":"publisher","first-page":"1530","DOI":"10.3390\/pharmaceutics14081530","article-title":"Machine learning and pharmacometrics for prediction of pharmacokinetic data: differences, similarities and challenges illustrated with rifampicin","volume":"14","author":"Keutzer","year":"2022","journal-title":"Pharmaceutics"},{"key":"B18","doi-asserted-by":"publisher","first-page":"e02387-18","DOI":"10.1128\/AAC.02387-18","article-title":"Population pharmacokinetics and dosing optimization of linezolid in pediatric patients","volume":"63","author":"Li","year":"2019","journal-title":"Antimicrob. Agents Chemother."},{"key":"B19","doi-asserted-by":"publisher","first-page":"110782","DOI":"10.1016\/j.compbiomed.2025.110782","article-title":"Machine learning-assisted tacrolimus dose optimization in childhood- onset systemic lupus erythematosus through population pharmacokinetic modeling","volume":"196","author":"Liang","year":"2025","journal-title":"Comput. Biol. Med."},{"key":"B20","doi-asserted-by":"publisher","first-page":"149","DOI":"10.1007\/s00228-022-03427-7","article-title":"A standard dose of linezolid puts patients with hepatic impairment at risk of overexposure","volume":"79","author":"Liao","year":"2023","journal-title":"Eur. J. Clin. Pharmacol."},{"key":"B21","doi-asserted-by":"publisher","first-page":"967311","DOI":"10.3389\/fpubh.2022.967311","article-title":"Expert consensus statement on therapeutic drug monitoring and individualization of linezolid","volume":"10","author":"Lin","year":"2022","journal-title":"Front. Public Health"},{"key":"B22","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1186\/s40360-022-00628-9","article-title":"Safety of linezolid in patients with decreased renal function and trough monitoring: a systematic review and meta-analysis","volume":"23","author":"Liu","year":"2022","journal-title":"BMC Pharmacol. Toxicol."},{"key":"B23","doi-asserted-by":"publisher","first-page":"4021","DOI":"10.2147\/DDDT.S495050","article-title":"A real-time plasma concentration prediction model for voriconazole in elderly patients via machine learning combined with population pharmacokinetics","volume":"19","author":"Liu","year":"2025","journal-title":"Drug Des. Devel Ther."},{"key":"B24","doi-asserted-by":"publisher","first-page":"419","DOI":"10.2165\/00128072-200305060-00009","article-title":"Linezolid: in infants and children with severe gram-positive infections","volume":"5","author":"Lyseng-Williamson","year":"2003","journal-title":"Pediatr. Drugs"},{"key":"B25","doi-asserted-by":"publisher","first-page":"27165","DOI":"10.1038\/s41598-024-78558-1","article-title":"Prediction of vancomycin plasma concentration in elderly patients based on multi-algorithm mining combined with population pharmacokinetics","volume":"14","author":"Ma","year":"2024","journal-title":"Sci. Rep."},{"key":"B26","doi-asserted-by":"publisher","first-page":"253","DOI":"10.3390\/pharmaceutics16020253","article-title":"Population pharmacokinetic model of linezolid and probability of target attainment in patients with COVID-19-associated acute respiratory distress syndrome on veno-venous extracorporeal membrane oxygenation-a step toward correct dosing","volume":"16","author":"Milakovi\u0107","year":"2024","journal-title":"Pharmaceutics"},{"key":"B27","doi-asserted-by":"publisher","first-page":"115421","DOI":"10.1016\/j.addr.2024.115421","article-title":"Model-informed precision dosing: state of the art and future perspectives","volume":"215","author":"Minichmayr","year":"2024","journal-title":"Adv. Drug Deliv. Rev."},{"key":"B28","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1007\/s40262-023-01213-x","article-title":"Pharmacokinetic alterations associated with critical illness","volume":"62","author":"Morales Castro","year":"2023","journal-title":"Clin. Pharmacokinet."},{"key":"B29","doi-asserted-by":"publisher","first-page":"e6","DOI":"10.1038\/psp.2012.4","article-title":"Basic concepts in population modeling, simulation, and model-based drug development","volume":"1","author":"Mould","year":"2012","journal-title":"CPT Pharmacometrics Syst. Pharmacol."},{"key":"B30","volume-title":"CLSI M100","year":"2026"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.1210\/clinem\/dgaf487","article-title":"ML prediction of recurrence in pediatric thyroid cancer: MET cohort analysis using XGBoost and SHAP","author":"Redlich","year":"2026","journal-title":"J. Clin. Endocrinol. Metab."},{"key":"B32","doi-asserted-by":"publisher","first-page":"851","DOI":"10.1002\/phar.2617","article-title":"Scoping review of augmented renal clearance in critically ill pediatric patients","volume":"41","author":"Rhoney","year":"2021","journal-title":"Pharmacotherapy"},{"key":"B33","doi-asserted-by":"publisher","first-page":"629","DOI":"10.1111\/bcp.15930","article-title":"Artificial intelligence and machine learning for clinical pharmacology","volume":"90","author":"Ryan","year":"2024","journal-title":"Br. J. Clin. Pharmacol."