{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,26]],"date-time":"2026-09-26T19:00:47Z","timestamp":1790449247848,"version":"4.1.0"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2025,3,20]],"date-time":"2025-03-20T00:00:00Z","timestamp":1742428800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,3,20]],"date-time":"2025-03-20T00:00:00Z","timestamp":1742428800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"European Union\u2019s Horizon 2020 research and innovation programme","award":["No 874739, LongITools"],"award-info":[{"award-number":["No 874739, LongITools"]}]},{"DOI":"10.13039\/501100005774","name":"Universitat de Barcelona","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100005774","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Healthc Inform Res"],"published-print":{"date-parts":[[2025,9]]},"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>Machine learning classifiers in healthcare tend to reproduce or exacerbate existing health disparities due to inherent biases in training data. This relevant issue has brought the attention of researchers in both healthcare and other domains, proposing techniques that deal with it in different stages of the machine learning process. Post-processing methods adjust model predictions to ensure fairness without interfering in the learning process nor requiring access to the original training data, preserving privacy and enabling the application to any trained model. This study rigorously compares state-of-the-art debiasing methods within the family of post-processing techniques across a wide range of synthetic and real-world (healthcare) datasets, by means of different performance and fairness metrics. Our experiments reveal the strengths and weaknesses of each method, examining the trade-offs between group fairness and predictive performance, as well as among different notions of group fairness. Additionally, we analyze the impact on untreated attributes to ensure overall bias mitigation. Our comprehensive evaluation provides insights into how these debiasing methods can be optimally implemented in healthcare settings to balance accuracy and fairness.<\/jats:p>","DOI":"10.1007\/s41666-025-00196-7","type":"journal-article","created":{"date-parts":[[2025,3,21]],"date-time":"2025-03-21T00:58:58Z","timestamp":1742518738000},"page":"465-493","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Empirical Comparison of Post-processing Debiasing Methods for Machine Learning Classifiers in Healthcare"],"prefix":"10.1007","volume":"9","author":[{"given":"Vien Ngoc","family":"Dang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"V\u00edctor M.","family":"Campello","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jer\u00f3nimo","family":"Hern\u00e1ndez-Gonz\u00e1lez","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Karim","family":"Lekadir","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,3,20]]},"reference":[{"key":"196_CR1","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1146\/annurev-biodatasci-092820-114757","volume":"4","author":"IY Chen","year":"2021","unstructured":"Chen IY et al (2021) Ethical machine learning in healthcare. Ann Rev Biomed Data Sci 4:123\u2013144","journal-title":"Ann Rev Biomed Data Sci"},{"key":"196_CR2","doi-asserted-by":"publisher","first-page":"2176","DOI":"10.1038\/s41591-021-01595-0","volume":"27","author":"L Seyyed-Kalantari","year":"2021","unstructured":"Seyyed-Kalantari L et al (2021) Underdiagnosis bias of artificial intelligence algorithms applied to chest radiographs in under-served patient populations. Nat Med 27:2176\u20132182","journal-title":"Nat Med"},{"key":"196_CR3","doi-asserted-by":"publisher","first-page":"7848","DOI":"10.1038\/s41598-024-58427-7","volume":"14","author":"VN Dang","year":"2024","unstructured":"Dang VN et al (2024) Fairness and bias correction in machine learning for depression