{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,17]],"date-time":"2026-10-17T16:32:57Z","timestamp":1792254777725,"version":"4.4.0"},"reference-count":59,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2022,9,27]],"date-time":"2022-09-27T00:00:00Z","timestamp":1664236800000},"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:p><jats:bold>Background and Aim:<\/jats:bold> Therapeutic drug monitoring (TDM) has evolved over the years as an important tool for personalized medicine. Nevertheless, some limitations are associated with traditional TDM. Emerging data-driven model forecasting [e.g., through machine learning (ML)-based approaches] has been used for individualized therapy. This study proposes an interpretable stacking-based ML framework to predict concentrations in real time after olanzapine (OLZ) treatment.<\/jats:p><jats:p><jats:bold>Methods:<\/jats:bold> The TDM-OLZ dataset, consisting of 2,142 OLZ measurements and 472 features, was formed by collecting electronic health records during the TDM of 927 patients who had received OLZ treatment. We compared the performance of ML algorithms by using 10-fold cross-validation and the mean absolute error (MAE). The optimal subset of features was analyzed by a random forest-based sequential forward feature selection method in the context of the top five heterogeneous regressors as base models to develop a stacked ensemble regressor, which was then optimized <jats:italic>via<\/jats:italic> the grid search method. Its predictions were explained by using local interpretable model-agnostic explanations (LIME) and partial dependence plots (PDPs).<\/jats:p><jats:p><jats:bold>Results:<\/jats:bold> A state-of-the-art stacking ensemble learning framework that integrates optimized extra trees, XGBoost, random forest, bagging, and gradient-boosting regressors was developed for nine selected features [i.e., daily dose (OLZ), gender_male, age, valproic acid_yes, ALT, K, BW, MONO#, and time of blood sampling after first administration]. It outperformed other base regressors that were considered, with an MAE of 0.064, R-square value of 0.5355, mean squared error of 0.0089, mean relative error of 13%, and ideal rate (the percentages of predicted TDM within \u00b1 30% of actual TDM) of 63.40%. Predictions at the individual level were illustrated by LIME plots, whereas the global interpretation of associations between features and outcomes was illustrated by PDPs.<\/jats:p><jats:p><jats:bold>Conclusion:<\/jats:bold> This study highlights the feasibility of the real-time estimation of drug concentrations by using stacking-based ML strategies without losing interpretability, thus facilitating model-informed precision dosing.<\/jats:p>","DOI":"10.3389\/fphar.2022.975855","type":"journal-article","created":{"date-parts":[[2022,9,27]],"date-time":"2022-09-27T08:52:04Z","timestamp":1664268724000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":28,"title":["An interpretable stacking ensemble learning framework based on multi-dimensional data for real-time prediction of drug concentration: The example of olanzapine"],"prefix":"10.3389","volume":"13","author":[{"given":"Xiuqing","family":"Zhu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinqing","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tao","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shanqing","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuguan","family":"Wen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dewei","family":"Shang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2022,9,27]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"154","DOI":"10.4236\/abb.2021.126011","article-title":"Application of biochemical tests and machine learning techniques to diagnose and evaluate liver disease","volume":"12","author":"Akter","year":"2021","journal-title":"Adv. Biosci. Biotechnol."},{"key":"B2","doi-asserted-by":"publisher","first-page":"255","DOI":"10.1097\/JCP.0000000000001390","article-title":"Effects of dose, age, sex, body weight, and smoking on plasma concentrations of olanzapine and N-desmethyl olanzapine in inpatients with schizophrenia","volume":"41","author":"An","year":"2021","journal-title":"J. Clin. Psychopharmacol."