{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,10]],"date-time":"2026-01-10T19:48:33Z","timestamp":1768074513229,"version":"3.49.0"},"reference-count":32,"publisher":"Springer Science and Business Media LLC","issue":"1","content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Med Inform Decis Mak"],"published-print":{"date-parts":[[2017,12]]},"DOI":"10.1186\/s12911-017-0522-5","type":"journal-article","created":{"date-parts":[[2017,8,14]],"date-time":"2017-08-14T08:35:53Z","timestamp":1502699753000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":20,"title":["Enhancement of hepatitis virus immunoassay outcome predictions in imbalanced routine pathology data by data balancing and feature selection before the application of support vector machines"],"prefix":"10.1186","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7084-1524","authenticated-orcid":false,"given":"Alice M.","family":"Richardson","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Brett A.","family":"Lidbury","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2017,8,14]]},"reference":[{"key":"522_CR1","volume-title":"GLOBOCAN 2008 v1.2, cancer incidence and mortality worldwide: IARC CancerBase 10","author":"J Ferlay","year":"2010","unstructured":"Ferlay J, Shin HR, Bray F, Forman D, Mathers C, Parkin DM. GLOBOCAN 2008 v1.2, cancer incidence and mortality worldwide: IARC CancerBase 10. Lyon: International Agency for Research on Cancer; 2010."},{"key":"522_CR2","doi-asserted-by":"crossref","first-page":"1264","DOI":"10.1053\/j.gastro.2011.12.061","volume":"142","author":"HB El-Serag","year":"2012","unstructured":"El-Serag HB. Epidemiology of viral hepatitis and hepatocellular carcinoma. Gastro. 2012;142:1264\u201373.","journal-title":"Gastro"},{"key":"522_CR3","doi-asserted-by":"crossref","first-page":"206","DOI":"10.1186\/1471-2105-14-206","volume":"14","author":"AM Richardson","year":"2013","unstructured":"Richardson AM, Lidbury BA. Infection status outcome, machine learning method and virus type interact to affect the optimised prediction of hepatitis B and C virus immunoassay results from routine pathology laboratory assays in unbalanced data sets. BMC Bioinfo. 2013;14:206\u201313.","journal-title":"BMC Bioinfo"},{"key":"522_CR4","volume-title":"Statistical learning theory","author":"V Vapnik","year":"1998","unstructured":"Vapnik V. Statistical learning theory. New York: Wiley; 1998."},{"key":"522_CR5","doi-asserted-by":"crossref","first-page":"199","DOI":"10.1023\/B:STCO.0000035301.49549.88","volume":"14","author":"AJ Smola","year":"2004","unstructured":"Smola AJ, Sch\u00f6lkopf B. A tutorial on support vector regression. Stat Comput. 2004;14:199\u2013222.","journal-title":"Stat Comput"},{"key":"522_CR6","doi-asserted-by":"crossref","first-page":"1132","DOI":"10.1093\/bioinformatics\/btg102","volume":"19","author":"Y Lee","year":"2003","unstructured":"Lee Y, Lee CK. Classification of multiple cancer types by multicategory support vector machines using gene expression data. Bioinfo. 2003;19:1132\u20139.","journal-title":"Bioinfo"},{"key":"522_CR7","doi-asserted-by":"crossref","first-page":"679","DOI":"10.1016\/S0301-5629(02)00788-3","volume":"29","author":"RF Chang","year":"2003","unstructured":"Chang RF, Wu WJ, Moon WK, Chen DR. Improvement in breast tumor discrimination by support vector machines and speckle-emphasis texture analysis. Ultrasound Med Biol. 2003;29:679\u201386.","journal-title":"Ultrasound Med Biol"},{"key":"522_CR8","doi-asserted-by":"crossref","first-page":"220","DOI":"10.1016\/j.eswa.2016.12.035","volume":"73","author":"G Haixiang","year":"2017","unstructured":"Haixiang G, Yijing L, Shang J, Mingyun G, Yuanyue H, Bing G. Learning from class-imbalanced data: review of methods and applications. Expert Syst Appl. 2017;73:220\u201339.","journal-title":"Expert Syst Appl"},{"key":"522_CR9","doi-asserted-by":"crossref","first-page":"220","DOI":"10.1016\/j.neuroimage.2013.10.005","volume":"87","author":"R Dubey","year":"2014","unstructured":"Dubey R, Zhou J, Wang Y, Thompson PM, Ye J, for the Alzheimer\u2019s Disease Neuroimaging Inititative. Analysis of sampling techniques for imbalanced data: an n = 648 ADNI study. NeuroImage. 