{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,29]],"date-time":"2025-10-29T13:47:03Z","timestamp":1761745623372,"version":"3.41.2"},"reference-count":92,"publisher":"SAGE Publications","issue":"1","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Health Informatics J"],"published-print":{"date-parts":[[2022,1]]},"abstract":"<jats:p> Re-sampling methods to solve class imbalance problems have shown to improve classification accuracy by mitigating the bias introduced by differences in class size. However, it is possible that a model which uses a specific re-sampling technique prior to Artificial neural networks (ANN) training may not be suitable for aid in classifying varied datasets from the healthcare industry. Five healthcare-related datasets were used across three re-sampling conditions: under-sampling, over-sampling and combi-sampling. Within each condition, different algorithmic approaches were applied to the dataset and the results were statistically analysed for a significant difference in ANN performance. The combi-sampling condition showed that four out of the five datasets did not show significant consistency for the optimal re-sampling technique between the f1-score and Area Under the Receiver Operating Characteristic Curve performance evaluation methods. Contrarily, the over-sampling and under-sampling condition showed all five datasets put forward the same optimal algorithmic approach across performance evaluation methods. Furthermore, the optimal combi-sampling technique (under-, over-sampling and convergence point), were found to be consistent across evaluation measures in only two of the five datasets. This study exemplifies how discrete ANN performances on datasets from the same industry can occur in two ways: how the same re-sampling technique can generate varying ANN performance on different datasets, and how different re-sampling techniques can generate varying ANN performance on the same dataset. <\/jats:p>","DOI":"10.1177\/14604582221087109","type":"journal-article","created":{"date-parts":[[2022,3,31]],"date-time":"2022-03-31T19:23:53Z","timestamp":1648754633000},"update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":3,"title":["Assessing performance of artificial neural networks and re-sampling techniques for healthcare datasets"],"prefix":"10.1177","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9872-1743","authenticated-orcid":false,"given":"Marcia","family":"Saul","sequence":"first","affiliation":[{"name":"Bournemouth University, Poole, UK"}]},{"given":"Shahin","family":"Rostami","sequence":"additional","affiliation":[{"name":"Polyra Limited, Bournemouth, UK"}]}],"member":"179","published-online":{"date-parts":[[2022,3,31]]},"reference":[{"key":"bibr1-14604582221087109","doi-asserted-by":"publisher","DOI":"10.1038\/nature21056"},{"key":"bibr2-14604582221087109","doi-asserted-by":"publisher","DOI":"10.1038\/nmeth.3547"},{"volume-title":"Introduction to Neural Networks in Healthcare","year":"2002","author":"Sordo M","key":"bibr3-14604582221087109"},{"key":"bibr4-14604582221087109","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0212356"},{"volume-title":"Neural Networks for Decision Support Systems: Problems and Opportunities","year":"1991","author":"Schocken S","key":"bibr5-14604582221087109"},{"key":"bibr6-14604582221087109","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4614-8036-5_2"},{"key":"bibr7-14604582221087109","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2008.07.029"},{"key":"bibr8-14604582221087109","doi-asserted-by":"publisher","DOI":"10.3233\/ida-2002-6504"},{"volume-title":"A Combination Scheme for Inductive Learning from Imbalanced Data Sets","year":"2000","author":"Estabrooks A","key":"bibr9-14604582221087109"},{"key":"bibr10-14604582221087109","doi-asserted-by":"publisher","DOI":"10.1111\/j.0824-7935.2004.t01-1-00228.x"},{"key":"bibr11-14604582221087109","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2016.12.035"},{"key":"bibr12-14604582221087109","doi-asserted-by":"publisher","DOI":"10.3390\/ijerph17217923"},{"key":"bibr13-14604582221087109","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2017.01.001"},{"key":"bibr14-14604582221087109","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2013.10.005"},{"key":"bibr15-14604582221087109","doi-asserted-by":"publisher","DOI":"10.3390\/ijerph110909776"},{"key":"bibr16-14604582221087109","doi-asserted-by":"publisher","DOI":"10.1088\/0967-3334\/28\/3\/r01"},{"key":"bibr17-14604582221087109","doi-asserted-by":"publisher","DOI":"10.1109\/tbme.2005.869784"},{"key":"bibr18-14604582221087109","doi-asserted-by":"publisher","DOI":"10.1117\/1.jbo.17.3.037005"},{"key":"bibr19-14604582221087109","doi-asserted-by":"publisher","DOI":"10.1080\/08035250600612280"},{"key":"bibr20-14604582221087109","doi-asserted-by":"publisher","DOI":"10.1111\/j.1468-0394.2010.00520.x"},{"key":"bibr21-14604582221087109","doi-asserted-by":"publisher","DOI":"10.1186\/1472-6947-7-41"},{"key":"bibr22-14604582221087109","doi-asserted-by":"publisher","DOI":"10.1056\/nejmp1006602"},{"volume-title":"The