{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T08:06:54Z","timestamp":1790237214085,"version":"4.1.0"},"reference-count":45,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2024,12,18]],"date-time":"2024-12-18T00:00:00Z","timestamp":1734480000000},"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>Aims<\/jats:title>\n                    <jats:p>Few personalized monitoring models for valproic acid (VPA) in pediatric epilepsy patients (PEPs) incorporate machine learning (ML) algorithms. This study aimed to develop an ensemble ML model for VPA monitoring to enhance clinical precision of VPA usage.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      A dataset comprising 366 VPA trough concentrations from 252 PEPs, along with 19 covariates and the target variable (VPA trough concentration), was refined by Spearman correlation and multicollinearity testing (366 \u00d7 11). The dataset was split into a training set (292) and testing set (74) at a ratio of 8:2. An ensemble model was formulated by Gradient Boosting Regression Trees (GBRT), Random Forest Regression (RFR), and Support Vector Regression (SVR), and assessed by SHapley Additive exPlanations (SHAP) analysis for covariate importance. The model was optimized for R\n                      <jats:sup>2<\/jats:sup>\n                      , relative accuracy, and absolute accuracy, and validated against two independent external datasets (32 in-hospital and 28 out-of-hospital dataset).\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      Using the R\n                      <jats:sup>2<\/jats:sup>\n                      weight ratio of GBRT, RFR and SVR optimized at 5:2:3, the ensemble model demonstrated superior performance in terms of relative accuracy (87.8%), absolute accuracy (78.4%), and R\n                      <jats:sup>2<\/jats:sup>\n                      (0.50), while also exhibiting a lower Mean Absolute Error (9.87) and Root Mean Squared Error (12.24), as validated by the external datasets. Platelet count (PLT) and VPA daily dose were identified as pivotal covariates.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The proposed ensemble model effectively monitors VPA trough concentrations in PEPs. By integrating covariates across various ML algorithms, it delivers results closely aligned with clinical practice, offering substantial clinical value for the guided use of VPA.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fphar.2024.1521932","type":"journal-article","created":{"date-parts":[[2024,12,18]],"date-time":"2024-12-18T01:47:32Z","timestamp":1734486452000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["Monitoring of the trough concentration of valproic acid in pediatric epilepsy patients: a machine learning-based ensemble model"],"prefix":"10.3389","volume":"15","author":[{"given":"Yue-Wen","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xi-Kai","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Si","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ya-Lan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chen","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Rao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zong-Xing","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhou-Jie","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2024,12,18]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1097\/00043426-200001000-00012","article-title":"Hematologic toxicity of sodium valproate","volume":"22","author":"Acharya","year":"2000","journal-title":"J. Pediatr. Hematol. Oncol."},{"key":"B2","doi-asserted-by":"publisher","first-page":"182","DOI":"10.1212\/wnl.48.1.182","article-title":"Safety and efficacy of divalproex sodium monotherapy in partial epilepsy: a double-blind, concentration-response design clinical trial. Depakote Monotherapy for Partial Seizures Study Group","volume":"48","author":"Beydoun","year":"1997","journal-title":"Neurology"},{"key":"B3","doi-asserted-by":"publisher","first-page":"110","DOI":"10.1016\/j.seizure.2011.10.002","article-title":"Simultaneous determination of valproic acid and 2-propyl-4-pentenoic acid for the prediction of clinical adverse effects in Chinese patients with epilepsy","volume":"21","author":"Chen","year":"2012","journal-title":"Seizure"},{"key":"B4","doi-asserted-by":"publisher","first-page":"106506","DOI":"10.1016\/j.ejps.2023.106506","article-title":"Prediction of plasma trough concentration of voriconazole in adult patients using machine learning","volume":"188","author":"Cheng","year":"2023","journal-title":"Eur. J. Pharm. Sci."