},{"key":"B3","doi-asserted-by":"publisher","first-page":"665","DOI":"10.1007\/s00213-020-05715-5","article-title":"The usefulness of olanzapine plasma concentrations in monitoring treatment efficacy and metabolic disturbances in first-episode psychosis","volume":"238","author":"Arnaiz","year":"2021","journal-title":"Psychopharmacol. (Berl)"},{"key":"B4","doi-asserted-by":"publisher","first-page":"74","DOI":"10.1186\/s12911-016-0318-z","article-title":"Nearest neighbor imputation algorithms: A critical evaluation","volume":"16","author":"Beretta","year":"2016","journal-title":"BMC Med. Inf. Decis. Mak."},{"key":"B5","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1177\/0091270007310385","article-title":"Sex, race, and smoking impact olanzapine exposure","volume":"48","author":"Bigos","year":"2008","journal-title":"J. Clin. Pharmacol."},{"key":"B6","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1016\/j.ecoinf.2017.09.004","article-title":"Consensus methods based on machine learning techniques for marine phytoplankton presence-absence prediction","volume":"42","author":"Bourel","year":"2017","journal-title":"Ecol. Inf."},{"key":"B7","doi-asserted-by":"publisher","first-page":"1012","DOI":"10.1016\/j.ecolind.2017.11.031","article-title":"Multiclass classification methods in ecology","volume":"85","author":"Bourel","year":"2018","journal-title":"Ecol. Indic."},{"key":"B8","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1023\/A:1018054314350","article-title":"Bagging predictors","volume":"24","author":"Breiman","year":"1996","journal-title":"Mach. Learn."},{"key":"B9","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach. Learn."},{"key":"B10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.chemolab.2009.09.002","article-title":"The boosting: A new idea of building models","volume":"100","author":"Cao","year":"2010","journal-title":"Chemom. Intell. Lab. Syst."},{"key":"B11","doi-asserted-by":"publisher","first-page":"455","DOI":"10.1111\/acps.12794","article-title":"Effects of age and gender on the serum levels of clozapine, olanzapine, risperidone, and quetiapine","volume":"136","author":"Castberg","year":"2017","journal-title":"Acta Psychiatr. Scand."},{"key":"B12","doi-asserted-by":"publisher","first-page":"4210","DOI":"10.1021\/acs.jcim.1c00503","article-title":"Systematic investigation of error distribution in machine learning algorithms applied to the quantum-chemistry QM9 data set using the bias and variance decomposition","volume":"61","author":"Cesar de Azevedo","year":"2021","journal-title":"J. Chem. Inf. Model."},{"key":"B13","doi-asserted-by":"crossref","first-page":"785","DOI":"10.1145\/2939672.2939785","article-title":"XGBoost: A scalable tree boosting system","volume-title":"KDD '16: Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining","author":"Chen","year":"2016"},{"key":"B14","doi-asserted-by":"publisher","first-page":"152","DOI":"10.1097\/FTD.0000000000000119","article-title":"CYP1A2*1D and *1F polymorphisms have a significant impact on olanzapine serum concentrations","volume":"37","author":"Czerwensky","year":"2015","journal-title":"Ther. Drug Monit."},{"key":"B15","doi-asserted-by":"publisher","first-page":"105837","DOI":"10.1016\/j.asoc.2019.105837","article-title":"Ensemble approach based on bagging, boosting and stacking for short-term prediction in agribusiness time series","volume":"86","author":"Dal Molin Ribeiro","year":"2020","journal-title":"Appl. Soft Comput."},{"key":"B16","doi-asserted-by":"publisher","first-page":"225","DOI":"10.1146\/annurev-pharmtox-033020-113257","article-title":"Model-informed precision dosing: Background, requirements, validation, implementation, and forward trajectory of individualizing drug therapy","volume":"61","author":"Darwich","year":"2021","journal-title":"Annu. Rev. Pharmacol. Toxicol."},{"key":"B17","doi-asserted-by":"publisher","first-page":"636","DOI":"10.1097\/FTD.0000000000000738","article-title":"A retrospective analysis of steady-state olanzapine concentrations in Chinese patients using therapeutic drug monitoring: Effects of valproate and other factors","volume":"42","author":"Deng","year":"2020","journal-title":"Ther. Drug Monit."