{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T19:10:09Z","timestamp":1776107409067,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":139,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,6,12]],"date-time":"2023-06-12T00:00:00Z","timestamp":1686528000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,6,12]]},"DOI":"10.1145\/3593013.3593982","type":"proceedings-article","created":{"date-parts":[[2023,6,12]],"date-time":"2023-06-12T14:40:46Z","timestamp":1686580846000},"page":"123-137","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":12,"title":["In the Name of Fairness: Assessing the Bias in Clinical Record De-identification"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7251-6557","authenticated-orcid":false,"given":"Yuxin","family":"Xiao","sequence":"first","affiliation":[{"name":"Massachusetts Institute of Technology, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7586-6841","authenticated-orcid":false,"given":"Shulammite","family":"Lim","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5676-7898","authenticated-orcid":false,"given":"Tom Joseph","family":"Pollard","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6349-7251","authenticated-orcid":false,"given":"Marzyeh","family":"Ghassemi","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology, USA"}]}],"member":"320","published-online":{"date-parts":[[2023,6,12]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"[n. d.]. De-identifying sensitive data | Data Loss Prevention Documentation | Google Cloud \u2014 cloud.google.com. https:\/\/cloud.google.com\/dlp\/docs\/deidentify-sensitive-data. [Accessed 24-November-2022]."},{"key":"e_1_3_2_1_2_1","unstructured":"[n. d.]. De-identifying sensitive data | cloud healthcare API | google cloud. https:\/\/cloud.google.com\/healthcare-api\/docs\/how-tos\/deidentify. [Accessed 24-November-2022]."},{"key":"e_1_3_2_1_3_1","volume-title":"d.]. Decennial Census Surname Files","year":"2010","unstructured":"[n. d.]. Decennial Census Surname Files (2010, 2000) \u2014 census.gov. https:\/\/www.census.gov\/data\/developers\/data-sets\/surnames.html. [Accessed 30-June-2022]."},{"key":"e_1_3_2_1_4_1","unstructured":"[n. d.]. Detect PHI - Amazon Comprehend Medical \u2014 docs.aws.amazon.com. https:\/\/docs.aws.amazon.com\/comprehend-medical\/latest\/dev\/textanalysis-phi.html. [Accessed 24-November-2022]."},{"key":"e_1_3_2_1_5_1","unstructured":"[n. d.]. HealthVerity Census \u2013 Real-Time Patient Identity Resolution Technology \u2014 healthverity.com. https:\/\/healthverity.com\/solutions\/healthverity-census\/. [Accessed 06-Feb-2023]."},{"key":"e_1_3_2_1_6_1","unstructured":"[n. d.]. Popular Baby Names \u2014 ssa.gov. https:\/\/www.ssa.gov\/oact\/babynames\/limits.html. [Accessed 30-June-2022]."},{"key":"e_1_3_2_1_7_1","unstructured":"[n. d.]. Privacy Analytics - Software to Anonymize Text \u2014 privacy-analytics.com. https:\/\/privacy-analytics.com\/health-data-privacy\/health-data-software\/software-to-anonymize-text\/. [Accessed 06-Feb-2023]."},{"key":"e_1_3_2_1_8_1","unstructured":"[n. d.]. Using the healthcare natural language API | cloud healthcare API | google cloud. https:\/\/cloud.google.com\/healthcare-api\/docs\/how-tos\/nlp. [Accessed 24-November-2022]."},{"key":"e_1_3_2_1_9_1","unstructured":"[n. d.]. What is the Personally Identifying Information (PII) detection feature in Azure Cognitive Service for Language? - Azure Cognitive Services \u2014 learn.microsoft.com. https:\/\/learn.microsoft.com\/en-us\/azure\/cognitive-services\/language-service\/personally-identifiable-information\/overview. [Accessed 24-November-2022]."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijmedinf.2010.09.007"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3461702.3462624"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3514094.3534203"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3233547.3233667"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3406461"},{"key":"e_1_3_2_1_15_1","volume-title":"Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics (demonstrations).","author":"Akbik Alan","year":"2019","unstructured":"Alan Akbik, Tanja Bergmann, Duncan Blythe, Kashif Rasul, Stefan Schweter, and Roland Vollgraf. 2019. FLAIR: An easy-to-use framework for state-of-the-art NLP. In Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics (demonstrations)."},{"key":"e_1_3_2_1_16_1","volume-title":"Proceedings of the 27th international conference on computational linguistics.","author":"Akbik Alan","year":"2018","unstructured":"Alan Akbik, Duncan Blythe, and Roland Vollgraf. 2018. Contextual string embeddings for sequence labeling. In Proceedings of the 27th international conference on computational linguistics."