2014;87:220\u201341.","journal-title":"NeuroImage"},{"key":"522_CR10","doi-asserted-by":"crossref","first-page":"523","DOI":"10.1186\/1471-2105-11-523","volume":"11","author":"R Blagus","year":"2010","unstructured":"Blagus R, Lusa L. Class prediction for high-dimensional imbalanced data. BMC Bioinfo. 2010;11:523.","journal-title":"BMC Bioinfo"},{"key":"522_CR11","doi-asserted-by":"crossref","first-page":"554","DOI":"10.1016\/j.asoc.2013.08.014","volume":"14","author":"B Krawzcyk","year":"2014","unstructured":"Krawzcyk B, Wozniak M, Schaefer G. Cost-sensitive decision tree ensembles for effective imbalanced classification. Appl Soft Comput. 2014;14:554\u201362.","journal-title":"Appl Soft Comput"},{"key":"522_CR12","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1016\/j.compmedimag.2013.12.003","volume":"38","author":"P Cao","year":"2014","unstructured":"Cao P, Yang J, Li W, Zhao D, Zaiane O. Ensemble-based hybrid probabilistic sampling for imbalanced data learning in lung nodule CAD. Comput Med Imaging Graph. 2014;38:137\u201350.","journal-title":"Comput Med Imaging Graph"},{"key":"522_CR13","doi-asserted-by":"crossref","first-page":"885","DOI":"10.1007\/s10044-015-0458-2","volume":"19","author":"V Vigneron","year":"2016","unstructured":"Vigneron V, Chen H. A multi-scale seriation algorithm for clustering sparse imbalanced data: application to spike sorting. Pattern Anal Applic. 2016;19:885\u2013903.","journal-title":"Pattern Anal Applic"},{"key":"522_CR14","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1145\/1007730.1007739","volume":"6","author":"B Raskutti","year":"2004","unstructured":"Raskutti B, Kowalczyk A. Extreme re-balancing for SVMs: a case study. ACM SIGKDD Explorations Newsletter. 2004;6:60\u20139.","journal-title":"ACM SIGKDD Explorations Newsletter"},{"key":"522_CR15","doi-asserted-by":"crossref","first-page":"429","DOI":"10.3233\/IDA-2002-6504","volume":"6","author":"N Japkowicz","year":"2002","unstructured":"Japkowicz N, Stephen S. The class imbalance problem: a systematic study. Intell Data Anal. 2002;6:429\u201349.","journal-title":"Intell Data Anal"},{"key":"522_CR16","unstructured":"Drummond C, Holte RC. C4.5, class imbalance and cost sensitivity: why under-sampling beats over-sampling. In Workshop on Learning from Imbalanced Data Sets II, ICML Washington DC, USA, 2003. http:\/\/www.site.uottawa.ca\/~nat\/Workshop2003\/schedule.html . Accessed 15 May 2016."},{"key":"522_CR17","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1613\/jair.953","volume":"16","author":"N Chawla","year":"2002","unstructured":"Chawla N, Bowyer K, Hall L, Kegelmeyer W. SMOTE: synthetic minority oversampling technique. J Artif Intell Res. 2002;16:321\u201357.","journal-title":"J Artif Intell Res"},{"issue":"3","key":"522_CR18","doi-asserted-by":"crossref","first-page":"1","DOI":"10.3310\/hta17030","volume":"17","author":"D Harrison","year":"2013","unstructured":"Harrison D, Muskett H, Harvey S, Grieve R, Shahin J, Patel K, et al. Development and validation of a risk model for identification of non-neutropenic, critically ill adult patients at high risk of invasive Candida infection: the fungal infection risk evaluation (FIRE) study. Health Technol Assess. 2013;17(3):1\u2013156.","journal-title":"Health Technol Assess"},{"key":"522_CR19","doi-asserted-by":"crossref","first-page":"2507","DOI":"10.1093\/bioinformatics\/btm344","volume":"23","author":"Y Saeys","year":"2007","unstructured":"Saeys Y, Inza I, Larranaga P. A review of feature selection techniques in bioinformatics. Bioinfo. 2007;23:2507\u201317.","journal-title":"Bioinfo"},{"key":"522_CR20","volume-title":"Classification and regression trees","author":"L Breiman","year":"1984","unstructured":"Breiman L, Friedman JH, Olshen RA, Stone CJ. Classification and regression trees. Belmont: Wadsworth; 1984."