},{"key":"B5","doi-asserted-by":"publisher","first-page":"316","DOI":"10.1016\/S1474-4422(21)00023-5","article-title":"Epilepsy in China: major progress in the past two decades","volume":"20","author":"Ding","year":"2021","journal-title":"Lancet Neurol."},{"key":"B6","doi-asserted-by":"publisher","first-page":"301","DOI":"10.1007\/s12028-018-0627-4","article-title":"Accuracy of valproic acid concentration correction based on serum albumin","volume":"30","author":"Drisaldi","year":"2019","journal-title":"Neurocrit Care"},{"key":"B7","doi-asserted-by":"publisher","first-page":"1070","DOI":"10.1093\/jaoacint\/qsac146","article-title":"A novel approach for therapeutic drug monitoring of valproic acid using FT-IR spectroscopy and nonlinear support vector regression","volume":"106","author":"El Orche","year":"2023","journal-title":"J. AOAC Int."},{"key":"B8","doi-asserted-by":"publisher","first-page":"1289673","DOI":"10.3389\/fphar.2024.1289673","article-title":"Machine learning-based prediction of sertraline concentration in patients with depression through therapeutic drug monitoring","volume":"15","author":"Fu","year":"2024","journal-title":"Front. Pharmacol."},{"key":"B9","doi-asserted-by":"publisher","first-page":"236","DOI":"10.1097\/fpc.0b013e32835ea0b2","article-title":"Valproic acid pathway: pharmacokinetics and pharmacodynamics","volume":"23","author":"Ghodke-Puranik","year":"2013","journal-title":"Pharmacogenet Genomics"},{"key":"B10","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1016\/j.neurol.2011.02.035","article-title":"Relationship between plasma concentrations of valproic acid and hepatotoxicity in patients receiving high doses","volume":"167","author":"Ghozzi","year":"2011","journal-title":"Rev. Neurol. Paris."},{"key":"B11","doi-asserted-by":"publisher","first-page":"551","DOI":"10.1111\/epi.12074","article-title":"Updated ILAE evidence review of antiepileptic drug efficacy and effectiveness as initial monotherapy for epileptic seizures and syndromes","volume":"54","author":"Glauser","year":"2013","journal-title":"Epilepsia"},{"key":"B12","doi-asserted-by":"publisher","first-page":"999","DOI":"10.1007\/s00228-020-03080-y","article-title":"Population pharmacokinetics of unbound valproic acid in pediatric epilepsy patients in China: a protein binding model","volume":"77","author":"Gu","year":"2021","journal-title":"Eur. J. Clin. Pharmacol."},{"key":"B13","doi-asserted-by":"publisher","first-page":"1775","DOI":"10.3390\/children10111775","article-title":"Analysis of adverse drug reactions in pediatric patients with epilepsy: an intensive pharmacovigilance study","volume":"10","author":"Hern\u00e1ndez Garc\u00eda","year":"2023","journal-title":"Child. (Basel)"},{"key":"B14","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1016\/j.jad.2023.11.047","article-title":"Valproic acid monitoring: serum prediction using a machine learning framework from multicenter real-world data","volume":"347","author":"Hsu","year":"2024","journal-title":"J. Affect Disord."},{"key":"B15","doi-asserted-by":"publisher","first-page":"1549","DOI":"10.2147\/DDDT.S299037","article-title":"An ensemble model for prediction of vancomycin trough concentrations in pediatric patients","volume":"15","author":"Huang","year":"2021","journal-title":"Drug Des. Devel Ther."},{"key":"B16","doi-asserted-by":"publisher","first-page":"929","DOI":"10.1586\/14737175.8.6.929","article-title":"Value of therapeutic drug monitoring in epilepsy","volume":"8","author":"Johannessen","year":"2008","journal-title":"Expert Rev. Neurother."},{"key":"B17","doi-asserted-by":"publisher","first-page":"744","DOI":"10.1097\/ftd.0000000000000781","article-title":"Pharmacokinetic variability during long-term therapeutic drug monitoring of valproate, clobazam, and levetiracetam in patients with dravet syndrome","volume":"42","author":"Johannessen Landmark","year":"2020","journal-title":"Ther. Drug Monit."},{"key":"B18","doi-asserted-by":"publisher","first-page":"1157","DOI":"10.1056\/nejmra035092","article-title":"Developmental pharmacology--drug disposition, action, and therapy in infants and children","volume":"349","author":"Kearns","year":"2003","journal-title":"N. Engl. J. Med."