},{"key":"e_1_3_2_1_17_1","volume-title":"Identity theft: Does the risk vary with demographics?Federal Trade Commission","author":"Anderson Keith B","year":"2005","unstructured":"Keith B Anderson. 2005. Identity theft: Does the risk vary with demographics?Federal Trade Commission, Bureau of Economics Working Paper (2005)."},{"key":"e_1_3_2_1_18_1","volume-title":"Who are the victims of identity theft? The effect of demographics. Journal of Public Policy & Marketing","author":"Anderson Keith B","year":"2006","unstructured":"Keith B Anderson. 2006. Who are the victims of identity theft? The effect of demographics. Journal of Public Policy & Marketing (2006)."},{"key":"e_1_3_2_1_19_1","volume-title":"Big data and machine learning in health care. Jama","author":"Beam Andrew L","year":"2018","unstructured":"Andrew L Beam and Isaac S Kohane. 2018. Big data and machine learning in health care. Jama (2018)."},{"key":"e_1_3_2_1_20_1","volume-title":"Development and evaluation of an open source software tool for deidentification of pathology reports. BMC medical informatics and decision making","author":"Beckwith Bruce A","year":"2006","unstructured":"Bruce A Beckwith, Rajeshwarri Mahaadevan, Ulysses J Balis, and Frank Kuo. 2006. Development and evaluation of an open source software tool for deidentification of pathology reports. BMC medical informatics and decision making (2006)."},{"key":"e_1_3_2_1_21_1","first-page":"B3","volume":"201","author":"Bergdall Anna","unstructured":"Anna Bergdall, Stephen Asche, Nicole Schneider, Tessa Kerby, Karen Margolis, JoAnn Sperl-Hillen, Jaime Sekenski, Rachel Pritchard, Michael Maciosek, and Patrick O\u2019Connor. 2012. CB3-01: comparison of ethnicity and race categorization in electronic medical records and by Self-report. Clinical Medicine & Research (2012).","journal-title":"Connor."},{"key":"e_1_3_2_1_22_1","volume-title":"Are Emily and Greg more employable than Lakisha and Jamal? A field experiment on labor market discrimination. American economic review","author":"Bertrand Marianne","year":"2004","unstructured":"Marianne Bertrand and Sendhil Mullainathan. 2004. Are Emily and Greg more employable than Lakisha and Jamal? A field experiment on labor market discrimination. American economic review (2004)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3306618.3314234"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-3809"},{"key":"e_1_3_2_1_25_1","volume-title":"Race decoded: The genomic fight for social justice","author":"Bliss Catherine","unstructured":"Catherine Bliss. 2012. Race decoded: The genomic fight for social justice. Stanford University Press."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.485"},{"key":"e_1_3_2_1_27_1","volume-title":"Racial disparity in natural language processing: A case study of social media african-american english. arXiv preprint arXiv:1707.00061","author":"Blodgett Su Lin","year":"2017","unstructured":"Su Lin Blodgett and Brendan O\u2019Connor. 2017. Racial disparity in natural language processing: A case study of social media african-american english. arXiv preprint arXiv:1707.00061 (2017)."},{"key":"e_1_3_2_1_28_1","volume-title":"Man is to computer programmer as woman is to homemaker? debiasing word embeddings. Advances in neural information processing systems","author":"Bolukbasi Tolga","year":"2016","unstructured":"Tolga Bolukbasi, Kai-Wei Chang, James Y Zou, Venkatesh Saligrama, and Adam T Kalai. 2016. Man is to computer programmer as woman is to homemaker? debiasing word embeddings. Advances in neural information processing systems (2016)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3308560.3317593"},{"key":"e_1_3_2_1_30_1","volume-title":"Dark matters: On the surveillance of blackness","author":"Browne Simone","unstructured":"Simone Browne. 2015. Dark matters: On the surveillance of blackness. Duke University Press."},{"key":"e_1_3_2_1_31_1","volume-title":"Conference on fairness, accountability and transparency.","author":"Buolamwini Joy","year":"2018","unstructured":"Joy Buolamwini and Timnit Gebru. 2018. Gender shades: Intersectional accuracy disparities in commercial gender classification. In Conference on fairness, accountability and transparency."},{"key":"e_1_3_2_1_32_1","volume-title":"Instilling new habits: addressing implicit bias in healthcare professionals. Advances in Health Sciences Education","author":"Byrne Aidan","year":"2015","unstructured":"Aidan Byrne and Alessandra Tanesini. 2015. Instilling new habits: addressing implicit bias in healthcare professionals. Advances in Health Sciences Education (2015)."},{"key":"e_1_3_2_1_33_1","volume-title":"Semantics derived automatically from language corpora contain human-like biases. Science","author":"Caliskan Aylin","year":"2017","unstructured":"Aylin Caliskan, Joanna J Bryson, and Arvind Narayanan. 