{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T13:10:52Z","timestamp":1780405852099,"version":"3.54.1"},"reference-count":31,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2017,12,1]],"date-time":"2017-12-01T00:00:00Z","timestamp":1512086400000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"name":"NSW Office Of Health and Medical Research (AUS)","award":["RG14\/11"],"award-info":[{"award-number":["RG14\/11"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Health Inf Sci Syst"],"published-print":{"date-parts":[[2017,12]]},"DOI":"10.1007\/s13755-017-0039-4","type":"journal-article","created":{"date-parts":[[2017,12,6]],"date-time":"2017-12-06T17:30:34Z","timestamp":1512581434000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":20,"title":["The effect of imputing missing clinical attribute values on training lung cancer survival prediction model performance"],"prefix":"10.1007","volume":"5","author":[{"given":"Mohamed S.","family":"Barakat","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6169-6721","authenticated-orcid":false,"given":"Matthew","family":"Field","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aditya","family":"Ghose","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David","family":"Stirling","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lois","family":"Holloway","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shalini","family":"Vinod","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andre","family":"Dekker","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David","family":"Thwaites","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2017,12,6]]},"reference":[{"key":"39_CR1","unstructured":"WHO. Estimated cancer incidence, mortality and prevalence worldwide in 2012. International Agency for Cancer Research. 2016. http:\/\/globocan.iarc.fr\/Pages\/fact_sheets_cancer.aspx?cancer=lung . Accessed 05 Dec 2016."},{"key":"39_CR2","unstructured":"Key statistics for lung cancer. American Cancer Society. 2016. http:\/\/www.cancer.org\/cancer\/lungcancer-non-smallcell\/detailedguide\/non-small-cell-lung-cancer-key-statistics . Accessed 07 Dec 2016."},{"issue":"1","key":"39_CR3","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1016\/j.radonc.2014.08.013","volume":"113","author":"A Dekker","year":"2014","unstructured":"Dekker A, et al. Rapid learning in practice: a lung cancer survival decision support system in routine patient care data. Radiother Oncol. 2014;113(1):47\u201353.","journal-title":"Radiother Oncol"},{"issue":"27","key":"39_CR4","doi-asserted-by":"crossref","first-page":"4268","DOI":"10.1200\/JCO.2010.28.5478","volume":"28","author":"AP Abernethy","year":"2010","unstructured":"Abernethy AP, et al. Rapid-learning system for cancer care. J Clin Oncol. 2010;28(27):4268\u201374.","journal-title":"J Clin Oncol"},{"key":"39_CR5","volume-title":"Encyclopedia of machine learning","author":"C Sammut","year":"2011","unstructured":"Sammut C, Webb GI. Encyclopedia of machine learning. Berlin: Springer; 2011."},{"key":"39_CR6","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1016\/j.aca.2012.11.007","volume":"760","author":"C Beleites","year":"2013","unstructured":"Beleites C, Neugebauer U, Bocklitz T, Krafft C, Popp J. Sample size planning for classification models. Anal Chim Acta. 2013;760:25\u201333.","journal-title":"Anal Chim Acta"},{"key":"39_CR7","doi-asserted-by":"crossref","first-page":"125","DOI":"10.1016\/j.compbiomed.2015.02.006","volume":"59","author":"PJ Garc\u00eda-Laencina","year":"2015","unstructured":"Garc\u00eda-Laencina PJ, Abreu PH, Abreu MH, Afonoso N. Missing data imputation on the 5-year survival prediction of breast cancer patients with unknown discrete values. Comput Biol Med. 2015;59:125\u201333.","journal-title":"Comput Biol Med"},{"issue":"4","key":"39_CR8","doi-asserted-by":"crossref","first-page":"1401","DOI":"10.1118\/1.3352709","volume":"37","author":"K Jayasurya","year":"2010","unstructured":"Jayasurya K, et al. Comparison of Bayesian network and support vector machine models for two-year survival prediction in lung cancer patients treated with radiotherapy. Med