{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T15:59:11Z","timestamp":1785340751728,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":47,"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"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,6,30]]},"DOI":"10.1145\/3807503.3819465","type":"proceedings-article","created":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T02:55:27Z","timestamp":1785293727000},"page":"1-10","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["CACL: Context-Aware Contrastive Learning for Semantic Modeling of Anomalies in EHR Data"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8898-9498","authenticated-orcid":false,"given":"Hajar","family":"Homayouni","sequence":"first","affiliation":[{"name":"Computer Science, San Diego State University, San Diego, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-6708-1051","authenticated-orcid":false,"given":"Veera Venkata Satya Sai Kiran","family":"Polu","sequence":"additional","affiliation":[{"name":"San Diego State University, San Diego, California, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-7917-3716","authenticated-orcid":false,"given":"Ana Julia","family":"Morais Arantes","sequence":"additional","affiliation":[{"name":"San Diego State University, San Diego, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2721-0628","authenticated-orcid":false,"given":"Hossein","family":"Shirazi","sequence":"additional","affiliation":[{"name":"Management Information Systems, San Diego State University, San Diego, California, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,28]]},"reference":[{"key":"e_1_3_3_1_2_2","unstructured":"Nudrat Abbas. 2023. Vitamin Deficiency Disease Prediction Dataset. https:\/\/www.kaggle.com\/datasets\/nudratabbas\/vitamin-deficiency-disease-prediction-dataset"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-47578-3"},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"crossref","unstructured":"Mohiuddin Ahmed Raihan Seraj and Syed Mohammed\u00a0Shamsul Islam. 2020. The k-means algorithm: A comprehensive survey and performance evaluation. Electronics 9 8 (2020) 1295.","DOI":"10.3390\/electronics9081295"},{"key":"e_1_3_3_1_5_2","unstructured":"San Bin and Yuan Zhao. 2022. A Comprehensive Review of Fraud\u2010Oriented Anomaly Detection. IEEE Access 10 (2022) 77712\u201377733."},{"key":"e_1_3_3_1_6_2","volume-title":"Pattern Recognition and Machine Learning","author":"Bishop Christopher\u00a0M.","year":"2006","unstructured":"Christopher\u00a0M. Bishop. 2006. Pattern Recognition and Machine Learning. Springer."},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/342009.335388"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"crossref","unstructured":"Varun Chandola Arindam Banerjee and Vipin Kumar. 2009. Anomaly detection: A survey. Comput. Surveys 41 3 (2009) 1\u201358.","DOI":"10.1145\/1541880.1541882"},{"key":"e_1_3_3_1_9_2","unstructured":"Ting Chen Simon Kornblith Mohammad Norouzi and Geoffrey Hinton. 2020. A simple framework for contrastive learning of visual representations. International conference on machine learning (2020) 1597\u20131607."},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"crossref","unstructured":"Rayees\u00a0Ahmad Dar Muzafar Rasool Assif Assad et\u00a0al. 2022. Breast cancer detection using deep learning: Datasets methods and challenges ahead. Computers in biology and medicine 149 (2022) 106073.","DOI":"10.1016\/j.compbiomed.2022.106073"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"crossref","unstructured":"Jesse Davis and Mark Goadrich. 2006. The relationship between Precision-Recall and ROC curves. ICML (2006).","DOI":"10.1145\/1143844.1143874"},{"key":"e_1_3_3_1_12_2","unstructured":"Dheeru Dua and Casey Graff. 2017. UCI Machine Learning Repository: Breast Cancer Wisconsin Dataset. https:\/\/archive.ics.uci.edu\/ml\/datasets\/Breast+Cancer+Wisconsin+(Diagnostic)"},{"key":"e_1_3_3_1_13_2","unstructured":"Dheeru Dua and Casey Graff. 2017. UCI Machine Learning Repository: Ecoli Dataset. https:\/\/archive.ics.uci.edu\/ml\/datasets\/ecoli"},{"key":"e_1_3_3_1_14_2","unstructured":"Dheeru Dua and Casey Graff. 2017. UCI Machine Learning Repository: Pima Indians Diabetes Dataset. https:\/\/archive.ics.uci.edu\/ml\/datasets\/Pima+Indians+Diabetes"},{"key":"e_1_3_3_1_15_2","unstructured":"Dheeru Dua and Casey Graff. 