2017. Semantics derived automatically from language corpora contain human-like biases. Science (2017)."},{"key":"e_1_3_2_1_34_1","volume-title":"Generalizability of an acute kidney injury prediction model across health systems. Nature Machine Intelligence","author":"Cao Jie","year":"2022","unstructured":"Jie Cao, Xiaosong Zhang, Vahakn Shahinian, Huiying Yin, Diane Steffick, Rajiv Saran, Susan Crowley, Michael Mathis, Girish N Nadkarni, Michael Heung, 2022. Generalizability of an acute kidney injury prediction model across health systems. Nature Machine Intelligence (2022)."},{"key":"e_1_3_2_1_35_1","volume":"199","author":"Cassidy Kimberly Wright","unstructured":"Kimberly Wright Cassidy, Michael H Kelly, and Lee\u2019at J Sharoni. 1999. Inferring gender from name phonology.Journal of Experimental Psychology: General (1999).","journal-title":"J Sharoni."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-3804"},{"key":"e_1_3_2_1_37_1","volume-title":"Ethical machine learning in healthcare. Annual review of biomedical data science","author":"Chen Irene Y","year":"2021","unstructured":"Irene Y Chen, Emma Pierson, Sherri Rose, Shalmali Joshi, Kadija Ferryman, and Marzyeh Ghassemi. 2021. Ethical machine learning in healthcare. Annual review of biomedical data science (2021)."},{"key":"e_1_3_2_1_38_1","volume-title":"A snapshot of the frontiers of fairness in machine learning. Commun. ACM","author":"Chouldechova Alexandra","year":"2020","unstructured":"Alexandra Chouldechova and Aaron Roth. 2020. A snapshot of the frontiers of fairness in machine learning. Commun. ACM (2020)."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.747"},{"key":"e_1_3_2_1_40_1","volume-title":"Quantifying social biases in nlp: A generalization and empirical comparison of extrinsic fairness metrics. Transactions of the Association for Computational Linguistics","author":"Czarnowska Paula","year":"2021","unstructured":"Paula Czarnowska, Yogarshi Vyas, and Kashif Shah. 2021. Quantifying social biases in nlp: A generalization and empirical comparison of extrinsic fairness metrics. Transactions of the Association for Computational Linguistics (2021)."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-3504"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3287560.3287572"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-2017"},{"key":"e_1_3_2_1_44_1","volume-title":"Ozlem Uzuner, and Peter Szolovits.","author":"Dernoncourt Franck","year":"2016","unstructured":"Franck Dernoncourt, Ji Young Lee, Ozlem Uzuner, and Peter Szolovits. 2016. De-identification of Patient Notes with Recurrent Neural Networks. Journal of the American Medical Informatics Association (JAMIA) (2016)."},{"key":"e_1_3_2_1_45_1","volume-title":"Demographic bias in biometrics: A survey on an emerging challenge","author":"Drozdowski Pawel","year":"2020","unstructured":"Pawel Drozdowski, Christian Rathgeb, Antitza Dantcheva, Naser Damer, and Christoph Busch. 2020. Demographic bias in biometrics: A survey on an emerging challenge. IEEE Transactions on Technology and Society (2020)."},{"key":"e_1_3_2_1_46_1","volume-title":"Is there bias in US law enforcement?The Journal of Social, Political, and Economic Studies","author":"Eisenman Russell","year":"1995","unstructured":"Russell Eisenman. 1995. Is there bias in US law enforcement?The Journal of Social, Political, and Economic Studies (1995)."},{"key":"e_1_3_2_1_47_1","volume-title":"Stops and stares: Street stops, surveillance, and race in the new policing. Fordham Urb. LJ","author":"Fagan Jeffrey","year":"2016","unstructured":"Jeffrey Fagan, Anthony A Braga, Rod K Brunson, and April Pattavina. 2016. Stops and stares: Street stops, surveillance, and race in the new policing. Fordham Urb. LJ (2016)."},{"key":"e_1_3_2_1_48_1","volume-title":"Implicit bias in healthcare professionals: a systematic review. BMC medical ethics","author":"FitzGerald Chlo\u00eb","year":"2017","unstructured":"Chlo\u00eb FitzGerald and Samia Hurst. 2017. Implicit bias in healthcare professionals: a systematic review. BMC medical ethics (2017)."},{"key":"e_1_3_2_1_49_1","volume-title":"a national patient-centered clinical research network. Journal of the American Medical Informatics Association","author":"Fleurence Rachael L","year":"2014","unstructured":"Rachael L Fleurence, Lesley H Curtis, Robert M Califf, Richard Platt, Joe V Selby, and Jeffrey S Brown. 2014. Launching PCORnet, a national patient-centered clinical research network. Journal of the American Medical Informatics Association (2014)."},{"key":"e_1_3_2_1_50_1","volume":"200","author":"Jeff Friedlin F","unstructured":"F Jeff Friedlin and Clement J McDonald. 2008. A software tool for removing patient identifying information from clinical documents. Journal of the American Medical Informatics Association (2008).","journal-title":"Clement J McDonald."