Phys. 2010;37(4):1401.","journal-title":"Med Phys"},{"issue":"2","key":"39_CR9","doi-asserted-by":"crossref","first-page":"263","DOI":"10.1007\/s00521-009-0295-6","volume":"19","author":"PJ Garc\u00eda-Laencina","year":"2009","unstructured":"Garc\u00eda-Laencina PJ, Sancho-G\u00f3mez J-L, Figueiras-Vidal AR. Pattern classification with missing data: a review. Neural Comput Appl. 2009;19(2):263\u201382.","journal-title":"Neural Comput Appl"},{"key":"39_CR10","doi-asserted-by":"crossref","first-page":"b2393","DOI":"10.1136\/bmj.b2393","volume":"338","author":"JAC Sterne","year":"2009","unstructured":"Sterne JAC, et al. Multiple imputation for missing data in epidemiological and clinical research: potential and pitfalls. BMJ. 2009;338:b2393.","journal-title":"BMJ"},{"issue":"3","key":"39_CR11","doi-asserted-by":"crossref","first-page":"459","DOI":"10.1016\/j.radonc.2016.10.002","volume":"121","author":"A Jochems","year":"2016","unstructured":"Jochems A, et al. Distributed learning: developing a predictive model based on data from multiple hospitals without data leaving the hospital\u2014a real life proof of concept. Radiother Oncol. 2016;121(3):459\u201367.","journal-title":"Radiother Oncol"},{"issue":"5","key":"39_CR12","doi-asserted-by":"crossref","first-page":"1127","DOI":"10.1016\/j.ijrobp.2015.07.2286","volume":"93","author":"J Kang","year":"2015","unstructured":"Kang J, Schwartz R, Flickinger J, Beriwal S. Machine learning approaches for predicting radiation therapy outcomes: a clinician\u2019s perspective. Int J Radiat Oncol. 2015;93(5):1127\u201335.","journal-title":"Int J Radiat Oncol"},{"issue":"1","key":"39_CR13","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1016\/S0377-2217(02)00578-7","volume":"151","author":"A Olinsky","year":"2003","unstructured":"Olinsky A, Chen S, Harlow L. The comparative efficacy of imputation methods for missing data in structural equation modeling. Eur J Oper Res. 2003;151(1):53\u201379.","journal-title":"Eur J Oper Res"},{"issue":"9","key":"39_CR14","doi-asserted-by":"crossref","first-page":"979","DOI":"10.1016\/j.jclinepi.2007.03.003","volume":"60","author":"EW Steyerberg","year":"2007","unstructured":"Steyerberg EW, van Veen M. Imputation is beneficial for handling missing data in predictive models. J Clin Epidemiol. 2007;60(9):979.","journal-title":"J Clin Epidemiol"},{"key":"39_CR15","doi-asserted-by":"crossref","unstructured":"Opitz D, Maclin R (1999) Popular ensemble methods: an empirical study. http:\/\/jair.org\/papers\/paper614.html . Accessed 24 Oct 2016.","DOI":"10.1613\/jair.614"},{"issue":"1\u20132","key":"39_CR16","first-page":"1","volume":"33","author":"L Rokach","year":"2009","unstructured":"Rokach L. Ensemble-based classifiers. Artif Intell Rev. 2009;33(1\u20132):1\u201339.","journal-title":"Artif Intell Rev"},{"issue":"3","key":"39_CR17","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1109\/MCAS.2006.1688199","volume":"6","author":"R Polikar","year":"2006","unstructured":"Polikar R. Ensemble based systems in decision making. IEEE Circuits Syst Mag. 2006;6(3):21\u201345.","journal-title":"IEEE Circuits Syst Mag."},{"issue":"1","key":"39_CR18","doi-asserted-by":"crossref","first-page":"1","DOI":"10.2200\/S00240ED1V01Y200912DMK002","volume":"2","author":"G Seni","year":"2010","unstructured":"Seni G, Elder JF. Ensemble methods in data mining: improving accuracy through combining predictions. Synth Lect Data Min Knowl Discov. 2010;2(1):1\u2013126.","journal-title":"Synth Lect Data Min Knowl Discov"},{"issue":"404","key":"39_CR19","doi-asserted-by":"crossref","first-page":"1198","DOI":"10.1080\/01621459.1988.10478722","volume":"83","author":"RJ Little","year":"1988","unstructured":"Little RJ. A test of missing completely at random for multivariate data with missing values. J Am Stat Assoc. 1988;83(404):1198\u2013202.","journal-title":"J Am Stat Assoc"},{"issue":"3","key":"39_CR20","doi-asserted-by":"crossref","first-page":"581","DOI":"10.1093\/biomet\/63.3.581","volume":"63","author":"DB Rubin","year":"1976","unstructured":"Rubin DB. Inference and missing data. Biometrika. 