prediction across four study populations. Sci Rep 14:7848","journal-title":"Sci Rep"},{"key":"196_CR4","unstructured":"Chen IY et al (2018) Why is my classifier discriminatory? In: Proceedings of the 32nd international conference on Neural Information Processing Systems (NIPS\u201918), pp 3543\u20133554. Curran Associates Inc., Red Hook, NY, USA"},{"issue":"4","key":"196_CR5","doi-asserted-by":"publisher","first-page":"213909","DOI":"10.1001\/jamanetworkopen.2021.3909","volume":"4","author":"Y Park","year":"2021","unstructured":"Park Y et al (2021) Comparison of methods to reduce bias from clinical prediction models of postpartum depression. JAMA Netw Open 4(4):213909","journal-title":"JAMA Netw Open"},{"key":"196_CR6","doi-asserted-by":"publisher","first-page":"219","DOI":"10.1503\/jpn.150205","volume":"40","author":"RP Albert","year":"2015","unstructured":"Albert RP (2015) Why is depression more prevalent in women? J Psychiatry Neurosci 40:219\u2013221","journal-title":"J Psychiatry Neurosci"},{"issue":"2","key":"196_CR7","doi-asserted-by":"publisher","first-page":"120","DOI":"10.1089\/big.2016.0048","volume":"5","author":"B d\u2019Alessandro","year":"2017","unstructured":"d\u2019Alessandro B et al (2017) Conscientious classification: a data scientist\u2019s guide to discrimination-aware classification. Big Data 5(2):120\u2013134","journal-title":"Big Data"},{"issue":"5","key":"196_CR8","doi-asserted-by":"publisher","first-page":"36388","DOI":"10.2196\/36388","volume":"10","author":"J Huang","year":"2022","unstructured":"Huang J, Galal G, Etemadi M, Vaidyanathan M (2022) Evaluation and mitigation of racial bias in clinical machine learning models: scoping review. JMIR Med Inform 10(5):36388","journal-title":"JMIR Med Inform"},{"issue":"11","key":"196_CR9","doi-asserted-by":"publisher","first-page":"0000651","DOI":"10.1371\/journal.pdig.0000651","volume":"3","author":"JL Cross","year":"2024","unstructured":"Cross JL, Choma MA, Onofrey JA (2024) Bias in medical AI: implications for clinical decision-making. PLOS Digit Health 3(11):0000651","journal-title":"PLOS Digit Health"},{"key":"196_CR10","doi-asserted-by":"crossref","unstructured":"Chen Z et al (2023) A comprehensive empirical study of bias mitigation methods for machine learning classifiers. ACM Trans Softw Eng Methodol 32(4)","DOI":"10.1145\/3583561"},{"key":"196_CR11","doi-asserted-by":"crossref","unstructured":"Biswas S, Rajan H (2020) Do the machine learning models on a crowd-sourced platform exhibit bias? An empirical study on model fairness. In: Proceedings of the 28th ACM joint meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC\/FSE 2020), pp 642\u2013653","DOI":"10.1145\/3368089.3409704"},{"key":"196_CR12","doi-asserted-by":"crossref","unstructured":"Gohar U, Cheng L (2023) A survey on intersectional fairness in machine learning: notions, mitigation, and challenges. In: Proceedings of the thirty-second International Joint Conference on Artificial Intelligence (IJCAI \u201923), pp 6619\u20136627","DOI":"10.24963\/ijcai.2023\/742"},{"issue":"5","key":"196_CR13","doi-asserted-by":"publisher","first-page":"476","DOI":"10.1038\/s42256-023-00651-3","volume":"5","author":"E Lett","year":"2023","unstructured":"Lett E, La Cava WG (2023) Translating intersectionality to fair machine learning in health sciences. Nat Mach Intell 5(5):476\u2013479","journal-title":"Nat Mach Intell"},{"key":"196_CR14","doi-asserted-by":"crossref","unstructured":"Chen Z, Zhang JM, Sarro F, Harman M (2024) Fairness improvement with multiple protected attributes: how far are we? In: Proceedings of the IEEE\/ACM 46th International Conference on Software Engineering (ICSE \u201924), pp 160\u2013113. Association for Computing Machinery, New York, NY, USA","DOI":"10.1145\/3597503.3639083"},{"key":"196_CR15","unstructured":"Zhang H et al (2022) Improving the fairness of chest x-ray classifiers. In: Conference on