},{"key":"e_1_3_2_1_51_1","volume-title":"The use of ranks to avoid the assumption of normality implicit in the analysis of variance. Journal of the american statistical association","author":"Friedman Milton","year":"1937","unstructured":"Milton Friedman. 1937. The use of ranks to avoid the assumption of normality implicit in the analysis of variance. Journal of the american statistical association (1937)."},{"key":"e_1_3_2_1_52_1","volume-title":"How black are Lakisha and Jamal? Racial perceptions from names used in correspondence audit studies. Sociological Science","author":"Gaddis S Michael","year":"2017","unstructured":"S Michael Gaddis. 2017. How black are Lakisha and Jamal? Racial perceptions from names used in correspondence audit studies. Sociological Science (2017)."},{"key":"e_1_3_2_1_53_1","volume-title":"Workshop on Interpretable ML in Healthcare at International Connference on Machine Learning (ICML).","author":"Ganz Melanie","year":"2021","unstructured":"Melanie Ganz, Sune H Holm, and Aasa Feragen. 2021. Assessing bias in medical ai. In Workshop on Interpretable ML in Healthcare at International Connference on Machine Learning (ICML)."},{"key":"e_1_3_2_1_54_1","volume-title":"Machine learning and health need better values. npj Digital Medicine","author":"Ghassemi Marzyeh","year":"2022","unstructured":"Marzyeh Ghassemi and Shakir Mohamed. 2022. Machine learning and health need better values. npj Digital Medicine (2022)."},{"key":"e_1_3_2_1_55_1","volume-title":"AMIA Summits on Translational Science Proceedings","author":"Ghassemi Marzyeh","year":"2020","unstructured":"Marzyeh Ghassemi, Tristan Naumann, Peter Schulam, Andrew L Beam, Irene Y Chen, and Rajesh Ranganath. 2020. A Review of Challenges and Opportunities in Machine Learning for Health. AMIA Summits on Translational Science Proceedings (2020)."},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"crossref","unstructured":"Marzyeh Ghassemi and Elaine Okanyene Nsoesie. 2022. In medicine how do we machine learn anything real?Patterns (2022).","DOI":"10.1016\/j.patter.2021.100392"},{"key":"e_1_3_2_1_57_1","volume-title":"Potential biases in machine learning algorithms using electronic health record data. JAMA internal medicine","author":"Gianfrancesco Milena A","year":"2018","unstructured":"Milena A Gianfrancesco, Suzanne Tamang, Jinoos Yazdany, and Gabriela Schmajuk. 2018. Potential biases in machine learning algorithms using electronic health record data. JAMA internal medicine (2018)."},{"key":"e_1_3_2_1_58_1","series-title":"Series B: Biological Sciences","volume-title":"Drift as a mechanism for cultural change: an example from baby names. Proceedings of the Royal Society of London","author":"Hahn Matthew W","year":"2003","unstructured":"Matthew W Hahn and R Alexander Bentley. 2003. Drift as a mechanism for cultural change: an example from baby names. Proceedings of the Royal Society of London. Series B: Biological Sciences (2003)."},{"key":"e_1_3_2_1_59_1","volume-title":"Steven H Day, and Tamera Coyne-Beasley.","author":"Hall William J","year":"2015","unstructured":"William J Hall, Mimi V Chapman, Kent M Lee, Yesenia M Merino, Tainayah W Thomas, B Keith Payne, Eugenia Eng, Steven H Day, and Tamera Coyne-Beasley. 2015. Implicit racial\/ethnic bias among health care professionals and its influence on health care outcomes: a systematic review. American journal of public health (2015)."},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/2998181.2998327"},{"key":"e_1_3_2_1_61_1","volume-title":"Discrimination in mortgage lending: Evidence from a correspondence experiment. Journal of Urban Economics","author":"Hanson Andrew","year":"2016","unstructured":"Andrew Hanson, Zackary Hawley, Hal Martin, and Bo Liu. 2016. Discrimination in mortgage lending: Evidence from a correspondence experiment. Journal of Urban Economics (2016)."},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"crossref","unstructured":"J Andrew Harris. 2015. What\u2019s in a name? A method for extracting information about ethnicity from names. Political Analysis (2015).","DOI":"10.1093\/pan\/mpu038"},{"key":"e_1_3_2_1_63_1","volume-title":"Long short-term memory. Neural computation","author":"Hochreiter Sepp","year":"1997","unstructured":"Sepp Hochreiter and J\u00fcrgen Schmidhuber. 1997. Long short-term memory. Neural computation (1997)."},{"key":"e_1_3_2_1_64_1","volume-title":"Sofie Van Landeghem, and Adriane Boyd","author":"Honnibal Matthew","year":"2020","unstructured":"Matthew Honnibal, Ines Montani, Sofie Van Landeghem, and Adriane Boyd. 2020. spaCy: Industrial-strength Natural Language Processing in Python. (2020)."