{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,19]],"date-time":"2026-10-19T23:52:41Z","timestamp":1792453961224,"version":"4.5.0"},"reference-count":38,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T00:00:00Z","timestamp":1705622400000},"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. Cardiovasc. Med."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>With the rapid development of artificial intelligence, prediction of warfarin dose via machine learning has received more and more attention. Since the dose prediction involve both linear and nonlinear problems, traditional machine learning algorithms are ineffective to solve such problems at one time.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>Based on the characteristics of clinical data of Chinese warfarin patients, an improved stacking ensemble learning can achieve higher prediction accuracy.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Information of 641 patients from southern China who had reached a steady state on warfarin was collected, including demographic information, medical history, genotype, and co-medication status. The dataset was randomly divided into a training set (90%) and a test set (10%). The predictive capability is evaluated on a new test set generated by stacking ensemble learning. Additional factors associated with warfarin dose were discovered by feature selection methods.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      A newly proposed heuristic-stacking ensemble learning performs better than traditional-stacking ensemble learning in key metrics such as accuracy of ideal dose (73.44%, 71.88%), mean absolute errors (0.11 mg\/day, 0.13 mg\/day), root mean square errors (0.18 mg\/day, 0.20 mg\/day) and R\n                      <jats:sup>2<\/jats:sup>\n                      (0.87, 0.82).\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>The developed heuristic-stacking ensemble learning can satisfactorily predict warfarin dose with high accuracy. A relationship between hypertension, a history of severe preoperative embolism, and warfarin dose is found, which provides a useful reference for the warfarin dose administration in the future.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fcvm.2023.1320938","type":"journal-article","created":{"date-parts":[[2024,1,18]],"date-time":"2024-01-18T23:24:22Z","timestamp":1705620262000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":14,"title":["Improved stacking ensemble learning based on feature selection to accurately predict warfarin dose"],"prefix":"10.3389","volume":"10","author":[{"given":"Mingyuan","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiyi","family":"Qian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yaodong","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haobin","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei-Feng","family":"Rao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2024,1,19]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"340","DOI":"10.1111\/j.1365-2125.2011.04097.x","article-title":"The pharmacogenetics of the response to warfarin in Chinese","volume":"73","author":"Lam","year":"2012","journal-title":"Br J Clin Pharmacol"},{"key":"B2","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1097\/GIM.0b013e318163c35f","article-title":"Pharmacogenetic testing of CYP2C9 and VKORC1 alleles for warfarin","volume":"10","author":"Flockhart","year":"2008","journal-title":"Genet Med"},{"key":"B3","doi-asserted-by":"publisher","first-page":"202","DOI":"10.1038\/sj.tpj.6500182","article-title":"Pharmacogenetics of CYP2C9 and interindividual variability in anticoagulant response to warfarin","volume":"3","author":"Takahashi","year":"2003","journal-title":"Pharmacogenomics J"},{"key":"B4","doi-asserted-by":"publisher","first-page":"159","DOI":"10.1067\/mcp.2001.117444","article-title":"Interindividual variability in sensitivity to warfarin-nature or nurture?","volume":"70","author":"Loebstein","year":"2001","journal-title":"Clin Pharmacol Ther"},{"key":"B5","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1007\/s11239-007-0105-x","article-title":"Anticoagulation for mechanical heart valves: a role for patient based therapy","volume":"25","author":"Emery","year":"2008","journal-title":"J Thromb Thrombolysis"},{"key":"B6","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1097\/fjc.0000000000000317","article-title":"Pharmacogenetic-guided warfarin dosing algorithm in