},{"key":"B18","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1006\/jcss.1997.1504","article-title":"A decision-theoretic generalization of on-line learning and an application to boosting","volume":"55","author":"Freund","year":"1997","journal-title":"J. Comput. Syst. Sci."},{"key":"B19","doi-asserted-by":"publisher","first-page":"1189","DOI":"10.1214\/aos\/1013203451","article-title":"Greedy function approximation: A gradient boosting machine","volume":"29","author":"Friedman","year":"2001","journal-title":"Ann. Stat."},{"key":"B20","doi-asserted-by":"publisher","first-page":"816","DOI":"10.1097\/FTD.0b013e318296a2ff","article-title":"Therapeutic drug monitoring of psychotropic drugs in China: A nationwide survey","volume":"35","author":"Guo","year":"2013","journal-title":"Ther. Drug Monit."},{"key":"B21","doi-asserted-by":"publisher","first-page":"711868","DOI":"10.3389\/fpsyt.2021.711868","article-title":"A machine learning model to predict risperidone active moiety concentration based on initial therapeutic drug monitoring","volume":"12","author":"Guo","year":"2021","journal-title":"Front. Psychiatry"},{"key":"B22","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1055\/s-0043-116492","article-title":"Consensus guidelines for therapeutic drug monitoring in neuropsychopharmacology: Update 2017","volume":"51","author":"Hiemke","year":"2018","journal-title":"Pharmacopsychiatry"},{"key":"B23","doi-asserted-by":"publisher","first-page":"1558","DOI":"10.3390\/biomedicines9111558","article-title":"Predicting serum levels of lithium-treated patients: A supervised machine learning approach","volume":"9","author":"Hsu","year":"2021","journal-title":"Biomedicines"},{"key":"B24","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":"B25","doi-asserted-by":"publisher","first-page":"104554","DOI":"10.1016\/j.compbiomed.2021.104554","article-title":"A novel stacking technique for prediction of diabetes","volume":"135","author":"Kalagotla","year":"2021","journal-title":"Comput. Biol. Med."},{"key":"B26","doi-asserted-by":"publisher","first-page":"926","DOI":"10.1002\/cpt.1774","article-title":"Pharmacometrics and machine learning partner to advance clinical data analysis","volume":"107","author":"Koch","year":"2020","journal-title":"Clin. Pharmacol. Ther."},{"key":"B27","doi-asserted-by":"publisher","first-page":"1023","DOI":"10.3390\/pharmaceutics14051023","article-title":"Application of machine learning classification to improve the performance of vancomycin therapeutic drug monitoring","volume":"14","author":"Lee","year":"2022","journal-title":"Pharmaceutics"},{"key":"B28","doi-asserted-by":"publisher","first-page":"126","DOI":"10.4212\/cjhp.v72i2.2882","article-title":"Survey of therapeutic drug monitoring practices in pediatric health care programs across Canada","volume":"72","author":"Leung","year":"2019","journal-title":"Can. J. Hosp. Pharm."},{"key":"B29","doi-asserted-by":"publisher","first-page":"18","DOI":"10.3390\/e23010018","article-title":"Explainable AI: A review of machine learning interpretability methods","volume":"23","author":"Linardatos","year":"2020","journal-title":"Entropy (Basel)"},{"key":"B30","doi-asserted-by":"crossref","first-page":"2845","DOI":"10.1109\/IECON.2010.5675075","article-title":"Feature selection using sequential forward selection and classification applying artificial metaplasticity neural network","volume-title":"IECON 2010 - 36th annual conference on IEEE industrial electronics society","author":"Marcano-Cede\u00f1o","year":"2010"},{"key":"B31","doi-asserted-by":"publisher","first-page":"1482","DOI":"10.1111\/bcp.14801","article-title":"Machine learning in pharmacometrics: Opportunities and challenges","volume":"88","author":"McComb","year":"2022","journal-title":"Br. J. Clin. Pharmacol."},{"key":"B32","doi-asserted-by":"publisher","first-page":"905","DOI":"10.1016\/S2213-2600(18)30300-X","article-title":"Machine learning for real-time prediction of complications in critical care: A retrospective study","volume":"6","author":"Meyer","year":"2018","journal-title":"Lancet. Respir. Med."},{"key":"B33","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1111\/acps.12947","article-title":"Impact of CYP1A2 genetic polymorphisms on pharmacokinetics of antipsychotic drugs: A systematic review and meta-analysis","volume":"139","author":"Na Takuathung","year":"2019","journal-title":"Acta Psychiatr. Scand."