},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.7"},{"key":"e_1_3_2_1_66_1","volume-title":"Understanding how and why audits work in improving the quality of hospital care: A systematic realist review. PloS one","author":"Hut-Mossel Lisanne","year":"2021","unstructured":"Lisanne Hut-Mossel, Kees Ahaus, Gera Welker, and Rijk Gans. 2021. Understanding how and why audits work in improving the quality of hospital care: A systematic realist review. PloS one (2021)."},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1145\/3287560.3287600"},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.487"},{"key":"e_1_3_2_1_69_1","volume-title":"Marit Johansen, Jeremy Grimshaw, and Andrew D Oxman.","author":"Ivers Noah","year":"2012","unstructured":"Noah Ivers, Gro Jamtvedt, Signe Flottorp, Jane M Young, Jan Odgaard-Jensen, Simon D French, Mary Ann O\u2019Brien, Marit Johansen, Jeremy Grimshaw, and Andrew D Oxman. 2012. Audit and feedback: effects on professional practice and healthcare outcomes. Cochrane database of systematic reviews (2012)."},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1145\/3351095.3375671"},{"key":"e_1_3_2_1_71_1","volume-title":"a freely accessible electronic health record dataset. Scientific data","author":"Johnson Alistair EW","year":"2023","unstructured":"Alistair EW Johnson, Lucas Bulgarelli, Lu Shen, Alvin Gayles, Ayad Shammout, Steven Horng, Tom J Pollard, Benjamin Moody, Brian Gow, Li-wei H Lehman, 2023. MIMIC-IV, a freely accessible electronic health record dataset. Scientific data (2023)."},{"key":"e_1_3_2_1_72_1","volume-title":"Leo Anthony Celi, and Roger G Mark","author":"Johnson Alistair EW","year":"2016","unstructured":"Alistair EW Johnson, Tom J Pollard, Lu Shen, Li-wei H Lehman, Mengling Feng, Mohammad Ghassemi, Benjamin Moody, Peter Szolovits, Leo Anthony Celi, and Roger G Mark. 2016. MIMIC-III, a freely accessible critical care database. Scientific data (2016)."},{"key":"e_1_3_2_1_73_1","volume-title":"Modes of De-identification. In AMIA Annual Symposium Proceedings.","author":"Kayaalp Mehmet","year":"2017","unstructured":"Mehmet Kayaalp. 2017. Modes of De-identification. In AMIA Annual Symposium Proceedings."},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/S18-2005"},{"key":"e_1_3_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-3823"},{"key":"e_1_3_2_1_76_1","volume-title":"Proceedings of the Eighteenth International Conference on Machine Learning.","author":"Lafferty John D","year":"2001","unstructured":"John D Lafferty, Andrew McCallum, and Fernando CN Pereira. 2001. Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data. In Proceedings of the Eighteenth International Conference on Machine Learning."},{"key":"e_1_3_2_1_77_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.73"},{"key":"e_1_3_2_1_78_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2020.2981314"},{"key":"e_1_3_2_1_79_1","volume-title":"International Conference on Machine Learning.","author":"Liang Paul Pu","year":"2021","unstructured":"Paul Pu Liang, Chiyu Wu, Louis-Philippe Morency, and Ruslan Salakhutdinov. 2021. Towards understanding and mitigating social biases in language models. In International Conference on Machine Learning."},{"key":"e_1_3_2_1_80_1","doi-asserted-by":"publisher","DOI":"10.13026\/ngc0-0f54"},{"key":"e_1_3_2_1_81_1","volume-title":"2013 AAAI Spring Symposium Series.","author":"Liu Wendy","year":"2013","unstructured":"Wendy Liu and Derek Ruths. 2013. What\u2019s in a name? using first names as features for gender inference in twitter. In 2013 AAAI Spring Symposium Series."},{"key":"e_1_3_2_1_82_1","volume-title":"Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692","author":"Liu Yinhan","year":"2019","unstructured":"Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019)."},{"key":"e_1_3_2_1_83_1","volume-title":"Sharing clinical trial data: maximizing benefits, minimizing risk. Jama","author":"Bernard Lo.","year":"2015","unstructured":"Bernard Lo. 2015. Sharing clinical trial data: maximizing benefits, minimizing risk. Jama (2015)."},{"key":"e_1_3_2_1_84_1","volume-title":"Name-based demographic inference and the unequal distribution of misrecognition. Nature Human Behaviour","author":"Lockhart Jeffrey W","year":"2023","unstructured":"Jeffrey W Lockhart, Molly M King, and Christin Munsch. 2023. Name-based demographic inference and the unequal distribution of misrecognition. Nature Human Behaviour (2023)."},{"key":"e_1_3_2_1_85_1","volume-title":"When and how convolutional neural networks generalize to out-of-distribution category\u2013viewpoint combinations. Nature Machine Intelligence","author":"Madan Spandan","year":"2022","unstructured":"Spandan Madan, Timothy Henry, Jamell Dozier, Helen Ho, Nishchal Bhandari, Tomotake Sasaki, Fr\u00e9do Durand, Hanspeter Pfister, and Xavier Boix. 2022. When and how convolutional neural networks generalize to out-of-distribution category\u2013viewpoint combinations. Nature Machine Intelligence (2022)."