Robot Will See You Now: How Ai Could Revolutionise Nhs","year":"2018","author":"Campbell D","key":"bibr23-14604582221087109"},{"volume-title":"Ai and Healthcare: A Giant Opportunity","year":"2019","author":"Team I","key":"bibr24-14604582221087109"},{"issue":"4","key":"bibr25-14604582221087109","first-page":"1","volume":"52","author":"Kaur H","year":"2019","journal-title":"ACM Comput Surv (Csur)"},{"key":"bibr26-14604582221087109","doi-asserted-by":"publisher","DOI":"10.11591\/ijece.v7i4.pp2215-2222"},{"issue":"2013","key":"bibr27-14604582221087109","first-page":"332","volume":"1","author":"Abd Elrahman SM","year":"2013","journal-title":"J Netw Innovative Comput"},{"key":"bibr28-14604582221087109","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2010.5596486"},{"key":"bibr29-14604582221087109","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2008.03.031"},{"key":"bibr30-14604582221087109","unstructured":"Uci Machine Learning Repository: https:\/\/archive.ics.uci.edu\/ml\/index.php, 2018. URL https:\/\/archive.ics.uci.edu\/ml\/index.php."},{"key":"bibr31-14604582221087109","doi-asserted-by":"publisher","DOI":"10.1016\/b0-08-043076-7\/00449-6"},{"key":"bibr32-14604582221087109","doi-asserted-by":"publisher","DOI":"10.1198\/000313007X172556"},{"volume-title":"Missing Data","year":"2010","author":"Allison PD","key":"bibr33-14604582221087109"},{"key":"bibr34-14604582221087109","doi-asserted-by":"publisher","DOI":"10.22237\/jmasm\/1414814520"},{"key":"bibr35-14604582221087109","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-97982-3\u02d920"},{"key":"bibr36-14604582221087109","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(89)90020-8"},{"key":"bibr37-14604582221087109","doi-asserted-by":"publisher","DOI":"10.1007\/BF02551274"},{"key":"bibr38-14604582221087109","doi-asserted-by":"publisher","DOI":"10.4467\/20838476si.16.004.6185"},{"key":"bibr39-14604582221087109","doi-asserted-by":"publisher","DOI":"10.1137\/16M1080173"},{"volume-title":"Deep Learning","year":"2017","author":"Goodfellow I","key":"bibr40-14604582221087109"},{"key":"bibr41-14604582221087109","first-page":"2121","volume":"12","author":"Duchi J","year":"2011","journal-title":"J Machine Learn Res"},{"issue":"1","key":"bibr42-14604582221087109","first-page":"13","volume":"2","author":"Kaya Y","year":"2013","journal-title":"TEM J"},{"key":"bibr43-14604582221087109","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2008.01.005"},{"key":"bibr44-14604582221087109","unstructured":"Olson RS, Moore JH. Tpot: a tree-based pipeline optimization tool for automating machine learning. In: Workshop on automatic machine learning, New York, NY, USA, 24 Jun 2016. PMLR, pp. 66\u201374."},{"key":"bibr45-14604582221087109","unstructured":"Costa E, Lorena A, Carvalho A, et al. A review of performance evaluation measures for hierarchical classifiers. In: Evaluation Methods for machine Learning II: papers from the AAAI-2007 Workshop, San Francisco, California, USA, February 4-9 2017, pp. 1\u20136."},{"key":"bibr46-14604582221087109","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2008.08.010"},{"key":"bibr47-14604582221087109","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2009.03.002"},{"key":"bibr48-14604582221087109","unstructured":"Under-sampling - imbalanced learn 0.5.0 documentation, 2010. URL https:\/\/imbalanced-learn.readthedocs.io\/en\/stable\/under\u02d9sampling.html"},{"key":"bibr49-14604582221087109","doi-asserted-by":"publisher","DOI":"10.1613\/jair.953"},{"key":"bibr50-14604582221087109","unstructured":"He H, Bai Y, Garcia EA, et al. Adasyn: adaptive synthetic sampling approach for imbalanced learning. In: 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence), Hong Kong, 1\u20138 June 2008. IEEE, pp. 1322\u20131328."},{"key":"bibr51-14604582221087109","unstructured":"Over-sampling - imbalanced learn 0.5.0 documentation, 2009. URL https:\/\/imbalanced-learn.readthedocs.io\/en\/stable\/over\u02d9sampling.html."},{"key":"bibr52-14604582221087109","doi-asserted-by":"publisher","DOI":"10.1038\/35016072"},{"key":"bibr53-14604582221087109","unstructured":"Sharma S. Activation functions in neural networks, 2017. URL: https:\/\/towardsdatascience.com\/activation-functions-neural-networks-1cbd9f8d91d6."},{"key":"bibr54-14604582221087109","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-59497-3_175"},{"key":"bibr55-14604582221087109","doi-asserted-by":"publisher","DOI":"10.1016\/b978-0-12-802581-9.00007-x"},{"key":"bibr56-14604582221087109","unstructured":"Hinton GE, Krizhevsky A, Sutskever I, et al. System and method for addressing overfitting in a neural network. US Patent 9,406,017, 2016."