African-Americans","volume":"67","author":"Alzubiedi","year":"2016","journal-title":"J Cardiovasc Pharmacol"},{"key":"B7","doi-asserted-by":"publisher","first-page":"167","DOI":"10.2217\/pgs-2018-0127","article-title":"Evaluation of the predictive performance of Bayesian dosing for warfarin in Chinese patients","volume":"20","author":"Dong","year":"2019","journal-title":"Pharmacogenomics"},{"key":"B8","doi-asserted-by":"publisher","first-page":"1550","DOI":"10.3389\/fphar.2019.01550","article-title":"Machine learning algorithm for predicting warfarin dose in Caribbean hispanics using pharmacogenetic data","volume":"10","author":"Roche-Lima","year":"2019","journal-title":"Front Pharmacol"},{"key":"B9","doi-asserted-by":"publisher","first-page":"749786","DOI":"10.3389\/fphar.2021.749786","article-title":"Machine learning for prediction of stable warfarin dose in US Latinos and Latin Americans","volume":"12","author":"Steiner","year":"2021","journal-title":"Front Pharmacol"},{"key":"B10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3136625","article-title":"Feature selection: a data perspective","volume":"50","author":"Li","year":"2017","journal-title":"ACM Comput Surv"},{"key":"B11","doi-asserted-by":"publisher","first-page":"491","DOI":"10.1109\/tkde.2005.66","article-title":"Toward integrating feature selection algorithms for classification and clustering","volume":"17","author":"Liu","year":"2005","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"B12","doi-asserted-by":"publisher","first-page":"158","DOI":"10.1111\/bcp.12308","article-title":"Characterizing variability in warfarin dose requirements in children using modelling and simulation","volume":"78","author":"Hamberg","year":"2014","journal-title":"Br J Clin Pharmacol"},{"key":"B13","doi-asserted-by":"publisher","first-page":"395","DOI":"10.1109\/jbhi.2018.2812165","article-title":"Evolutionary ensemble learning algorithm to modeling of warfarin dose prediction for Chinese","volume":"23","author":"Tao","year":"2019","journal-title":"IEEE J Biomed Health Inform"},{"key":"B14","doi-asserted-by":"publisher","first-page":"e0205872","DOI":"10.1371\/journal.pone.0205872","article-title":"Ensemble of machine learning algorithms using the stacked generalization approach to estimate the warfarin dose","volume":"13","author":"Ma","year":"2018","journal-title":"PLoS One"},{"key":"B15","doi-asserted-by":"crossref","first-page":"2514","DOI":"10.1109\/CEC.2019.8789976","article-title":"Evolutionary synthetic minority oversampling technique with random forest for warfarin dose prediction in Chinese patients","volume-title":"2019 IEEE Congress on Evolutionary Computation (CEC)","author":"Tao","year":"2019"},{"key":"B16","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1016\/j.artmed.2012.04.001","article-title":"Predicting warfarin dosage from clinical data: a supervised learning approach","volume":"56","author":"Hu","year":"2012","journal-title":"Artif Intell Med"},{"key":"B17","doi-asserted-by":"publisher","first-page":"1676","DOI":"10.1111\/jth.15318","article-title":"Comparison of multivariate linear regression and a machine learning algorithm developed for prediction of precision warfarin dosing in a Korean population","volume":"19","author":"Nguyen","year":"2021","journal-title":"J Thromb Haemostasis"},{"key":"B18","doi-asserted-by":"publisher","first-page":"863.e5","DOI":"10.1016\/j.echo.2009.03.005","article-title":"Fatal freely mobile left atrial thrombus: fallout of anticoagulation?","volume":"22","author":"Roy","year":"2009","journal-title":"J Am Soc Echocardiogr"},{"key":"B19","doi-asserted-by":"publisher","first-page":"499","DOI":"10.1111\/dom.14243","article-title":"Risk of developing diabetes in patients with atrial fibrillation taking non-vitamin K antagonist oral anticoagulants or warfarin: a nationwide cohort study","volume":"23","author":"Huang","year":"2021","journal-title":"Diabetes Obes Metab"},{"key":"B20","doi-asserted-by":"publisher","first-page":"454","DOI":"10.5414\/cp201996","article-title":"Warfarin compared with aspirin for older Chinese patients with stable coronary heart diseases and atrial fibrillation complications","volume":"52","author":"Liu","year":"2014","journal-title":"Int J Clin Pharm Ther"},{"key":"B21","doi-asserted-by":"publisher","first-page":"898","DOI":"10.1177\/1747493016658300","article-title":"Blood pressure burden and outcome in warfarin-related intracerebral hemorrhage","volume":"11","author":"Schlunk","year":"2016","journal-title":"Int