{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T15:59:34Z","timestamp":1785340774147,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":28,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T00:00:00Z","timestamp":1782777600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100002803","name":"Fondazione Cariplo","doi-asserted-by":"publisher","award":["2024-0173"],"award-info":[{"award-number":["2024-0173"]}],"id":[{"id":"10.13039\/501100002803","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,6,30]]},"DOI":"10.1145\/3807503.3819381","type":"proceedings-article","created":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T02:55:27Z","timestamp":1785293727000},"page":"1-6","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Assessing Utility-Leakage Trade-offs in Coreset Selection for Chest X-Ray Embeddings"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9651-7156","authenticated-orcid":false,"given":"Aldo","family":"Marzullo","sequence":"first","affiliation":[{"name":"Department of Electronics, Information and Bioengineering, Politecnico di Milano, Milan, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0579-6178","authenticated-orcid":false,"given":"Sebasti\u00e1n Andr\u00e9s","family":"Cajas Ord\u00f3\u00f1ez","sequence":"additional","affiliation":[{"name":"MIT Critical Data, Massachusetts Institute of Technology, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6712-6626","authenticated-orcid":false,"given":"Leo Anthony","family":"Celi","sequence":"additional","affiliation":[{"name":"Laboratory for Computational Physiology, Massachusetts Institute of Technology, Cambridge, MA, USA; Division of Pulmonary, Critical Care and Sleep Medicine, Beth Israel Deaconess Medical Center, Boston, MA, USA and Department of Biostatistics, Harvard T.H. Chan School of Public Health, Boston, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8819-2734","authenticated-orcid":false,"given":"Elena","family":"De Momi","sequence":"additional","affiliation":[{"name":"Department of Electronics, Information and Bioengineering, Politecnico di Milano, Milan, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,28]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_9"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00346"},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"crossref","unstructured":"Samuel Budd Emma\u00a0C. Robinson and Bernhard Kainz. 2021. A Survey on Active Learning and Human-in-the-Loop Deep Learning for Medical Image Analysis. Med. Image Anal. 71 (2021) 102062.","DOI":"10.1016\/j.media.2021.102062"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"crossref","unstructured":"Richard\u00a0J. Chen Judy\u00a0J. Wang Drew F.\u00a0K. Williamson Tiffany\u00a0Y. Chen Jana Lipkova Ming\u00a0Y. Lu Sahil Sahai and Faisal Mahmood. 2023. Algorithmic Fairness in Artificial Intelligence for Medicine and Healthcare. Nature Biomed. Eng. 7 6 (2023) 719\u2013742.","DOI":"10.1038\/s41551-023-01056-8"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/2783258.2783311"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.5555\/3305381.3305504"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"crossref","unstructured":"Judy\u00a0Wawira Gichoya Imon Banerjee Ananth\u00a0Reddy Bhimireddy John\u00a0L. Burns Leo\u00a0Anthony Celi Li-Ching Chen et\u00a0al. 2022. AI Recognition of Patient Race in Medical Imaging: A Modelling Study. Lancet Digit. Health 4 6 (2022) e406\u2013e414.","DOI":"10.1016\/S2589-7500(22)00063-2"},{"key":"e_1_3_3_1_9_2","unstructured":"Chengcheng Guo Bo Zhao and Yanbing Bai. 2022. DeepCore: A Comprehensive Library for Coreset Selection in Deep Learning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2204.08499 (2022)."},{"key":"e_1_3_3_1_10_2","volume-title":"Proc. 30th Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Hardt Moritz","year":"2016","unstructured":"Moritz Hardt, Eric Price, and Nati Srebro. 2016. Equality of Opportunity in Supervised Learning. In Proc. 30th Conf. Neural Inf. Process. Syst. (NeurIPS) , Vol.\u00a029."},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"crossref","unstructured":"Alistair E.\u00a0W. Johnson Lucas Bulgarelli Lu Shen Alvin Gayles Ayad Shammout Steven Horng Tom\u00a0J. Pollard Sicheng Hao Benjamin Moody Brian Gow Li-wei\u00a0H. Lehman Leo\u00a0Anthony Celi and Roger\u00a0G. Mark. 2023. MIMIC-IV a Freely Accessible Electronic Health Record Dataset. Sci. Data 10 (2023) 1.","DOI":"10.1038\/s41597-022-01899-x"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"crossref","unstructured":"Alistair E.\u00a0W. Johnson Tom\u00a0J. Pollard Seth\u00a0J. Berkowitz Nathaniel\u00a0R. Greenbaum Matthew\u00a0P. Lungren Chih-ying Deng Roger\u00a0G. Mark and Steven Horng. 2019. MIMIC-CXR a De-Identified Publicly Available Database of Chest Radiographs with Free-Text Reports. Sci. Data 6 (2019) 317.","DOI":"10.1038\/s41597-019-0322-0"},{"key":"e_1_3_3_1_13_2","series-title":"PMLR","first-page":"5464","volume-title":"Proc. 38th Int. Conf. Mach. Learn. (ICML)","author":"Killamsetty Krishnateja","year":"2021","unstructured":"Krishnateja Killamsetty, Durga Sivasubramanian, Ganesh Ramakrishnan, Abir De, and Rishabh Iyer. 2021. GRAD-MATCH: Gradient Matching Based Data Subset Selection for Efficient Deep Model Training. In Proc. 38th Int. Conf. Mach. Learn. (ICML)(PMLR, Vol.\u00a0139). 5464\u20135474."