},{"key":"e_1_3_2_1_86_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P14-5010"},{"key":"e_1_3_2_1_87_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.ltedi-1.10"},{"key":"e_1_3_2_1_88_1","volume-title":"The impact of unconscious bias in healthcare: how to recognize and mitigate it. The Journal of infectious diseases","author":"Marcelin Jasmine R","year":"2019","unstructured":"Jasmine R Marcelin, Dawd S Siraj, Robert Victor, Shaila Kotadia, and Yvonne A Maldonado. 2019. The impact of unconscious bias in healthcare: how to recognize and mitigate it. The Journal of infectious diseases (2019)."},{"key":"e_1_3_2_1_89_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1530"},{"key":"e_1_3_2_1_90_1","volume-title":"Reproducibility in machine learning for health research: Still a ways to go. Science Translational Medicine","author":"McDermott Matthew BA","year":"2021","unstructured":"Matthew BA McDermott, Shirly Wang, Nikki Marinsek, Rajesh Ranganath, Luca Foschini, and Marzyeh Ghassemi. 2021. Reproducibility in machine learning for health research: Still a ways to go. Science Translational Medicine (2021)."},{"key":"e_1_3_2_1_91_1","doi-asserted-by":"publisher","DOI":"10.1145\/3372923.3404804"},{"key":"e_1_3_2_1_92_1","volume-title":"A survey on bias and fairness in machine learning. ACM Computing Surveys (CSUR)","author":"Mehrabi Ninareh","year":"2021","unstructured":"Ninareh Mehrabi, Fred Morstatter, Nripsuta Saxena, Kristina Lerman, and Aram Galstyan. 2021. A survey on bias and fairness in machine learning. ACM Computing Surveys (CSUR) (2021)."},{"key":"e_1_3_2_1_93_1","volume-title":"Automatic de-identification of textual documents in the electronic health record: a review of recent research. BMC medical research methodology","author":"Meystre Stephane M","year":"2010","unstructured":"Stephane M Meystre, F Jeffrey Friedlin, Brett R South, Shuying Shen, and Matthew H Samore. 2010. Automatic de-identification of textual documents in the electronic health record: a review of recent research. BMC medical research methodology (2010)."},{"key":"e_1_3_2_1_94_1","volume-title":"Assessing demographic bias in named entity recognition. arXiv preprint arXiv:2008.03415","author":"Mishra Shubhanshu","year":"2020","unstructured":"Shubhanshu Mishra, Sijun He, and Luca Belli. 2020. Assessing demographic bias in named entity recognition. arXiv preprint arXiv:2008.03415 (2020)."},{"key":"e_1_3_2_1_95_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.416"},{"key":"e_1_3_2_1_96_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.154"},{"key":"e_1_3_2_1_97_1","volume-title":"Protected Health Information filter (Philter): accurately and securely de-identifying free-text clinical notes. NPJ digital medicine","author":"Norgeot Beau","year":"2020","unstructured":"Beau Norgeot, Kathleen Muenzen, Thomas A Peterson, Xuancheng Fan, Benjamin S Glicksberg, Gundolf Schenk, Eugenia Rutenberg, Boris Oskotsky, Marina Sirota, Jinoos Yazdany, 2020. Protected Health Information filter (Philter): accurately and securely de-identifying free-text clinical notes. NPJ digital medicine (2020)."},{"key":"e_1_3_2_1_98_1","volume-title":"Francesca Dalia Faraci, and Athina Tzovara.","author":"Norori Natalia","year":"2021","unstructured":"Natalia Norori, Qiyang Hu, Florence Marcelle Aellen, Francesca Dalia Faraci, and Athina Tzovara. 2021. Addressing bias in big data and AI for health care: A call for open science. Patterns (2021)."},{"key":"e_1_3_2_1_99_1","volume-title":"Addressing health disparities by addressing structural racism and implicit bias in nursing education.Nurse Education Today","author":"Ochs Jessica H","year":"2022","unstructured":"Jessica H Ochs. 2022. Addressing health disparities by addressing structural racism and implicit bias in nursing education.Nurse Education Today (2022)."},{"key":"e_1_3_2_1_100_1","doi-asserted-by":"publisher","DOI":"10.1145\/3351095.3372843"},{"key":"e_1_3_2_1_101_1","volume-title":"Addressing bias in artificial intelligence in health care. Jama","author":"Parikh Ravi B","year":"2019","unstructured":"Ravi B Parikh, Stephanie Teeple, and Amol S Navathe. 2019. Addressing bias in artificial intelligence in health care. Jama (2019)."},{"key":"e_1_3_2_1_102_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"e_1_3_2_1_103_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-3810"},{"key":"e_1_3_2_1_104_1","volume-title":"Secure and robust machine learning for healthcare: A survey","author":"Qayyum Adnan","year":"2020","unstructured":"Adnan Qayyum, Junaid Qadir, Muhammad Bilal, and Ala Al-Fuqaha. 2020. Secure and robust machine learning for healthcare: A survey. IEEE Reviews in Biomedical Engineering (2020)."