health, inference, and learning, pp 204\u2013233. PMLR"},{"key":"196_CR16","unstructured":"Marcinkevics R et al (2022) Debiasing deep chest x-ray classifiers using intra- and post-processing methods. In: Proceedings of the 7th machine learning for healthcare conference. Proceedings of machine learning research, vol 182, pp 504\u2013536"},{"issue":"4","key":"196_CR17","doi-asserted-by":"publisher","first-page":"141","DOI":"10.3390\/a17040141","volume":"17","author":"A Soltan","year":"2024","unstructured":"Soltan A, Washington P (2024) Challenges in reducing bias using post-processing fairness for breast cancer stage classification with deep learning. Algorithms 17(4):141","journal-title":"Algorithms"},{"key":"196_CR18","unstructured":"Dua D, Graff C (2019) UCI machine learning repository: CDC diabetes health indicators dataset. https:\/\/www.archive.ics.uci.edu\/dataset\/891\/cdc+diabetes+health+indicators"},{"key":"196_CR19","unstructured":"Janosi A et al (1988) UCI machine learning repository: heart disease data set. https:\/\/archive.ics.uci.edu\/dataset\/45\/heart+disease"},{"key":"196_CR20","unstructured":"Healthcare\u00a0Research A, Quality (2021) Medical expenditure panel survey data. https:\/\/meps.ahrq.gov\/mepsweb\/"},{"key":"196_CR21","doi-asserted-by":"publisher","first-page":"1001779","DOI":"10.1371\/journal.pmed.1001779","volume":"12","author":"C Sudlow","year":"2015","unstructured":"Sudlow C et al (2015) UK biobank: an open access resource for identifying the causes of a wide range of complex diseases of middle and old age. PLOS Med 12:1001779","journal-title":"PLOS Med"},{"key":"196_CR22","unstructured":"Kohavi R (1996) Scaling up the accuracy of naive-bayes classifiers: a decision-tree hybrid. In: Proceedings of the second international conference on knowledge discovery and data mining, pp 202\u2013207"},{"key":"196_CR23","unstructured":"Dua D, Graff C (2019) UCI machine learning repository: statlog (German Credit Data) data set. https:\/\/archive.ics.uci.edu\/ml\/datasets\/Statlog+(German+Credit+Data)"},{"key":"196_CR24","unstructured":"ProPublica (2016) ProPublica recidivism\/COMPAS analysis. https:\/\/github.com\/propublica\/compas-analysis"},{"key":"196_CR25","unstructured":"Moro S, Laureano RM, Cortez P (2014) UCI machine learning repository: bank marketing data set. https:\/\/archive.ics.uci.edu\/ml\/datasets\/Bank+Marketing"},{"key":"196_CR26","doi-asserted-by":"crossref","unstructured":"Zafar MB, Valera I, Gomez\u00a0Rodriguez M, Gummadi KP (2017) Fairness beyond disparate treatment and disparate impact: learning classification without disparate mistreatment. In: Proceedings of the 26th international conference on world wide web, pp 1171\u20131180","DOI":"10.1145\/3038912.3052660"},{"key":"196_CR27","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1007\/s10994-010-5221-8","volume":"85","author":"H-F Yu","year":"2011","unstructured":"Yu H-F et al (2011) Dual coordinate descent methods for logistic regression and maximum entropy models. Mach Learn 85:41\u201375","journal-title":"Mach Learn"},{"key":"196_CR28","doi-asserted-by":"crossref","unstructured":"Chen T, Guestrin C (2016) Xgboost: a scalable tree boosting system. In: Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining, pp 785\u2013794","DOI":"10.1145\/2939672.2939785"},{"issue":"7553","key":"196_CR29","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y LeCun","year":"2015","unstructured":"LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521(7553):436","journal-title":"Nature"},{"key":"196_CR30","unstructured":"Hardt M et al (2016) Equality of opportunity in supervised learning. In: Conference on neural information processing systems"},{"key":"196_CR31","doi-asserted-by":"crossref","unstructured":"Hort M, Zhang JM, Sarro F, Harman M (2021) Fairea: a model behaviour mutation approach to benchmarking bias mitigation methods. In: Proceedings of