},{"key":"B19","doi-asserted-by":"publisher","first-page":"1131","DOI":"10.1007\/s00467-013-2512-x","article-title":"The effects of sodium valproate on the renal function of children with epilepsy","volume":"29","author":"Knights","year":"2014","journal-title":"Pediatr. Nephrol."},{"key":"B20","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1016\/j.pediatrneurol.2019.04.019","article-title":"Valproic acid-induced coagulopathy","volume":"98","author":"Kumar","year":"2019","journal-title":"Pediatr. Neurol."},{"key":"B21","doi-asserted-by":"publisher","first-page":"S98","DOI":"10.1093\/ajcp\/aqab191.208","article-title":"Valproic acid induced thrombocytopenia and dysmegakaryopoiesis in a pediatric patient","volume":"156","author":"Langlie","year":"2022","journal-title":"Am. J. Clin. Pathol."},{"key":"B22","doi-asserted-by":"publisher","first-page":"2315298","DOI":"10.1080\/0886022X.2024.2315298","article-title":"Machine learning algorithm for predict the in-hospital mortality in critically ill patients with congestive heart failure combined with chronic kidney disease","volume":"46","author":"Li","year":"2024","journal-title":"Ren. Fail"},{"key":"B23","doi-asserted-by":"publisher","first-page":"2640","DOI":"10.1111\/epi.17058","article-title":"Epilepsy centers in China: current status and ways forward","volume":"62","author":"Lin","year":"2021","journal-title":"Epilepsia"},{"key":"B24","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1002\/epi4.12686","article-title":"Status of epilepsy in the tropics: an overlooked perspective","volume":"8","author":"Liu","year":"2023","journal-title":"Epilepsia Open"},{"key":"B25","doi-asserted-by":"publisher","first-page":"775","DOI":"10.11817\/j.issn.1672-7347.2019.180548","article-title":"Association of valproic acid and 2-propyl-4-pentenoic acid concentrations with adverse reaction in 254 Chinese patients with epilepsy","volume":"44","author":"Ma","year":"2019","journal-title":"Zhong Nan Da Xue Xue Bao Yi Xue Ban."},{"key":"B26","doi-asserted-by":"publisher","first-page":"808969","DOI":"10.3389\/fmed.2022.808969","article-title":"Construction and interpretation of prediction model of teicoplanin trough concentration via machine learning","volume":"9","author":"Ma","year":"2022","journal-title":"Front. Med. (Lausanne)"},{"key":"B28","doi-asserted-by":"publisher","first-page":"2082","DOI":"10.1345\/aph.1M296","article-title":"The effect of carbapenem antibiotics on plasma concentrations of valproic acid","volume":"43","author":"Mancl","year":"2009","journal-title":"Ann. Pharmacother."},{"key":"B29","doi-asserted-by":"publisher","first-page":"1016399","DOI":"10.3389\/fphar.2022.1016399","article-title":"Applying machine learning to the pharmacokinetic modeling of cyclosporine in adult renal transplant recipients: a multi-method comparison","volume":"13","author":"Mao","year":"2022","journal-title":"Front. Pharmacol."},{"key":"B30","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1186\/1824-7288-37-21","article-title":"Renal tubular dysfunction measured by N-acetyl-beta glucosaminidase\/Creatinine activity index in children receiving antiepileptic drugs: a randomized controlled trial","volume":"37","author":"Mazaheri","year":"2011","journal-title":"Ital. J. Pediatr."},{"key":"B31","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1016\/j.seizure.2021.11.018","article-title":"Predicting the occurrence of thrombocytopenia from free valproate levels: a prospective study","volume":"94","author":"Nasreddine","year":"2022","journal-title":"Seizure"},{"key":"B32","doi-asserted-by":"publisher","first-page":"438","DOI":"10.1111\/j.1528-1167.2007.01429.x","article-title":"Valproate-induced thrombocytopenia: a prospective monotherapy study","volume":"49","author":"Nasreddine","year":"2008","journal-title":"Epilepsia"},{"key":"B33","doi-asserted-by":"publisher","first-page":"108856","DOI":"10.1016\/j.compbiomed.2024.108856","article-title":"Optimizing trigger timing in minimal ovarian stimulation for in vitro fertilization using machine learning models with random search hyperparameter tuning","volume":"179","author":"P\u00e9rez-Padilla","year":"2024","journal-title":"Comput. Biol. Med."},{"key":"B34","doi-asserted-by":"publisher","first-page":"28","DOI":"10.22146\/ijbiotech.52621","article-title":"Enhancement of transient erythropoietin protein expression by valproic acid in CHO-K1 suspension adapted cells","volume":"25","author":"Rubiyana","year":"2020","journal-title":"Indonesian J. Biotechnol."