},{"key":"B34","doi-asserted-by":"publisher","first-page":"7402","DOI":"10.1038\/s41598-017-07408-0","article-title":"Machine learning applications for prediction of relapse in childhood acute lymphoblastic leukemia","volume":"7","author":"Pan","year":"2017","journal-title":"Sci. Rep."},{"key":"B35","first-page":"2825","article-title":"Scikit-learn: Machine learning in Python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"B36","doi-asserted-by":"publisher","first-page":"1680","DOI":"10.1177\/147323000903700603","article-title":"Machine learning methods applied to pharmacokinetic modelling of remifentanil in healthy volunteers: A multi-method comparison","volume":"37","author":"Poynton","year":"2009","journal-title":"J. Int. Med. Res."},{"key":"B37","doi-asserted-by":"publisher","first-page":"978","DOI":"10.3390\/jpm11100978","article-title":"Hyperparameter tuning and pipeline optimization via grid search method and tree-based autoML in breast cancer prediction","volume":"11","author":"Radzi","year":"2021","journal-title":"J. Pers. Med."},{"key":"B38","doi-asserted-by":"publisher","first-page":"105284","DOI":"10.1016\/j.compbiomed.2022.105284","article-title":"QCovSML: A reliable COVID-19 detection system using CBC biomarkers by a stacking machine learning model","volume":"143","author":"Rahman","year":"2022","journal-title":"Comput. Biol. Med."},{"key":"B39","doi-asserted-by":"publisher","first-page":"853","DOI":"10.1002\/cpt.1777","article-title":"Model-informed artificial intelligence: Reinforcement learning for precision dosing","volume":"107","author":"Ribba","year":"2020","journal-title":"Clin. Pharmacol. Ther."},{"key":"B40","doi-asserted-by":"crossref","first-page":"1135","DOI":"10.1145\/2939672.2939778","article-title":"\u201cWhy should I trust you?\u201d explaining the predictions of any classifier","volume-title":"Kdd '16: Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining","author":"Ribeiro","year":"2016"},{"key":"B41","doi-asserted-by":"publisher","first-page":"1051","DOI":"10.1007\/s12517-022-10274-4","article-title":"Meta-learner methods in forecasting regulated and natural river flow","volume":"15","author":"Sayari","year":"2022","journal-title":"Arab. J. Geosci."},{"key":"B42","doi-asserted-by":"publisher","first-page":"1651","DOI":"10.1214\/aos\/1024691352","article-title":"Boosting the margin: A new explanation for the effectiveness of voting methods","volume":"26","author":"Schapire","year":"1998","journal-title":"Ann. Stat."},{"key":"B43","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1002\/widm.1143","article-title":"Generating ensembles of heterogeneous classifiers using stacked generalization","volume":"5","author":"Sesmero","year":"2015","journal-title":"WIREs. Data Min. Knowl. Discov."},{"key":"B44","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1007\/s10928-021-09793-6","article-title":"Population pharmacokinetic model selection assisted by machine learning","volume":"49","author":"Sibieude","year":"2022","journal-title":"J. Pharmacokinet. Pharmacodyn."},{"key":"B45","doi-asserted-by":"publisher","first-page":"1435","DOI":"10.1007\/s40262-021-01033-x","article-title":"Drug clearance in neonates: A combination of population pharmacokinetic modelling and machine learning approaches to improve individual prediction","volume":"60","author":"Tang","year":"2021","journal-title":"Clin. Pharmacokinet."},{"key":"B46","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":"B47","doi-asserted-by":"publisher","first-page":"241","DOI":"10.1016\/S0893-6080(05)80023-1","article-title":"Stacked generalization","volume":"5","author":"Wolpert","year":"1992","journal-title":"Neural Netw."},{"key":"B48","doi-asserted-by":"publisher","first-page":"106039","DOI":"10.1016\/j.compag.2021.106039","article-title":"Evaluation of stacking and blending ensemble learning methods for estimating daily reference evapotranspiration","volume":"184","author":"Wu","year":"2021","journal-title":"Comput. Electron. Agric."