},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i9.16988"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"crossref","unstructured":"Agostina\u00a0J. Larrazabal Nicol\u00e1s Nieto Victoria Peterson Diego\u00a0H. Milone and Enzo Ferrante. 2020. Gender Imbalance in Medical Imaging Datasets Produces Biased Classifiers for Computer-Aided Diagnosis. Proc. Natl. Acad. Sci. USA 117 23 (2020) 12592\u201312594.","DOI":"10.1073\/pnas.1919012117"},{"key":"e_1_3_3_1_16_2","series-title":"PMLR","first-page":"6755","volume-title":"Proc. 37th Int. Conf. Mach. Learn. (ICML)","author":"Martinez Natalia","year":"2020","unstructured":"Natalia Martinez, Martin Bertran, and Guillermo Sapiro. 2020. Minimax Pareto Fairness: A Multi-Objective Perspective. In Proc. 37th Int. Conf. Mach. Learn. (ICML)(PMLR, Vol.\u00a0119). 6755\u20136764."},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"crossref","unstructured":"Ninareh Mehrabi Fred Morstatter Nripsuta Saxena Kristina Lerman and Aram Galstyan. 2021. A Survey on Bias and Fairness in Machine Learning. ACM Comput. Surv. 54 6 (2021) 1\u201335.","DOI":"10.1145\/3457607"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525583"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"crossref","unstructured":"Michael Moor Oishi Banerjee Zahra S.\u00a0H. Abad Harlan\u00a0M. Krumholz Jure Leskovec Eric\u00a0J. Topol and Pranav Rajpurkar. 2023. Foundation Models for Generalist Medical Artificial Intelligence. Nature 616 7956 (2023) 259\u2013265.","DOI":"10.1038\/s41586-023-05881-4"},{"key":"e_1_3_3_1_20_2","volume-title":"arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2505.17799","author":"Moser Brian","year":"2025","unstructured":"Brian Moser, Federico Raue, Stanislav Frolov, Sebastian Palacio, J\u00f6rn Hees, and Andreas Dengel. 2025. Less is More: A Survey on Coreset Selection for Efficient Machine Learning. In arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2505.17799."},{"key":"e_1_3_3_1_21_2","first-page":"20596","volume-title":"Proc. 35th Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Paul Mansheej","year":"2021","unstructured":"Mansheej Paul, Surya Ganguli, and Gintare\u00a0Karolina Dziugaite. 2021. Deep Learning on a Data Diet: Finding Important Examples Early in Training. In Proc. 35th Conf. Neural Inf. Process. Syst. (NeurIPS) , Vol.\u00a034. 20596\u201320607."},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"crossref","unstructured":"Stephen\u00a0R. Pfohl Agata Foryciarz and Nigam\u00a0H. Shah. 2021. An Empirical Characterization of Fair Machine Learning for Clinical Risk Prediction. J. Biomed. Inform. 113 (2021) 103621.","DOI":"10.1016\/j.jbi.2020.103621"},{"key":"e_1_3_3_1_23_2","volume-title":"Proc. 9th Int. Conf. Learn. Represent. (ICLR)","author":"Roh Yuji","year":"2021","unstructured":"Yuji Roh, Kangwook Lee, Steven\u00a0Euijong Whang, and Changho Suh. 2021. FairBatch: Batch Selection for Model Fairness. In Proc. 9th Int. Conf. Learn. Represent. (ICLR)."},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"crossref","unstructured":"Laleh Seyyed-Kalantari Haoran Zhang Matthew B.\u00a0A. McDermott Irene\u00a0Y. Chen and Marzyeh Ghassemi. 2021. Underdiagnosis Bias of Artificial Intelligence Algorithms Applied to Chest Radiographs in Under-Served Patient Populations. Nature Med. 27 12 (2021) 2176\u20132182.","DOI":"10.1038\/s41591-021-01595-0"},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1419"},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"crossref","unstructured":"Ekin Tiu Ellie Taber Aran Brennan Sathvik Arunachalam Jared Laber Hashir Rasheed et\u00a0al. 2022. Expert-Level Detection of Pathologies from Unannotated Chest X-Ray Images via Self-Supervised Learning. Nature Biomed. Eng. 6 (2022) 1399\u20131406.","DOI":"10.1038\/s41551-022-00936-9"},{"key":"e_1_3_3_1_27_2","volume-title":"Proc. 7th Int. Conf. Learn. Represent. (ICLR)","author":"Toneva Mariya","year":"2019","unstructured":"Mariya Toneva, Alessandro Sordoni, Remi\u00a0Tachet des Combes, Adam Trischler, Yoshua Bengio, and Geoffrey\u00a0J. Gordon. 2019. An Empirical Study of Example Forgetting During Deep Neural Network Learning. In Proc. 7th Int. Conf. Learn. Represent. (ICLR)."},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0004"},{"key":"e_1_3_3_1_29_2","unstructured":"Shawn Xu Lin Yang Christopher Kelly Marcin Sieniek Timo Kohlberger Martin Ma Wei-Hung Weng Atilla Kiraly Sahar Kazemzadeh Alexandra Melamed et\u00a0al. 2023. ELIXR: Towards a General Purpose X-ray Artificial Intelligence System through Alignment of Large Language Models and Radiology Vision Encoders. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2308.01317 (2023)."}],"event":{"name":"BCB '26: 17th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics","location":"Rende (CS) Italy","acronym":"BCB '26","sponsor":["SIGBio ACM Special Interest Group on Bioinformatics"]},"container-title":["Proceedings of the 17th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3807503.3819381","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T15:15:16Z","timestamp":1785338116000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3807503.3819381"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,30]]},"references-count":28,"alternative-id":["10.1145\/3807503.3819381","10.1145\/3807503"],"URL":"https:\/\/doi.org\/10.1145\/3807503.3819381","relation":{},"subject":[],"published":{"date-parts":[[2026,6,30]]},"assertion":[{"value":"2026-07-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}