{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,6]],"date-time":"2026-11-06T22:13:07Z","timestamp":1794003187078,"version":"4.8.0"},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"S10","license":[{"start":{"date-parts":[[2020,10,1]],"date-time":"2020-10-01T00:00:00Z","timestamp":1601510400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2020,10,22]],"date-time":"2020-10-22T00:00:00Z","timestamp":1603324800000},"content-version":"vor","delay-in-days":21,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Med Genomics"],"published-print":{"date-parts":[[2020,10]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Vitamin K antagonist (warfarin) is the most classical and widely used oral anticoagulant with assuring anticoagulant effect, wide clinical indications and low price. Warfarin dosage requirements of different patients vary largely. For warfarin daily dosage prediction, the data imbalance in dataset leads to inaccurate prediction on the patients of rare genotype, who usually have large stable dosage requirement. To balance the dataset of patients treated with warfarin and improve the predictive accuracy, an appropriate partition of majority and minority groups, together with an oversampling method, is required.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Method<\/jats:title>\n                    <jats:p>To solve the data-imbalance problem mentioned above, we developed a clustering-based oversampling technique denoted as DBCSMOTE, which combines density-based spatial clustering of application with noise (DBCSCAN) and synthetic minority oversampling technique (SMOTE). DBCSMOTE automatically finds the minority groups by acquiring the association between samples in terms of the clinical features\/genotypes and the warfarin dosage, and creates an extended dataset by adding the new synthetic samples of majority and minority groups. Meanwhile, two ensemble models, boosted regression tree (BRT) and random forest (RF), which are built on the extended dataset generateed by DBCSMOTE, accomplish the task of warfarin daily dosage prediction.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      DBCSMOTE and the comparison methods were tested on the datasets derived from our Hospital and International Warfarin Pharmacogenetics Consortium (IWPC). As the results, DBCSMOTE-BRT obtained the highest\n                      <jats:italic>R<\/jats:italic>\n                      -squared (\n                      <jats:italic>R<\/jats:italic>\n                      <jats:sup>2<\/jats:sup>\n                      ) of 0.424 and the smallest mean squared error (mse) of 1.08. In terms of the percentage of patients whose predicted dose of warfarin is within 20% of the actual stable therapeutic dose (20%-\n                      <jats:italic>p<\/jats:italic>\n                      ), DBCSMOTE-BRT can achieve the largest value of 47.8% among predictive models. The more important thing is that DBCSMOTE saved about 68% computational time to achieve the same or better performance than the Evolutionary SMOTE, which was the best oversampling method in warfarin dose prediction by far. Meanwhile, in warfarin dose prediction, it is discovered that DBCSMOTE is more effective in\u00a0 integrating BRT than RF\u00a0 for warfarin dose prediction.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Our finding is that the genotypes, CYP2C9 and VKORC1, no doubt contribute to the predictive accuracy. It was also discovered left atrium diameter, glutamic pyruvic transaminase and serum creatinine included in the model actually improved the predictive accuracy; When congestive heart failure, diabetes mellitus and valve replacement were absent in DBCSMOTE-BRT\/RF, the predictive accuracy of DBCSMOTE-BRT\/RF decreased. The oversampling ratio and number of minority clusters have a large impact on the effect of oversampling. According to our test, the predictive accuracy was high when the number of minority clusters was 6\u2009~\u20098. The oversampling ratio for small minority clusters should be large (&gt;\u20091.2) and for large minority clusters should be small (&lt;\u20090.2). If\u00a0the dataset becomes larger, the DBCSMOTE would be re-optimized and its BRT\/RF model should be re-trained. DBCSMOTE-BRT\/RF outperformed the current commonly-used tool called Warfarindosing. As compared to Evolutionary SMOTE-BRT and RF\u00a0 models, DBCSMOTE-BRT and RF models take only a small computational time to achieve the same or higher performance in many cases. In terms of predictive accuracy, RF is not as good as BRT. However, RF still has a powerful ability in generating a highly accurate model as the dataset increases; the software \u201cWarfarinSeer v2.0\u201d is a test version, which packed DBCSMOTE-BRT\/RF. It could be a convenient tool for clinical application in warfarin treatment.