the 29th ACM joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC\/FSE 2021), pp 994\u20131006","DOI":"10.1145\/3468264.3468565"},{"key":"196_CR32","unstructured":"Pleiss G et al (2017) On fairness and calibration. In: Conference on neural information processing systems"},{"key":"196_CR33","doi-asserted-by":"crossref","unstructured":"Kamiran F et al (2012) Decision theory for discrimination-aware classification. In: IEEE international conference on data mining","DOI":"10.1109\/ICDM.2012.45"},{"key":"196_CR34","unstructured":"Kim JS et al (2020) Fact: a diagnostic for group fairness trade-offs. In: Proceedings of the 37th International Conference on Machine Learning (ICML\u201920), vol 119, pp 5264\u20135274"},{"key":"196_CR35","doi-asserted-by":"crossref","unstructured":"Jang T et al (2022) Group-aware threshold adaptation for fair classification. In: Proceedings of the AAAI conference on artificial intelligence, vol 36, pp 6988\u20136995","DOI":"10.1609\/aaai.v36i6.20657"},{"key":"196_CR36","doi-asserted-by":"crossref","unstructured":"Kim MP et al (2019) Multiaccuracy: black-box post-processing for fairness in classification. In: Proceedings of the 2019 AAAI\/ACM conference on AI, Ethics, and Society (AIES \u201919), pp 247\u2013254. Association for Computing Machinery, New York, NY, USA","DOI":"10.1145\/3306618.3314287"},{"key":"196_CR37","unstructured":"Bellamy RKE et al (2018) Ai fairness 360: an extensible toolkit for detecting, understanding, and mitigating unwanted algorithmic bias. arXiv:1810.01943"},{"key":"196_CR38","first-page":"2825","volume":"12","author":"F Pedregosa","year":"2011","unstructured":"Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, Blondel M, Prettenhofer P, Weiss R, Dubourg V, Vanderplas J, Passos A, Cournapeau D, Brucher M, Perrot M, Duchesnay E (2011) Scikit-learn: machine learning in python. J Mach Learn Res 12:2825\u20132830","journal-title":"J Mach Learn Res"},{"key":"196_CR39","unstructured":"Chollet F (2015) Keras: deep learning library for Theano and TensorFlow. GitHub repository. Available at: https:\/\/github.com\/fchollet\/keras. Accessed 17 Feb 2025"},{"issue":"2","key":"196_CR40","doi-asserted-by":"publisher","first-page":"579","DOI":"10.1007\/s10664-016-9437-5","volume":"22","author":"BA Kitchenham","year":"2017","unstructured":"Kitchenham BA et al (2017) Robust statistical methods for empirical software engineering. Empir Softw Eng 22(2):579\u2013630","journal-title":"Empir Softw Eng"},{"issue":"4","key":"196_CR41","first-page":"1","volume":"5","author":"D Ramyachitra","year":"2014","unstructured":"Ramyachitra D, Manikandan P (2014) Imbalanced dataset classification and solutions: a review. Int J Comput Bus Res 5(4):1\u201329","journal-title":"Int J Comput Bus Res"}],"container-title":["Journal of Healthcare Informatics Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s41666-025-00196-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s41666-025-00196-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s41666-025-00196-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,6]],"date-time":"2025-09-06T08:56:08Z","timestamp":1757148968000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s41666-025-00196-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,20]]},"references-count":41,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2025,9]]}},"alternative-id":["196"],"URL":"https:\/\/doi.org\/10.1007\/s41666-025-00196-7","relation":{},"ISSN":["2509-4971","2509-498X"],"issn-type":[{"value":"2509-4971","type":"print"},{"value":"2509-498X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3,20]]},"assertion":[{"value":"1 October 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 February 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 March 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 March 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of Interest"}}]}}