},{"key":"B35","doi-asserted-by":"publisher","first-page":"738","DOI":"10.1097\/FTD.0000000000001020","article-title":"Estimation of mycophenolic acid exposure in Chinese renal transplant patients by a joint deep learning model","volume":"44","author":"Shao","year":"2022","journal-title":"Ther. Drug Monit."},{"key":"B36","doi-asserted-by":"publisher","first-page":"205","DOI":"10.1007\/s10545-008-0841-x","article-title":"Valproic acid metabolism and its effects on mitochondrial fatty acid oxidation: a review","volume":"31","author":"Silva","year":"2008","journal-title":"J. Inherit. Metab. Dis."},{"key":"B37","doi-asserted-by":"publisher","first-page":"e108970","DOI":"10.1371\/journal.pone.0108970","article-title":"Valproic acid and fatalities in children: a review of individual case safety reports in VigiBase","volume":"9","author":"Star","year":"2014","journal-title":"PLoS One"},{"key":"B38","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":"B39","doi-asserted-by":"publisher","first-page":"1105","DOI":"10.1007\/s40262-023-01265-z","article-title":"Use of machine learning for dosage individualization of vancomycin in neonates","volume":"62","author":"Tang","year":"2023","journal-title":"Clin. Pharmacokinet."},{"key":"B40","doi-asserted-by":"publisher","first-page":"2735","DOI":"10.1007\/s00415-020-09809-0","article-title":"Expert opinion: use of valproate in girls and women of childbearing potential with epilepsy: recommendations and alternatives based on a review of the literature and clinical experience-a European perspective","volume":"268","author":"Toledo","year":"2021","journal-title":"J. Neurol."},{"key":"B41","doi-asserted-by":"publisher","first-page":"599044","DOI":"10.3389\/fped.2020.599044","article-title":"Genetic and non-genetic factors contributing to the significant variation in the plasma trough concentration-to-dose ratio of valproic acid in children with epilepsy","volume":"8","author":"Xu","year":"2020","journal-title":"Front. Pediatr."},{"key":"B42","doi-asserted-by":"publisher","first-page":"782","DOI":"10.11817\/j.issn.1672-7347.2020.190360","article-title":"Valproic acid concentration and biochemical indexes in epilepsy outpatients during monotherapy or combination therapy","volume":"45","author":"Yang","year":"2020","journal-title":"Zhong Nan Da Xue Xue Bao Yi Xue Ban."},{"key":"B43","doi-asserted-by":"publisher","first-page":"1228641","DOI":"10.3389\/fphar.2023.1228641","article-title":"Modeling the protein binding non-linearity in population pharmacokinetic model of valproic acid in children with epilepsy: a systematic evaluation study","volume":"14","author":"Zhang","year":"2023","journal-title":"Front. Pharmacol."},{"key":"B44","doi-asserted-by":"publisher","first-page":"760","DOI":"10.1097\/FTD.0000000000000751","article-title":"Impact of age and genotype on serum concentrations of valproic acid and its hepatotoxic metabolites in Chinese pediatric patients with epilepsy","volume":"42","author":"Zhao","year":"2020","journal-title":"Ther. Drug Monit."},{"key":"B45","doi-asserted-by":"publisher","first-page":"1011492","DOI":"10.3389\/fendo.2022.1011492","article-title":"Integrating machine learning with electronic health record data to facilitate detection of prolactin level and pharmacovigilance signals in olanzapine-treated patients","volume":"13","author":"Zhu","year":"","journal-title":"Front. Endocrinol. (Lausanne)"},{"key":"B46","doi-asserted-by":"publisher","first-page":"994665","DOI":"10.3389\/fphar.2022.994665","article-title":"Machine learning advances the integration of covariates in population pharmacokinetic models: valproic acid as an example","volume":"13","author":"Zhu","year":"","journal-title":"Front. Pharmacol."}],"container-title":["Frontiers in Pharmacology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fphar.2024.1521932\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,18]],"date-time":"2024-12-18T01:47:36Z","timestamp":1734486456000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fphar.2024.1521932\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,18]]},"references-count":45,"alternative-id":["10.3389\/fphar.2024.1521932"],"URL":"https:\/\/doi.org\/10.3389\/fphar.2024.1521932","relation":{},"ISSN":["1663-9812"],"issn-type":[{"value":"1663-9812","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,18]]},"article-number":"1521932"}}