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1186\/s12920-020-00781-2","type":"journal-article","created":{"date-parts":[[2020,10,21]],"date-time":"2020-10-21T19:04:26Z","timestamp":1603307066000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":20,"title":["DBCSMOTE: a clustering-based oversampling technique for data-imbalanced warfarin dose prediction"],"prefix":"10.1186","volume":"13","author":[{"given":"Yanyun","family":"Tao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuzhen","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bin","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,10,22]]},"reference":[{"issue":"11","key":"781_CR1","doi-asserted-by":"publisher","first-page":"1609:1678","DOI":"10.1093\/europace\/euw295","volume":"18","author":"P Kirchhof","year":"2016","unstructured":"Kirchhof P, Benussi S, Kotecha D, et al. 2016 ESC Guidelines for the management of atrial fibrillation developed in collaboration with EACTS. Europace. 2016;18(11):1609:1678.","journal-title":"Europace"},{"key":"781_CR2","first-page":"2017","volume":"26","author":"M Valgimigli","year":"2017","unstructured":"Valgimigli M, Bueno H, Byrne AR, et al. ESC focused update on dual antiplatelet therapy in coronary artery disease developed in collaboration with EACTS: the task force for dual antiplatelet therapy in coronary artery disease of the European Society of Cardiology (ESC) and of the European Association for Cardio-Thoracic Surgery (EACTS). Eur Heart J, Aug. 2017;26:2017.","journal-title":"Eur Heart J, Aug"},{"issue":"3","key":"781_CR3","doi-asserted-by":"publisher","first-page":"397:404","DOI":"10.1002\/cpt.668","volume":"102","author":"JA Johnson","year":"2017","unstructured":"Johnson JA, Caudle KE, Gong L, et al. Clinical Pharmacogenetics Implementation Consortium (CPIC) Guideline for Pharmacogenetics-Guided Warfarin Dosing: 2017 Update. Clin Pharmacol Ther. 2017;102(3):397:404.","journal-title":"Clin Pharmacol Ther"},{"issue":"1","key":"781_CR4","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1160\/TH03-06-0379","volume":"91","author":"BF Gage","year":"2004","unstructured":"Gage BF, Eby C, Milligan PE, et al. Use of pharmacogenetics and clinical factors to predict the maintenance dose of warfarin. Thromb Haemost. 2004;91(1):87\u201394.","journal-title":"Thromb Haemost"},{"issue":"8","key":"781_CR5","doi-asserted-by":"publisher","first-page":"893","DOI":"10.1055\/s-0032-1328891","volume":"38","author":"E Fung","year":"2012","unstructured":"Fung E, Patsopoulos NA, Belknap SM, et al. Effect of Genetic Variants, Especially CYP2C9 and VKORC1, on the Pharmacology of Warfarin. Semin Thromb Hemost. 2012;38(8):893\u2013904.","journal-title":"Semin Thromb Hemost"},{"issue":"8","key":"781_CR6","doi-asserted-by":"publisher","first-page":"e105250","DOI":"10.1371\/journal.pone.0105250","volume":"9","author":"J Chen","year":"2014","unstructured":"Chen J, Shao L, Gong L, et al. A Pharmacogenetics-Based Warfarin Maintenance Dosing Algorithm from Northern Chinese Patients. Plos One. 2014;9(8):e105250.","journal-title":"Plos One"},{"issue":"4","key":"781_CR7","doi-asserted-by":"publisher","first-page":"626:641","DOI":"10.1111\/bcp.12220","volume":"77","author":"TI Verhoef","year":"2014","unstructured":"Verhoef TI, Redekop WK, Daly AK, et al. Pharmacogenetic-guided dosing of coumarin anticoagulants: algorithms for warfarin, acenocoumarol and phenprocoumon. Br J Clin Pharmacol. 2014;77(4):626:641.","journal-title":"Br J Clin Pharmacol"},{"issue":"4","key":"781_CR8","doi-asserted-by":"publisher","first-page":"531:538","DOI":"10.1097\/FTD.0000000000000177","volume":"37","author":"SM Saffian","year":"2015","unstructured":"Saffian SM, Wright DF, Roberts RL, et al. Methods for Predicting Warfarin Dose Requirements. Ther Drug Monit. 2015;37(4):531:538.","journal-title":"Ther Drug Monit"},{"issue":"12","key":"781_CR9","first-page":"1135:1141","volume":"63","author":"J Yang","year":"2007","unstructured":"Yang J, Miao L, Huang C, et al. 