},{"key":"B34","doi-asserted-by":"publisher","first-page":"665","DOI":"10.1001\/jama.2024.0179","article-title":"International consensus criteria for pediatric sepsis and septic shock","volume":"331","author":"Schlapbach","year":"2024","journal-title":"JAMA"},{"key":"B35","doi-asserted-by":"publisher","first-page":"849","DOI":"10.1016\/s0022-3476(84)80479-5","article-title":"A simple estimate of glomerular filtration rate in full-term infants during the first year of life","volume":"104","author":"Schwartz","year":"1984","journal-title":"J. Pediatr."},{"key":"B36","doi-asserted-by":"publisher","first-page":"629","DOI":"10.1681\/ASN.2008030287","article-title":"New equations to estimate GFR in children with CKD","volume":"20","author":"Schwartz","year":"2009","journal-title":"J. Am. Soc. Nephrol."},{"key":"B37","doi-asserted-by":"publisher","first-page":"1671652","DOI":"10.3389\/fphar.2025.1671652","article-title":"Precision dosing of voriconazole in immunocompromised children under 2 years: integrated machine learning and population pharmacokinetic modeling","volume":"16","author":"Shen","year":"2025","journal-title":"Front. Pharmacol."},{"key":"B38","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1186\/s12874-019-0681-4","article-title":"Machine learning in medicine: a practical introduction","volume":"19","author":"Sidey-Gibbons","year":"2019","journal-title":"BMC Med. Res. Methodol."},{"key":"B39","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.coph.2015.06.002","article-title":"Augmented renal clearance in critically ill patients: etiology, definition and implications for beta-lactam dose optimization","volume":"24","author":"Sime","year":"2015","journal-title":"Curr. Opin. Pharmacol."},{"key":"B40","doi-asserted-by":"publisher","first-page":"105221","DOI":"10.1016\/j.ebiom.2024.105221","article-title":"Optimal use of \u03b2-lactams in neonates: machine learning-based clinical decision support system","volume":"105","author":"Tang","year":"2024","journal-title":"EBioMedicine"},{"key":"B41","doi-asserted-by":"publisher","first-page":"e0129924","DOI":"10.1128\/aac.01299-24","article-title":"Population pharmacokinetics and clinical assessment of linezolid in pediatric bacterial infections","volume":"69","author":"Tian","year":"2025","journal-title":"Antimicrob. Agents Chemother."},{"key":"B42","doi-asserted-by":"publisher","first-page":"105578","DOI":"10.1016\/j.phrs.2021.105578","article-title":"Estimation of drug exposure by machine learning based on simulations from published pharmacokinetic models: the example of tacrolimus","volume":"167","author":"Woillard","year":"2021","journal-title":"Pharmacol. Res."},{"key":"B43","doi-asserted-by":"publisher","first-page":"e02504-20","DOI":"10.1128\/AAC.02504-20","article-title":"Population pharmacokinetics and dosage optimization of linezolid in critically ill pediatric patients","volume":"95","author":"Yang","year":"2021","journal-title":"Antimicrob. Agents Chemother."},{"key":"B44","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1007\/s11095-025-03817-3","article-title":"Prediction trough concentrations of valproic acid among Chinese adult patients with epilepsy using machine learning techniques","volume":"42","author":"Yao","year":"2025","journal-title":"Pharm. Res."},{"key":"B45","doi-asserted-by":"publisher","first-page":"e70346","DOI":"10.1111\/cts.70346","article-title":"Population pharmacokinetic model\u2010based optimization of linezolid dosing in hematooncological patients with suspected or proven gram\u2010positive sepsis","volume":"18","author":"Zav\u0159elov\u00e1","year":"2025","journal-title":"Clin. Transl. Sci."},{"key":"B46","doi-asserted-by":"publisher","first-page":"4150","DOI":"10.1021\/acs.jcim.9b00633","article-title":"LightGBM: an effective and scalable algorithm for prediction of chemical toxicity\u2013application to the Tox21 and mutagenicity data sets","volume":"59","author":"Zhang","year":"2019","journal-title":"J. Chem. Inf. Model."},{"key":"B47","doi-asserted-by":"publisher","first-page":"1612369","DOI":"10.3389\/fnut.2025.1612369","article-title":"Machine learning and SHAP value interpretation for predicting cardiovascular disease risk in patients with diabetes using dietary antioxidants","volume":"12","author":"Zhang","year":"2025","journal-title":"Front. Nutr."}],"container-title":["Frontiers in Pharmacology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fphar.2026.1817282\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T05:42:00Z","timestamp":1780378920000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fphar.2026.1817282\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,2]]},"references-count":47,"alternative-id":["10.3389\/fphar.2026.1817282"],"URL":"https:\/\/doi.org\/10.3389\/fphar.2026.1817282","relation":{},"ISSN":["1663-9812"],"issn-type":[{"value":"1663-9812","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,2]]},"article-number":"1817282"}}