},{"key":"e_1_3_2_1_105_1","volume-title":"Manning","author":"Qi Peng","year":"2020","unstructured":"Peng Qi, Yuhao Zhang, Yuhui Zhang, Jason Bolton, and Christopher D. Manning. 2020. Stanza: A Python Natural Language Processing Toolkit for Many Human Languages. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations."},{"key":"e_1_3_2_1_106_1","doi-asserted-by":"publisher","DOI":"10.1145\/3306618.3314244"},{"key":"e_1_3_2_1_107_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2002"},{"key":"e_1_3_2_1_108_1","doi-asserted-by":"publisher","DOI":"10.3115\/1119176.1119195"},{"key":"e_1_3_2_1_109_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1163"},{"key":"e_1_3_2_1_110_1","volume-title":"Gender bias in machine translation. Transactions of the Association for Computational Linguistics","author":"Savoldi Beatrice","year":"2021","unstructured":"Beatrice Savoldi, Marco Gaido, Luisa Bentivogli, Matteo Negri, and Marco Turchi. 2021. Gender bias in machine translation. Transactions of the Association for Computational Linguistics (2021)."},{"key":"e_1_3_2_1_111_1","volume-title":"Flert: Document-level features for named entity recognition. arXiv preprint arXiv:2011.06993","author":"Schweter Stefan","year":"2020","unstructured":"Stefan Schweter and Alan Akbik. 2020. Flert: Document-level features for named entity recognition. arXiv preprint arXiv:2011.06993 (2020)."},{"key":"e_1_3_2_1_112_1","volume-title":"Louis Agha-Mir-Salim, Xavier Borrat Frigola","author":"Seastedt Kenneth P","year":"2022","unstructured":"Kenneth P Seastedt, Patrick Schwab, Zach O\u2019Brien, Edith Wakida, Karen Herrera, Portia Grace F Marcelo, Louis Agha-Mir-Salim, Xavier Borrat Frigola, Emily Boardman Ndulue, Alvin Marcelo, 2022. Global healthcare fairness: We should be sharing more, not less, data. PLOS Digital Health (2022)."},{"key":"e_1_3_2_1_113_1","doi-asserted-by":"crossref","unstructured":"Laleh Seyyed-Kalantari Guanxiong Liu Matthew McDermott Irene Chen and Marzyeh Ghassemi. 2021. Medical imaging algorithms exacerbate biases in underdiagnosis. (2021).","DOI":"10.21203\/rs.3.rs-151985\/v1"},{"key":"e_1_3_2_1_114_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.468"},{"key":"e_1_3_2_1_115_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICECA.2018.8474918"},{"key":"e_1_3_2_1_116_1","volume-title":"Neutralizing Gender Bias in Word Embeddings with Latent Disentanglement and Counterfactual Generation. In Findings of the Association for Computational Linguistics: EMNLP","author":"Shin Seungjae","year":"2020","unstructured":"Seungjae Shin, Kyungwoo Song, JoonHo Jang, Hyemi Kim, Weonyoung Joo, and Il-Chul Moon. 2020. Neutralizing Gender Bias in Word Embeddings with Latent Disentanglement and Counterfactual Generation. In Findings of the Association for Computational Linguistics: EMNLP 2020."},{"key":"e_1_3_2_1_117_1","volume-title":"Deep learning methods for biomedical named entity recognition: a survey and qualitative comparison. Briefings in Bioinformatics","author":"Song Bosheng","year":"2021","unstructured":"Bosheng Song, Fen Li, Yuansheng Liu, and Xiangxiang Zeng. 2021. Deep learning methods for biomedical named entity recognition: a survey and qualitative comparison. Briefings in Bioinformatics (2021)."},{"key":"e_1_3_2_1_118_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1164"},{"key":"e_1_3_2_1_119_1","volume-title":"Annotating longitudinal clinical narratives for de-identification: The 2014 i2b2\/UTHealth corpus. Journal of biomedical informatics","author":"Stubbs Amber","year":"2015","unstructured":"Amber Stubbs and \u00d6zlem Uzuner. 2015. Annotating longitudinal clinical narratives for de-identification: The 2014 i2b2\/UTHealth corpus. Journal of biomedical informatics (2015)."},{"key":"e_1_3_2_1_120_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1159"},{"key":"e_1_3_2_1_121_1","volume-title":"Proceedings of the AMIA Symposium.","author":"Thomas Sean M","year":"2002","unstructured":"Sean M Thomas, Burke Mamlin, Gunther Schadow, and Clement McDonald. 2002. A successful technique for removing names in pathology reports using an augmented search and replace method.. In Proceedings of the AMIA Symposium."},{"key":"e_1_3_2_1_122_1","volume-title":"A clinically applicable approach to continuous prediction of future acute kidney injury. Nature","author":"Toma\u0161ev Nenad","year":"2019","unstructured":"Nenad Toma\u0161ev, Xavier Glorot, Jack W Rae, Michal Zielinski, Harry Askham, Andre Saraiva, Anne Mottram, Clemens Meyer, Suman Ravuri, Ivan Protsyuk, 2019. A clinically applicable approach to continuous prediction of future acute kidney injury. Nature (2019)."},{"key":"e_1_3_2_1_123_1","doi-asserted-by":"crossref","unstructured":"Eric J Topol. 