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. Eur J Clin Pharmacol. 2007;63(12):1135:1141.","journal-title":"Eur J Clin Pharmacol"},{"issue":"01","key":"781_CR10","doi-asserted-by":"publisher","first-page":"23:29","DOI":"10.5414\/CPP49023","volume":"49","author":"J Yang","year":"2011","unstructured":"Yang J, Huang CZ, Shen Z, et al. Contribution of 1173C > T polymorphism in the VKORC1 gene to warfarin dose requirements in Han Chinese patients receiving anticoagulation. Int J Clin Pharmacol Ther. 2011;49(01):23:29.","journal-title":"Int J Clin Pharmacol Ther"},{"issue":"6","key":"781_CR11","first-page":"9904:9910","volume":"8","author":"Z Yu","year":"2015","unstructured":"Yu Z, Ding Y, Lu F, et al. Warfarin dosage adjustment strategy in Chinese population. Int J Clin Exp Med. 2015;8(6):9904:9910.","journal-title":"Int J Clin Exp Med"},{"key":"781_CR12","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1155\/2015\/560108","volume":"1","author":"A Sharabiani","year":"2015","unstructured":"Sharabiani A, Bress A, Douzali E, et al. Revisiting Warfarin Dosing Using Machine Learning Techniques. Comput Math Methods Med. 2015;1:9. https:\/\/doi.org\/10.1155\/2015\/560108.","journal-title":"Comput Math Methods Med"},{"issue":"7\/8","key":"781_CR13","first-page":"365:371","volume":"65","author":"DM Carty","year":"2015","unstructured":"Carty DM, Young TM, Zaretzki RL, et al. Predicting and Correlating the Strength Properties of Wood Composite Process Parameters by Use of Boosted Regression Tree Models. Forest Prod J. 2015;65(7\/8):365:371.","journal-title":"Forest Prod J"},{"key":"781_CR14","unstructured":"Byrne SCP, Barry A, Graham I, et.al, Using Neural Nets for Decision Support in Prescription and Outcome Prediction in Anticoagulation Drug Therapy, The Fifth Workshop on Intelligent Data Analysis in Medicine and Pharmacology (IDAMAP-2000) Workshop Notes of the 14th European Conference on Artificial Intelligence (ECAI-2000). 2000; 576:582."},{"issue":"12","key":"781_CR15","first-page":"732:735","volume":"6","author":"I Solomon","year":"2004","unstructured":"Solomon I, Maharshak N, Chechik G, et al. Applying an artificial neural network to warfarin maintenance dose prediction. IMAJ. 2004;6(12):732:735.","journal-title":"IMAJ"},{"issue":"10","key":"781_CR16","doi-asserted-by":"publisher","first-page":"1384:1389","DOI":"10.1093\/bioinformatics\/btr159","volume":"27","author":"E Cosgun","year":"2011","unstructured":"Cosgun E, Limdi NA, Duarte CW. High-dimensional pharmacogenetic prediction of a continuous trait using machine learning techniques with application to warfarin dose prediction in African Americans. Bioinformatics. 2011;27(10):1384:1389.","journal-title":"Bioinformatics"},{"issue":"5","key":"781_CR17","doi-asserted-by":"publisher","first-page":"1189:1232","DOI":"10.1214\/aos\/1013203451","volume":"29","author":"JH Friedman","year":"2001","unstructured":"Friedman JH. Greedy Function Approximation: A Gradient Boosting Machine. Ann Stat. 2001;29(5):1189:1232.","journal-title":"Ann Stat"},{"key":"781_CR18","doi-asserted-by":"crossref","unstructured":"Dietterich T G. An Experimental Comparison of Three Methods for Constructing Ensembles of Decision Trees: Bagging, Boosting, and Randomization. Machine Learning, 2000, 40(2);139:157.","DOI":"10.1023\/A:1007607513941"},{"issue":"2","key":"781_CR19","doi-asserted-by":"publisher","first-page":"297:304","DOI":"10.1002\/cpt.649","volume":"102","author":"SM Saffian","year":"2017","unstructured":"Saffian SM, Duffull SB, Wright DFB. Warfarin dosing algorithms under-predict dose requirements in patients requiring\u22657mg daily: A systematic review and meta-analysis. Clin Pharmacol Ther. 2017;102(2):297:304.","journal-title":"Clin Pharmacol Ther"},{"issue":"8","key":"781_CR20","first-page":"753:764","volume":"360","author":"TE Klein","year":"2009","unstructured":"Klein TE, Altman RB, Eriksson N, et al. Estimation of warfarin dose with clinical and pharmacogenetic data. N Engl J Med. 2009;360(8):753:764.","journal-title":"N Engl J Med"},{"key":"781_CR21","doi-asserted-by":"publisher","unstructured":"Tao YY, Zhang YZ, WarfarinSeer: a predictive tool based on SMOTE-random forest to improve warfarin dose prediction in Chinese patients, Proceeding of 2018 IEEE