},{"key":"B49","doi-asserted-by":"publisher","first-page":"3411","DOI":"10.2147\/DDDT.S316110","article-title":"What to do about missed doses? A retrospective study of olanzapine in the elderly","volume":"15","author":"Xiao","year":"2021","journal-title":"Drug Des. Devel. Ther."},{"key":"B50","doi-asserted-by":"publisher","first-page":"9152506","DOI":"10.1155\/2019\/9152506","article-title":"Comparison of bagging and boosting ensemble machine learning methods for automated EMG signal classification","volume":"2019","author":"Yaman","year":"2019","journal-title":"Biomed. Res. Int."},{"key":"B51","doi-asserted-by":"publisher","first-page":"159151","DOI":"10.1109\/ACCESS.2020.3019377","article-title":"Feature selection based on random forest for partial discharges characteristic set","volume":"8","author":"Yao","year":"2020","journal-title":"IEEE Access"},{"key":"B52","doi-asserted-by":"publisher","first-page":"144715","DOI":"10.1016\/j.scitotenv.2020.144715","article-title":"Bayesian machine learning ensemble approach to quantify model uncertainty in predicting groundwater storage change","volume":"769","author":"Yin","year":"2021","journal-title":"Sci. Total Environ."},{"key":"B53","doi-asserted-by":"publisher","first-page":"706329","DOI":"10.3389\/fphar.2021.706329","article-title":"Case report: Predicting the range of lamotrigine concentration using pharmacokinetic models based on Monte Carlo simulation: A case study of antiepileptic drug-related leukopenia","volume":"12","author":"Zhu","year":"","journal-title":"Front. Pharmacol."},{"key":"B54","doi-asserted-by":"publisher","first-page":"353","DOI":"10.1007\/s13318-021-00673-5","article-title":"The impact of smoking, sex, infection, and comedication administration on oral olanzapine: A population pharmacokinetic model in Chinese psychiatric patients","volume":"46","author":"Zang","year":"2021","journal-title":"Eur. J. Drug Metab. Pharmacokinet."},{"key":"B55","doi-asserted-by":"publisher","first-page":"107771","DOI":"10.1016\/j.sigpro.2020.107771","article-title":"Learning stacking regression for no-reference super-resolution image quality assessment","volume":"178","author":"Zhang","year":"2021","journal-title":"Signal Process."},{"key":"B56","doi-asserted-by":"publisher","first-page":"727245","DOI":"10.3389\/fphar.2021.727245","article-title":"Predicting blood concentration of tacrolimus in patients with autoimmune diseases using machine learning techniques based on real-world evidence","volume":"12","author":"Zheng","year":"2021","journal-title":"Front. Pharmacol."},{"key":"B57","doi-asserted-by":"publisher","first-page":"403","DOI":"10.1007\/s10439-018-02168-y","article-title":"Localization of ventricular activation origin from the 12-lead ECG: A comparison of linear regression with non-linear methods of machine learning","volume":"47","author":"Zhou","year":"2019","journal-title":"Ann. Biomed. Eng."},{"key":"B58","doi-asserted-by":"publisher","first-page":"216","DOI":"10.1089\/cap.2017.0079","article-title":"Comparison of unlicensed and off-label use of antipsychotics prescribed to child and adolescent psychiatric outpatients for treatment of mental and behavioral disorders with different guidelines: The China food and drug administration versus the FDA","volume":"28","author":"Zhu","year":"2018","journal-title":"J. Child. Adolesc. Psychopharmacol."},{"key":"B59","doi-asserted-by":"publisher","first-page":"5568","DOI":"10.1038\/s41598-021-85157-x","article-title":"A machine learning approach to personalized dose adjustment of lamotrigine using noninvasive clinical parameters","volume":"11","author":"Zhu","year":"","journal-title":"Sci. Rep."}],"container-title":["Frontiers in Pharmacology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fphar.2022.975855\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,27]],"date-time":"2022-09-27T08:52:13Z","timestamp":1664268733000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fphar.2022.975855\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9,27]]},"references-count":59,"alternative-id":["10.3389\/fphar.2022.975855"],"URL":"https:\/\/doi.org\/10.3389\/fphar.2022.975855","relation":{},"ISSN":["1663-9812"],"issn-type":[{"value":"1663-9812","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,9,27]]},"article-number":"975855"}}