1976;63(3):581\u201392.","journal-title":"Biometrika"},{"key":"39_CR21","volume-title":"Multiple imputation for nonresponse in surveys","author":"DB Rubin","year":"2004","unstructured":"Rubin DB. Multiple imputation for nonresponse in surveys, vol. 81. New York: Wiley; 2004."},{"issue":"1","key":"39_CR22","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s10044-014-0411-9","volume":"18","author":"M Aste","year":"2014","unstructured":"Aste M, Boninsegna M, Freno A, Trentin E. Techniques for dealing with incomplete data: a tutorial and survey. Pattern Anal Appl. 2014;18(1):1\u201329.","journal-title":"Pattern Anal Appl"},{"key":"39_CR23","unstructured":"Rahman G, Islam Z. A decision tree-based missing value imputation technique for data pre-processing. In: Proceedings of the ninth Australasian data mining conference\u2014volume 121, Darlinghurst, Australia, 2011, p. 41\u201350."},{"issue":"3","key":"39_CR24","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1177\/1758834011401951","volume":"3","author":"T Berghmans","year":"2011","unstructured":"Berghmans T, Paesmans M, Sculier J-P. Prognostic factors in stage III non-small cell lung cancer: a review of conventional, metabolic and new biological variables. Ther Adv Med Oncol. 2011;3(3):127\u201338.","journal-title":"Ther Adv Med Oncol"},{"issue":"4","key":"39_CR25","doi-asserted-by":"crossref","first-page":"935","DOI":"10.1016\/j.ijrobp.2015.02.048","volume":"92","author":"C Oberije","year":"2015","unstructured":"Oberije C, et al. A Validated prediction model for overall survival from stage iii non-small cell lung cancer: toward survival prediction for individual patients. Int J Radiat Oncol. 2015;92(4):935\u201344.","journal-title":"Int J Radiat Oncol"},{"issue":"1","key":"39_CR26","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1145\/1656274.1656278","volume":"11","author":"Mark Hall","year":"2009","unstructured":"Hall Mark, Frank Eibe, Holmes Geoffrey, Pfahringer Bernhard, Reutemann Peter, Witten Ian H. The WEKA data mining software: an update. SIGKDD Explor. 2009;11(1):10\u20138.","journal-title":"SIGKDD Explor"},{"key":"39_CR27","doi-asserted-by":"crossref","DOI":"10.4324\/9781315806167","volume-title":"Signal detection theory and ROC analysis in psychology and diagnostics: collected papers","author":"JA Swets","year":"2014","unstructured":"Swets JA. Signal detection theory and ROC analysis in psychology and diagnostics: collected papers. New York: Psychology Press; 2014."},{"key":"39_CR28","doi-asserted-by":"crossref","unstructured":"Caruana R, Niculescu-Mizil A. An empirical comparison of supervised learning algorithms. In: Proceedings of the 23rd international conference on machine learning, New York, NY, USA, 2006, p. 161\u2013168.","DOI":"10.1145\/1143844.1143865"},{"key":"39_CR29","unstructured":"MATLAB and Statistics Toolbox Release 2015a. Natick: The MathWorks, Inc."},{"key":"39_CR30","unstructured":"IBM SPSS Statistics for Macintosh. Armonk, NY: IBM Corp; 2013."},{"issue":"1","key":"39_CR31","doi-asserted-by":"crossref","first-page":"101","DOI":"10.1007\/s10182-008-0053-6","volume":"92","author":"D Schunk","year":"2008","unstructured":"Schunk D. A Markov chain Monte Carlo algorithm for multiple imputation in large surveys. AStA Adv Stat Anal. 2008;92(1):101\u201314.","journal-title":"AStA Adv Stat Anal"}],"container-title":["Health Information Science and Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s13755-017-0039-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s13755-017-0039-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s13755-017-0039-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,10,23]],"date-time":"2020-10-23T22:45:54Z","timestamp":1603493154000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s13755-017-0039-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,12]]},"references-count":31,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2017,12]]}},"alternative-id":["39"],"URL":"https:\/\/doi.org\/10.1007\/s13755-017-0039-4","relation":{},"ISSN":["2047-2501"],"issn-type":[{"value":"2047-2501","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,12]]},"article-number":"16"}}