International Conference on Bioinformatics and Biomedicine (BIBM18), Madrid, Spain, 2018;1022:1026; doi:https:\/\/doi.org\/10.1109\/BIBM.2018.8621203.","DOI":"10.1109\/BIBM.2018.8621203"},{"key":"781_CR22","doi-asserted-by":"crossref","unstructured":"Tao YY, Zhang YZ, Evolutionary synthetic minority oversampling technique with random forest for warfarin dose prediction in Chinese patients, IEEE congress on evolutionary computation(CEC19). New Zealand, 2019.","DOI":"10.1109\/CEC.2019.8789976"},{"key":"781_CR23","doi-asserted-by":"crossref","unstructured":"Hartono, Sitompul OS, Tulus, et.al, Optimization Model of K-Means Clustering Using Artificial Neural Networks to Handle Class Imbalance Problem. IOP Conference Series: Materials Science and Engineering, 2018, 288;012:075.","DOI":"10.1088\/1757-899X\/288\/1\/012075"},{"key":"781_CR24","volume-title":"Experiments in parallel clustering with DBSCAN. International Euro-par Conference Manchester on Parallel Processing","author":"D Arlia","year":"2001","unstructured":"Arlia D, Coppola M. Experiments in parallel clustering with DBSCAN. International Euro-par Conference Manchester on Parallel Processing; 2001."},{"key":"781_CR25","doi-asserted-by":"crossref","unstructured":"Barua S, Islam MM, and Murase K, A Novel Synthetic Minority Oversampling Technique for Imbalanced Data Set Learning. International Conference on Neural Information Processing (ICONIP 2011), 2011; 735:744.","DOI":"10.1007\/978-3-642-24958-7_85"},{"key":"781_CR26","doi-asserted-by":"crossref","unstructured":"Tao Y, Chen YJ, Fu X, et al. Evolutionary ensemble learning algorithm to modeling of warfarin dose prediction for Chinese. IEEE J Biomed Health Informatics. 2018;(23):395:406.","DOI":"10.1109\/JBHI.2018.2812165"},{"key":"781_CR27","doi-asserted-by":"crossref","unstructured":"Tao Y, Chen YJ, Fu X, et al. An Ensemble Model With Clustering Assumption for Warfarin Dose Prediction in Chinese Patients. IEEE J Biomed Health Informatics. 2019;(23):2642:2654.","DOI":"10.1109\/JBHI.2019.2891164"},{"issue":"4","key":"781_CR28","doi-asserted-by":"publisher","first-page":"603:605","DOI":"10.5301\/jn.5000292","volume":"26","author":"IR Logan","year":"2013","unstructured":"Logan IR, Sheerin NS. Anticoagulation and kidney injury: rare observation or common problem? J Nephrol. 2013;26(4):603:605.","journal-title":"J Nephrol"},{"issue":"3","key":"781_CR29","first-page":"311:324","volume":"154","author":"D Keeling","year":"2011","unstructured":"Keeling D, Baglin T, Tait C, et al. Guidelines on oral anticoagulation with warfarin \u2013 fourth edition. Bri J Haematol. 2011;154(3):311:324.","journal-title":"Bri J Haematol"},{"issue":"6","key":"781_CR30","doi-asserted-by":"publisher","first-page":"430:434","DOI":"10.1016\/j.jjcc.2014.02.028","volume":"64","author":"H Matsuo","year":"2014","unstructured":"Matsuo H, Matsumura M, Nakajima Y, et al. Frequency of deep vein thrombosis among hospitalized non-surgical Japanese patients with congestive heart failure. J Cardiol. 2014;64(6):430:434.","journal-title":"J Cardiol"}],"container-title":["BMC Medical Genomics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12920-020-00781-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12920-020-00781-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12920-020-00781-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,10,21]],"date-time":"2021-10-21T19:32:43Z","timestamp":1634844763000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcmedgenomics.biomedcentral.com\/articles\/10.1186\/s12920-020-00781-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10]]},"references-count":30,"journal-issue":{"issue":"S10","published-print":{"date-parts":[[2020,10]]}},"alternative-id":["781"],"URL":"https:\/\/doi.org\/10.1186\/s12920-020-00781-2","relation":{},"ISSN":["1755-8794"],"issn-type":[{"value":"1755-8794","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,10]]},"assertion":[{"value":"22 October 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Not applicable.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"Data freely derived from research group of the First Affiliated Hospital of Soochow University is only for the testing of the machine learning technology on warfarin treatment samples. The authors declare that they have no competing interests.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"152"}}