J Stroke"},{"key":"B22","doi-asserted-by":"publisher","first-page":"753","DOI":"10.1056\/NEJMoa0809329","article-title":"Estimation of the warfarin dose with clinical and pharmacogenetic data","volume":"360","author":"Klein","year":"2009","journal-title":"N Engl J Med"},{"key":"B23","doi-asserted-by":"publisher","first-page":"22863","DOI":"10.1109\/access.2018.2818682","article-title":"A hybrid genetic algorithm with wrapper-embedded approaches for feature selection","volume":"6","author":"Liu","year":"2018","journal-title":"IEEE Access"},{"key":"B24","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1016\/S1088-467X(97)00008-5","article-title":"Feature selection for classification","volume":"1","author":"Dash","year":"1997","journal-title":"Intell Data Anal"},{"key":"B25","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1080\/00031305.1988.10475524","article-title":"Thirteen ways to look at the correlation coefficient","volume":"42","author":"Rodgers","year":"1988","journal-title":"Am Stat"},{"key":"B26","doi-asserted-by":"crossref","DOI":"10.4324\/9780203726631","volume-title":"Research Design and Statistical Analysis","author":"Myers","year":"2013"},{"key":"B27","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1093\/biomet\/30.1-2.81","article-title":"A new measure of rank correlation","volume":"30","author":"Kendall","year":"1938","journal-title":"Biometrika"},{"key":"B28","doi-asserted-by":"publisher","first-page":"120","DOI":"10.1007\/s11239-012-0725-7","article-title":"Impact of CYP2C9*3, VKORC1-1639, CYP4F2rs2108622 genetic polymorphism and clinical factors on warfarin maintenance dose in Han-Chinese patients","volume":"34","author":"Liang","year":"2012","journal-title":"J Thromb Thrombolysis"},{"key":"B29","doi-asserted-by":"publisher","first-page":"1130","DOI":"10.1378\/chest.10-0777","article-title":"Assessing evidence of interaction between smoking and warfarin a systematic review and meta-analysis","volume":"139","author":"Nathisuwan","year":"2011","journal-title":"Chest"},{"key":"B30","first-page":"385","article-title":"Factors influencing quality of anticoagulation control and warfarin dosage in patients after aortic valve replacement within the 3 months of follow up","volume":"67","author":"Wypasek","year":"2016","journal-title":"J Physiol Pharmacol"},{"key":"B31","doi-asserted-by":"publisher","first-page":"1135","DOI":"10.1007\/s00228-007-0381-6","article-title":"Contribution of age, body weight, and CYP2C9 and VKORC1 genotype to the anticoagulant response to warfarin: proposal for a new dosing regimen in Chinese patients","volume":"63","author":"Miao","year":"2007","journal-title":"Eur J Clin Pharmacol"},{"key":"B32","doi-asserted-by":"publisher","first-page":"197","DOI":"10.1142\/S0218001488000145","article-title":"On automatic feature selection","volume":"2","author":"Siedlecki","year":"1988","journal-title":"Int J Pattern Recognit Artif Intell"},{"key":"B33","first-page":"2825","article-title":"Scikit-learn: machine learning in python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J Mach Learn Res"},{"key":"B34","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1038\/sj.clpt.6100453","article-title":"Prospective study of warfarin dosage requirements based on CYP2C9 and VKORC1 genotypes","volume":"84","author":"Wen","year":"2008","journal-title":"Clin Pharmacol Ther"},{"key":"B35","first-page":"211","article-title":"Sparse Bayesian learning and the relevance vector machine","volume":"1","author":"Tipping","year":"2001","journal-title":"J Mach Learn Res"},{"key":"B36","volume-title":"Gaussian Processes for Machine Learning","author":"Williams","year":"2006"},{"key":"B37","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":"Wiley Interdiscip Rev-Data Mining Knowl Discov"},{"key":"B38","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"}],"container-title":["Frontiers in Cardiovascular Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fcvm.2023.1320938\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,18]],"date-time":"2024-01-18T23:24:26Z","timestamp":1705620266000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fcvm.2023.1320938\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,19]]},"references-count":38,"alternative-id":["10.3389\/fcvm.2023.1320938"],"URL":"https:\/\/doi.org\/10.3389\/fcvm.2023.1320938","relation":{},"ISSN":["2297-055X"],"issn-type":[{"value":"2297-055X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1,19]]},"article-number":"1320938"}}