{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T19:46:51Z","timestamp":1782330411885,"version":"3.54.5"},"reference-count":33,"publisher":"Oxford University Press (OUP)","issue":"6","license":[{"start":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T00:00:00Z","timestamp":1779148800000},"content-version":"vor","delay-in-days":1,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62176053"],"award-info":[{"award-number":["62176053"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,6,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Motivation<\/jats:title>\n                    <jats:p>Medical text classification plays a critical role in clinical decision support, automated diagnosis, and biomedical research. However, deep learning models are highly susceptible to dataset-induced biases, such as label bias and keyword bias, which can lead to unreliable predictions and poor generalization in real-world clinical applications. Existing debiasing methods often either overcorrect informative samples or lack interpretability during inference, limiting their effectiveness in multilabel medical text classification tasks.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>We propose Cooperative Debiasing Network (CoDeNet), a cooperative training framework that mitigates dataset bias through dynamic sample reweighting and interpretable counterfactual inference. The framework consists of a primary classifier and a debias estimator, where the debias estimator quantifies sample-level bias and dynamically regulates the optimization process through an elastic scaling mechanism. In addition, a counterfactual postprocessing strategy explicitly isolates label-level and keyword-level biases to improve interpretability. Experiments conducted on the DepressionEMO and BDI-Sen datasets demonstrate that CoDeNet consistently improves classification performance over strong transformer-based baselines, including BERT and MentalBERT. In particular, CoDeNet achieves improvements of up to +6.57% macro-F1 on BDI-Sen and +2.16% macro-F1 on DepressionEMO, with especially strong gains on low-frequency clinical labels. The results indicate that CoDeNet effectively reduces dataset-induced bias while preserving model robustness and interpretability.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Availability and implementation<\/jats:title>\n                    <jats:p>The source code and implementation details of CoDeNet will be publicly available on GitHub: https:\/\/github.com\/66ccff39C5BB\/CoDeNet.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btag317","type":"journal-article","created":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T12:21:16Z","timestamp":1778674876000},"source":"Crossref","is-referenced-by-count":0,"title":["Mitigating bias in multilabel medical text classification: a cooperative training framework with dynamic debiasing"],"prefix":"10.1093","volume":"42","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-4218-7358","authenticated-orcid":false,"given":"Pengfei","family":"Li","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, MOE Key Laboratory of Computer Network and Information Integration, Southeast University , Nanjing, Jiangsu 210096,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9294-2841","authenticated-orcid":false,"given":"Xu","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, MOE Key Laboratory of Computer Network and Information Integration, Southeast University , Nanjing, Jiangsu 210096,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoyu","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, MOE Key Laboratory of Computer Network and Information Integration, Southeast University , Nanjing, Jiangsu 210096,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zexu","family":"Lin","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, MOE Key Laboratory of Computer Network and Information Integration, Southeast University , Nanjing, Jiangsu 210096,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Deyu","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, MOE Key Laboratory of Computer Network and Information Integration, Southeast University , Nanjing, Jiangsu 210096,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,5,18]]},"reference":[{"key":"2026062415022465000_btag317-B1","doi-asserted-by":"crossref","first-page":"588","DOI":"10.1207\/s15327752jpa6703_13","article-title":"Comparison of beck depression inventories-IA and-II in psychiatric outpatients","volume":"67","author":"Beck","year":"1996","journal-title":"J Pers Assess"},{"key":"2026062415022465000_btag317-B2","doi-asserted-by":"crossref","first-page":"1481","DOI":"10.1109\/TVCG.2020.3030455","article-title":"Selection-bias-corrected visualization via dynamic reweighting","volume":"27","author":"Borland","year":"2021","journal-title":"IEEE Trans Vis Comput Graph"},{"key":"2026062415022465000_btag317-B3","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3643806","article-title":"A survey of mix-based data augmentation: taxonomy, methods, applications, and explainability","volume":"57","author":"Cao","year":"2024","journal-title":"ACM Comput Surv"},{"key":"2026062415022465000_btag317-B4","doi-asserted-by":"crossref","first-page":"4514","DOI":"10.3390\/ijms24054514","article-title":"Application of machine learning models in systemic lupus erythematosus","volume":"24","author":"Ceccarelli","year":"2023","journal-title":"Int J Mol Sci"},{"key":"2026062415022465000_btag317-B5","doi-asserted-by":"crossref","first-page":"231","DOI":"10.1136\/bmjqs-2018-008370","article-title":"Artificial intelligence, bias and clinical safety","volume":"28","author":"Challen","year":"2019","journal-title":"BMJ Qual Saf"},{"key":"2026062415022465000_btag317-B6","doi-asserted-by":"crossref","first-page":"981","DOI":"10.1056\/NEJMp1714229","article-title":"Implementing machine learning in health care\u2014addressing ethical challenges","volume":"378","author":"Char","year":"2018","journal-title":"N Engl J