},{"key":"522_CR21","doi-asserted-by":"crossref","first-page":"1334","DOI":"10.1002\/jmv.23609","volume":"85","author":"G Shang","year":"2013","unstructured":"Shang G, Richardson A, Gahan ME, Esteal S, Ohms S, Lidbury BA. Predicting the presence of hepatitis B virus surface antigen in Chinese patients by pathology data mining. J Med Virol. 2013;85:1334\u20139.","journal-title":"J Med Virol"},{"key":"522_CR22","unstructured":"Faisal S. Missing data in pathology databases. Unpublished Masters thesis, University of Canberra, 2011."},{"key":"522_CR23","doi-asserted-by":"crossref","DOI":"10.1201\/b10328","volume-title":"Data mining with R: learning with case studies","author":"L Torgo","year":"2010","unstructured":"Torgo L. Data mining with R: learning with case studies. Boca Raton FL: CRC Press; 2010."},{"key":"522_CR24","unstructured":"R Development Core Team. R: A Language and Environment for Statistical Computing. R Foundation for Statistical Computing. 2015. https:\/\/www.r-project.org\/ . Accessed 15 May 2016."},{"key":"522_CR25","first-page":"18","volume":"2","author":"A Liaw","year":"2002","unstructured":"Liaw A, Wiener M. Classification and regression by randomForest. R News. 2002;2:18\u201322.","journal-title":"R News"},{"key":"522_CR26","doi-asserted-by":"publisher","unstructured":"Karatzoglou A, Meyer D, Hornik K. Support vector machines in R. J Stat Soft. 2006; doi: 10.18637\/jss\/v015\/i09 .","DOI":"10.18637\/jss\/v015\/i09"},{"key":"522_CR27","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4419-9890-3","volume-title":"Data mining with rattle and R","author":"G Williams","year":"2011","unstructured":"Williams G. Data mining with rattle and R. New York: Springer; 2011."},{"key":"522_CR28","doi-asserted-by":"crossref","first-page":"819","DOI":"10.1089\/10665270050514954","volume":"7","author":"MK Kerr","year":"2000","unstructured":"Kerr MK, Martin M, Churchill GA. Analysis of variance for gene expression microarray data. J Comp Biol. 2000;7:819\u201337.","journal-title":"J Comp Biol"},{"key":"522_CR29","doi-asserted-by":"crossref","first-page":"1832","DOI":"10.1002\/hep.27750","volume":"61","author":"MA Konerman","year":"2015","unstructured":"Konerman MA, Zhang Y, Higgins PDR, Lok ASF, Waljee AK. Improvement of predictive models of risk of disease progression in chronic hepatitis C by incorporating longitudinal data. Hepatology. 2015;61:1832\u201341.","journal-title":"Hepatology"},{"key":"522_CR30","unstructured":"Australian Institute of Health and Welfare (AIHW). Chronic diseases and associated risk factors in Australia, 2001. Canberra: AIHW. p. 2002."},{"key":"522_CR31","doi-asserted-by":"crossref","first-page":"345","DOI":"10.1017\/S026988891300043X","volume":"29","author":"SS Khan","year":"2013","unstructured":"Khan SS, Madden MG. One-class classification: taxonomy of study and review of techniques. Knowledge Eng Rev. 2013;29:345\u201374.","journal-title":"Knowledge Eng Rev"},{"key":"522_CR32","first-page":"172","volume":"10","author":"S Dreiseitl","year":"2010","unstructured":"Dreiseitl S, Osl M, Scheibb\u00f6ck C, Binder M. Outlier detection with one-class SVMs: an application to melanoma prognosis. Proc AMIA Symp. 2010;10:172\u20136.","journal-title":"Proc AMIA Symp"}],"container-title":["BMC Medical Informatics and Decision Making"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s12911-017-0522-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,10,2]],"date-time":"2019-10-02T07:24:44Z","timestamp":1570001084000},"score":1,"resource":{"primary":{"URL":"http:\/\/bmcmedinformdecismak.biomedcentral.com\/articles\/10.1186\/s12911-017-0522-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,8,14]]},"references-count":32,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2017,12]]}},"alternative-id":["522"],"URL":"https:\/\/doi.org\/10.1186\/s12911-017-0522-5","relation":{},"ISSN":["1472-6947"],"issn-type":[{"value":"1472-6947","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,8,14]]},"article-number":"121"}}