2017. UCI Machine Learning Repository: Thyroid Disease Dataset. https:\/\/archive.ics.uci.edu\/ml\/datasets\/thyroid+disease"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"crossref","unstructured":"R\u00a0Scott Evans. 2016. Electronic health records: then now and in the future. Yearbook of medical informatics 25 S 01 (2016) S48\u2013S61.","DOI":"10.15265\/IYS-2016-s006"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"publisher","unstructured":"Tharindu Fernando Harshala Gammulle Simon Denman Sridha Sridharan and Clinton Fookes. 2021. Deep Learning for Medical Anomaly Detection \u2013 A Survey. ACM Comput. Surv. 54 7 Article 141 (July 2021) 37\u00a0pages. 10.1145\/3464423","DOI":"10.1145\/3464423"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"crossref","unstructured":"Waleed Hilal S\u00a0Andrew Gadsden and John Yawney. 2022. Financial fraud: a review of anomaly detection techniques and recent advances. Expert systems With applications 193 (2022) 116429.","DOI":"10.1016\/j.eswa.2021.116429"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/BigData50022.2020.9378192"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"crossref","unstructured":"Haigen Hu Xiaoyuan Wang Yan Zhang Qi Chen and Qiu Guan. 2024. A comprehensive survey on contrastive learning. Neurocomputing 610 (2024) 128645.","DOI":"10.1016\/j.neucom.2024.128645"},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"publisher","unstructured":"Andrey Kharitonov Abdulrahman Nahhas Matthias Pohl and Klaus Turowski. 2022. Comparative analysis of machine learning models for anomaly detection in manufacturing. Procedia Computer Science 200 (2022) 1288\u20131297. 10.1016\/j.procs.2022.01.330","DOI":"10.1016\/j.procs.2022.01.330"},{"key":"e_1_3_3_1_22_2","unstructured":"Kyuho Kim and Sang Shim. 2022. Machine\u2010Learning Approaches for Predictive Maintenance of Industrial Equipment. Engineering Applications of Artificial Intelligence 109 (2022) 104664."},{"key":"e_1_3_3_1_23_2","unstructured":"Kingma and Welling. 2013. Auto-Encoding Variational Bayes. (2013)."},{"key":"e_1_3_3_1_24_2","unstructured":"Ron Kohavi. 1995. A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection. IJCAI (1995)."},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"crossref","unstructured":"Fei\u00a0Tony Liu Kai\u00a0Ming Ting and Zhi-Hua Zhou. 2008. Isolation forest. 2008 Eighth IEEE International Conference on Data Mining (2008) 413\u2013422.","DOI":"10.1109\/ICDM.2008.17"},{"key":"e_1_3_3_1_26_2","unstructured":"Vitthal Madane. 2023. Pharma Air Handling Units Data. https:\/\/www.kaggle.com\/datasets\/vitthalmadane\/pharma-air-handling-units-data."},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"crossref","unstructured":"Leland McInnes John Healy Steve Astels et\u00a0al. 2017. hdbscan: Hierarchical density based clustering. J. Open Source Softw. 2 11 (2017) 205.","DOI":"10.21105\/joss.00205"},{"key":"e_1_3_3_1_28_2","unstructured":"Long Nguyen Jie Zhao and Rina Patel. 2024. Retrieval-Augmented Deep Anomaly Detection for Tabular Data. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2406.09321 (2024)."},{"key":"e_1_3_3_1_29_2","first-page":"1381","volume-title":"European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases","author":"Park Hyeonjin","year":"2023","unstructured":"Hyeonjin Park, Dongmin Kim, and Jaekyun Yoo. 2023. Deep Anomaly Detection with Partition Contrastive Learning for Tabular Data. In European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases. Springer, 1381\u20131397."},{"key":"e_1_3_3_1_30_2","first-page":"1914","volume-title":"The Thirty Sixth Annual Conference on Learning Theory","author":"Parulekar Advait","year":"2023","unstructured":"Advait Parulekar, Liam Collins, Karthikeyan Shanmugam, Aryan Mokhtari, and Sanjay Shakkottai. 2023. Infonce loss provably learns cluster-preserving representations. In The Thirty Sixth Annual Conference on Learning Theory. PMLR, 1914\u20131961."},{"key":"e_1_3_3_1_31_2","unstructured":"Fabian et\u00a0al. Pedregosa. 2011. Scikit-learn: Machine learning in Python. Journal of Machine Learning Research 12 (2011) 2825\u20132830."},{"key":"e_1_3_3_1_32_2","unstructured":"Shebuti Rayana. 2016. ODDS: Outlier Detection DataSets. https:\/\/shebuti.com\/outlier-detection-datasets-odds\/."