Med"},{"key":"2026062415022465000_btag317-B7","author":"Chen","year":"2016"},{"key":"2026062415022465000_btag317-B8","doi-asserted-by":"crossref","first-page":"103024","DOI":"10.1016\/j.inffus.2025.103024","article-title":"A review of medical text analysis: theory and practice","volume":"119","author":"Chen","year":"2025","journal-title":"Information Fusion"},{"key":"2026062415022465000_btag317-B9","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1023\/A:1022627411411","article-title":"Support-vector networks","volume":"20","author":"Cortes","year":"1995","journal-title":"Mach. Learn"},{"key":"2026062415022465000_btag317-B10","doi-asserted-by":"publisher","author":"Devlin","year":"2019","DOI":"10.18653\/v1\/N19-1423"},{"key":"2026062415022465000_btag317-B11","author":"Hosmer"},{"key":"2026062415022465000_btag317-B12","author":"Ji","year":"2022"},{"key":"2026062415022465000_btag317-B13","author":"Jiang","year":"2020"},{"key":"2026062415022465000_btag317-B14","author":"Ke","year":"2017"},{"key":"2026062415022465000_btag317-B15","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1146\/annurev-physchem-083122-124538","article-title":"Dynamical reweighting for biased rare event simulations","volume":"75","author":"Keller","year":"2024","journal-title":"Annu Rev Phys Chem"},{"key":"2026062415022465000_btag317-B16","doi-asserted-by":"crossref","first-page":"104621","DOI":"10.1016\/j.jbi.2024.104621","article-title":"Artificial intelligence-powered pharmacovigilance: a review of machine and deep learning in clinical text-based adverse drug event detection for benchmark datasets","volume":"152","author":"Li","year":"2024","journal-title":"J Biomed Inform"},{"key":"2026062415022465000_btag317-B17","first-page":"340","author":"Losada","year":"2019"},{"key":"2026062415022465000_btag317-B18","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1186\/s12874-022-01665-y","article-title":"A comparative study on deep learning models for text classification of unstructured medical notes with various levels of class imbalance","volume":"22","author":"Lu","year":"2022","journal-title":"BMC Med Res Methodol"},{"key":"2026062415022465000_btag317-B19","author":"Min","year":"2024"},{"key":"2026062415022465000_btag317-B20","first-page":"20673","volume-title":"Advances in Neural Information Processing Systems","author":"Nam","year":"2020"},{"key":"2026062415022465000_btag317-B21","author":"P\u00e9rez","year":"2023"},{"key":"2026062415022465000_btag317-B22","doi-asserted-by":"crossref","first-page":"18143","DOI":"10.52202\/068431-1319","article-title":"Mocoda: model-based counterfactual data augmentation","volume":"35","author":"Pitis","year":"2022","journal-title":"Adv Neural Inf Process Syst"},{"key":"2026062415022465000_btag317-B23","doi-asserted-by":"crossref","first-page":"9425655","DOI":"10.1155\/2021\/9425655","article-title":"Medical text classification using hybrid deep learning models with multihead attention","volume":"2021","author":"Prabhakar","year":"2021","journal-title":"Comput Intell Neurosci"},{"key":"2026062415022465000_btag317-B24","author":"Qian","year":"2021"},{"key":"2026062415022465000_btag317-B25","doi-asserted-by":"crossref","first-page":"445","DOI":"10.1016\/j.jad.2024.08.013","article-title":"DepressionEMO: a novel dataset for multilabel classification of depression emotions","volume":"366","author":"Rahman","year":"2024","journal-title":"J Affect Disord"},{"key":"2026062415022465000_btag317-B26","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1038\/s41746-018-0029-1","article-title":"Scalable and accurate deep learning with electronic health records","volume":"1","author":"Rajkomar","year":"2018","journal-title":"NPJ Digit Med"},{"key":"2026062415022465000_btag317-B27","author":"Schmidgall","year":"2024"},{"key":"2026062415022465000_btag317-B28","first-page":"100375","article-title":"Solving the class imbalance problem using a counterfactual method for data augmentation","volume":"9","author":"Temraz","year":"2022","journal-title":"Mach Learn Appl"},{"key":"2026062415022465000_btag317-B29","doi-asserted-by":"crossref","first-page":"269","DOI":"10.1007\/s10669-019-09717-3","article-title":"Active learning in automated text classification: a case study exploring bias in predicted model performance metrics","volume":"39","author":"Varghese","year":"2019","journal-title":"Environ Syst Decis"},{"key":"2026062415022465000_btag317-B30","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1007\/s11409-020-09235-7","article-title":"The keyword effect: a conceptual replication, effects on bias, and an optimization","volume":"16","author":"Waldeyer","year":"2021","journal-title":"Metacognition Learning"},{"key":"2026062415022465000_btag317-B31","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1038\/s41746-023-00805-y","article-title":"An adversarial training framework for mitigating algorithmic biases in clinical machine learning","volume":"6","author":"Yang","year":"2023","journal-title":"NPJ Digit Med"},{"key":"2026062415022465000_btag317-B32","author":"Zhang","year":"2020"},{"key":"2026062415022465000_btag317-B33","first-page":"8792","article-title":"Generalized cross entropy loss for training deep neural networks with noisy labels","volume":"31","author":"Zhang","year":"2018","journal-title":"Adv Neural Inf Process Syst"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btag317\/68331819\/btag317.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/42\/6\/btag317\/68331819\/btag317.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/42\/6\/btag317\/68331819\/btag317.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T19:02:35Z","timestamp":1782327755000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btag317\/8687107"}},"subtitle":[],"editor":[{"given":"Macha","family":"Nikolski","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,5,18]]},"references-count":33,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2026,6,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btag317","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,6]]},"published":{"date-parts":[[2026,5,18]]},"article-number":"btag317"}}