},{"key":"bibr57-14604582221087109","doi-asserted-by":"publisher","DOI":"10.1007\/s00365-006-0663-2"},{"key":"bibr58-14604582221087109","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0118432"},{"key":"bibr59-14604582221087109","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2005.50"},{"key":"bibr60-14604582221087109","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2005.10.010"},{"key":"bibr61-14604582221087109","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1951.10500769"},{"key":"bibr62-14604582221087109","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-4380-9_16"},{"key":"bibr63-14604582221087109","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1937.10503522"},{"key":"bibr64-14604582221087109","first-page":"117","volume-title":"Proceedings of the Fourth Australian Knowledge Acquisition Workshop","author":"Brain D","year":"2000"},{"volume-title":"Better Deep Learning: Train Faster, Reduce Overfitting, and Make Better Predictions","year":"2018","author":"Brownlee J","key":"bibr65-14604582221087109"},{"key":"bibr66-14604582221087109","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-30132-5_103"},{"key":"bibr67-14604582221087109","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511921803"},{"key":"bibr68-14604582221087109","doi-asserted-by":"publisher","DOI":"10.1007\/s10844-015-0368-1"},{"volume-title":"Survey of Resampling Techniques for Improving Classification Performance in Unbalanced Datasets","year":"2016","author":"More A","key":"bibr69-14604582221087109"},{"issue":"5","key":"bibr70-14604582221087109","first-page":"1","volume":"1","author":"Sasaki Y","year":"2007","journal-title":"Teach Tutor Mater"},{"key":"bibr71-14604582221087109","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-86514-6_1"},{"key":"bibr72-14604582221087109","unstructured":"Kerr K, Norris T, Stockdale R. Data quality information and decision making: a healthcare case study. In: ACIS 2007 Proceedings, Toowoomba, 5\u20137 December 2007, p. 98."},{"key":"bibr73-14604582221087109","doi-asserted-by":"publisher","DOI":"10.1145\/2808797.2809367"},{"key":"bibr74-14604582221087109","doi-asserted-by":"publisher","DOI":"10.1109\/4235.585893"},{"volume-title":"Generalization in Deep Learning","year":"2017","author":"Kawaguchi K","key":"bibr75-14604582221087109"},{"key":"bibr76-14604582221087109","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4471-0123-9_3"},{"key":"bibr77-14604582221087109","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00793"},{"key":"bibr78-14604582221087109","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1992.4.1.1"},{"key":"bibr79-14604582221087109","first-page":"769","volume":"6","author":"Tomek I","year":"1976","journal-title":"IEEE Trans Systems, Man Cybernetics"},{"key":"bibr80-14604582221087109","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-13278-0_39"},{"key":"bibr81-14604582221087109","doi-asserted-by":"publisher","DOI":"10.1145\/1299015.1299021"},{"key":"bibr82-14604582221087109","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2002.802012"},{"key":"bibr83-14604582221087109","doi-asserted-by":"crossref","unstructured":"Forman G, Cohen I. Learning from little: comparison of classifiers given little training. In: European Conference on Principles of Data Mining and Knowledge Discovery, Pisa, Italy, & September 20-24, 2004. Springer, pp. 161\u2013172.","DOI":"10.1007\/978-3-540-30116-5_17"},{"key":"bibr84-14604582221087109","unstructured":"Minaei-Bidgoli B, Topchy AP, Punch WF. A comparison of resampling methods for clustering ensembles. In: IC-AI, Las Vegas, Nevada, USA, 21\u201324 June 2004, pp. 939\u2013945."},{"key":"bibr85-14604582221087109","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/bti499"},{"key":"bibr86-14604582221087109","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-23878-9_3"},{"key":"bibr87-14604582221087109","doi-asserted-by":"publisher","DOI":"10.1007\/s11269-015-1114-8"},{"key":"bibr88-14604582221087109","doi-asserted-by":"publisher","DOI":"10.1080\/07474938.2010.481556"},{"key":"bibr89-14604582221087109","doi-asserted-by":"publisher","DOI":"10.1145\/270572.270573"},{"key":"bibr90-14604582221087109","doi-asserted-by":"publisher","DOI":"10.1016\/S0933-3657(01)00077-X"},{"key":"bibr91-14604582221087109","doi-asserted-by":"publisher","DOI":"10.21037\/atm.2018.05.32"},{"key":"bibr92-14604582221087109","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocy068"}],"container-title":["Health Informatics Journal"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/14604582221087109","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/14604582221087109","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/14604582221087109","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,2]],"date-time":"2025-03-02T08:35:30Z","timestamp":1740904530000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/14604582221087109"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1]]},"references-count":92,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2022,1]]}},"alternative-id":["10.1177\/14604582221087109"],"URL":"https:\/\/doi.org\/10.1177\/14604582221087109","relation":{},"ISSN":["1460-4582","1741-2811"],"issn-type":[{"type":"print","value":"1460-4582"},{"type":"electronic","value":"1741-2811"}],"subject":[],"published":{"date-parts":[[2022,1]]},"article-number":"14604582221087109"}}