},{"key":"e_1_3_3_1_33_2","first-page":"4393","volume-title":"Proceedings of the 35th International Conference on Machine Learning (ICML)","author":"Ruff Lukas","year":"2018","unstructured":"Lukas Ruff, Robert\u00a0A. Vandermeulen, Nico G\u00f6rnitz, Lucas Deecke, Shoaib\u00a0Ahmed Siddiqui, Alexander Binder, Emmanuel M\u00fcller, and Marius Kloft. 2018. Deep One-Class Classification. In Proceedings of the 35th International Conference on Machine Learning (ICML). 4393\u20134402."},{"key":"e_1_3_3_1_34_2","unstructured":"Hamza Safwan. 2023. Credit Card Fraud Detection Dataset. https:\/\/www.kaggle.com\/datasets\/hamzasafwan\/credit-card-fraud."},{"key":"e_1_3_3_1_35_2","doi-asserted-by":"crossref","unstructured":"Takaya Saito and Marc Rehmsmeier. 2015. The precision-recall plot is more informative than the ROC plot when evaluating binary classifiers on imbalanced datasets. PLOS ONE (2015).","DOI":"10.1371\/journal.pone.0118432"},{"key":"e_1_3_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1145\/2689746.2689747"},{"key":"e_1_3_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1145\/3711896.3736910"},{"key":"e_1_3_3_1_38_2","doi-asserted-by":"crossref","unstructured":"Bernhard Sch\u00f6lkopf John\u00a0C Platt John Shawe-Taylor Alex\u00a0J Smola and Robert\u00a0C Williamson. 2001. Estimating the support of a high-dimensional distribution. Neural computation 13 7 (2001) 1443\u20131471.","DOI":"10.1162\/089976601750264965"},{"key":"e_1_3_3_1_39_2","doi-asserted-by":"crossref","unstructured":"Panos\u00a0K Syriopoulos Nektarios\u00a0G Kalampalikis Sotiris\u00a0B Kotsiantis and Michael\u00a0N Vrahatis. 2025. k NN Classification: a review. Annals of mathematics and artificial intelligence 93 1 (2025) 43\u201375.","DOI":"10.1007\/s10472-023-09882-x"},{"key":"e_1_3_3_1_40_2","first-page":"5998","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan\u00a0N. Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention Is All You Need. In Advances in Neural Information Processing Systems (NeurIPS). 5998\u20136008."},{"key":"e_1_3_3_1_41_2","doi-asserted-by":"crossref","unstructured":"Hongzuo Xu Guansong Pang Yijie Wang and Yongjun Wang. 2023. Deep isolation forest for anomaly detection. IEEE transactions on knowledge and data engineering 35 12 (2023) 12591\u201312604.","DOI":"10.1109\/TKDE.2023.3270293"},{"key":"e_1_3_3_1_42_2","doi-asserted-by":"crossref","unstructured":"Zhichao Yang Avijit Mitra Weisong Liu Dan Berlowitz and Hong Yu. 2023. TransformEHR: transformer-based encoder-decoder generative model to enhance prediction of disease outcomes using electronic health records. Nature communications 14 1 (2023) 7857.","DOI":"10.1038\/s41467-023-43715-z"},{"key":"e_1_3_3_1_43_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_38"},{"key":"e_1_3_3_1_44_2","unstructured":"Jinsung Yoon Daniel Jarrett and Mihaela van\u00a0der Schaar. 2020. VIME: Extending Masked Language Modeling for Tabular Data. Advances in Neural Information Processing Systems 33 (2020)."},{"key":"e_1_3_3_1_45_2","first-page":"11033","volume-title":"Advances in Neural Information Processing Systems","author":"Yoon Jinsung","year":"2020","unstructured":"Jinsung Yoon, Daniel Jarrett, and Mihaela van\u00a0der Schaar. 2020. VIME: Extending masked language modeling to tabular data. In Advances in Neural Information Processing Systems , Vol.\u00a033. 11033\u201311043."},{"key":"e_1_3_3_1_46_2","unstructured":"Wei Zhang Arjun Kumar and Hannah Lee. 2025. Deep Context-Conditioned Anomaly Detection for Tabular Data. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2501.01234 (2025)."},{"key":"e_1_3_3_1_47_2","unstructured":"Xue Zhou Mengya Ji Yufeng Han and Bin Cui. 2023. Deep Anomaly Detection with Partition Contrastive Learning for Tabular Data. Machine Learning 112 4 (2023) 1381\u20131405."},{"key":"e_1_3_3_1_48_2","unstructured":"Ziya. 2023. Low Voltage Network Dataset. https:\/\/www.kaggle.com\/datasets\/ziya07\/low-voltage-network-dataset."}],"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\/3807503.3819465","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T15:12:41Z","timestamp":1785337961000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3807503.3819465"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,30]]},"references-count":47,"alternative-id":["10.1145\/3807503.3819465","10.1145\/3807503"],"URL":"https:\/\/doi.org\/10.1145\/3807503.3819465","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"}}]}}