2019. High-performance medicine: the convergence of human and artificial intelligence. Nature medicine (2019).","DOI":"10.1038\/s41591-018-0300-7"},{"key":"e_1_3_2_1_124_1","volume-title":"The reproducibility issues that haunt health-care AI. Nature","author":"K TSIMA.","year":"2023","unstructured":"K TSIMA. 2023. The reproducibility issues that haunt health-care AI. Nature (2023)."},{"key":"e_1_3_2_1_125_1","volume-title":"Protecting patient privacy when sharing patient-level data from clinical trials. BMC medical research methodology","author":"Tucker Katherine","year":"2016","unstructured":"Katherine Tucker, Janice Branson, Maria Dilleen, Sally Hollis, Paul Loughlin, Mark J Nixon, and Zo\u00eb Williams. 2016. Protecting patient privacy when sharing patient-level data from clinical trials. BMC medical research methodology (2016)."},{"key":"e_1_3_2_1_126_1","volume-title":"Demographic aspects of first names. Scientific data","author":"Tzioumis Konstantinos","year":"2018","unstructured":"Konstantinos Tzioumis. 2018. Demographic aspects of first names. Scientific data (2018)."},{"key":"e_1_3_2_1_127_1","volume-title":"Evaluating the state-of-the-art in automatic de-identification. Journal of the American Medical Informatics Association","author":"Uzuner \u00d6zlem","year":"2007","unstructured":"\u00d6zlem Uzuner, Yuan Luo, and Peter Szolovits. 2007. Evaluating the state-of-the-art in automatic de-identification. Journal of the American Medical Informatics Association (2007)."},{"key":"e_1_3_2_1_128_1","volume-title":"A de-identifier for medical discharge summaries. Artificial intelligence in medicine","author":"Uzuner \u00d6zlem","year":"2008","unstructured":"\u00d6zlem Uzuner, Tawanda C Sibanda, Yuan Luo, and Peter Szolovits. 2008. A de-identifier for medical discharge summaries. Artificial intelligence in medicine (2008)."},{"key":"e_1_3_2_1_129_1","volume-title":"Social bias, discrimination and inequity in healthcare: mechanisms, implications and recommendations. BJA education","author":"Webster Craig S","year":"2022","unstructured":"Craig S Webster, Saana Taylor, Courtney Thomas, and Jennifer M Weller. 2022. Social bias, discrimination and inequity in healthcare: mechanisms, implications and recommendations. BJA education (2022)."},{"key":"e_1_3_2_1_130_1","volume-title":"Ontonotes release 5.0 ldc2013t19","author":"Weischedel Ralph","year":"2013","unstructured":"Ralph Weischedel, Martha Palmer, Mitchell Marcus, Eduard Hovy, Sameer Pradhan, Lance Ramshaw, Nianwen Xue, Ann Taylor, Jeff Kaufman, Michelle Franchini, 2013. Ontonotes release 5.0 ldc2013t19. Linguistic Data Consortium, Philadelphia, PA (2013)."},{"key":"e_1_3_2_1_131_1","volume-title":"Bonferroni correction. https:\/\/mathworld. wolfram. com\/","author":"Weisstein Eric W","year":"2004","unstructured":"Eric W Weisstein. 2004. Bonferroni correction. https:\/\/mathworld. wolfram. com\/ (2004)."},{"key":"e_1_3_2_1_132_1","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2015.9260"},{"key":"e_1_3_2_1_133_1","volume-title":"Wilcoxon signed-rank test","author":"Woolson Robert F","year":"2007","unstructured":"Robert F Woolson. 2007. Wilcoxon signed-rank test. Wiley encyclopedia of clinical trials (2007)."},{"key":"e_1_3_2_1_134_1","volume-title":"Proceedings of the 27th International Conference on Computational Linguistics.","author":"Yadav Vikas","year":"2018","unstructured":"Vikas Yadav and Steven Bethard. 2018. A Survey on Recent Advances in Named Entity Recognition from Deep Learning models. In Proceedings of the 27th International Conference on Computational Linguistics."},{"key":"e_1_3_2_1_135_1","volume-title":"Automatic detection of protected health information from clinic narratives. Journal of biomedical informatics","author":"Yang Hui","year":"2015","unstructured":"Hui Yang and Jonathan M Garibaldi. 2015. Automatic detection of protected health information from clinic narratives. Journal of biomedical informatics (2015)."},{"key":"e_1_3_2_1_136_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1074"},{"key":"e_1_3_2_1_137_1","volume-title":"Examining the presence, consequences, and reduction of implicit bias in health care: a narrative review","author":"Zestcott Colin A","year":"2016","unstructured":"Colin A Zestcott, Irene V Blair, and Jeff Stone. 2016. Examining the presence, consequences, and reduction of implicit bias in health care: a narrative review. Group Processes & Intergroup Relations (2016)."},{"key":"e_1_3_2_1_138_1","doi-asserted-by":"publisher","DOI":"10.1145\/3368555.3384448"},{"key":"e_1_3_2_1_139_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2003"}],"event":{"name":"FAccT '23: the 2023 ACM Conference on Fairness, Accountability, and Transparency","location":"Chicago IL USA","acronym":"FAccT '23"},"container-title":["2023 ACM Conference on Fairness Accountability and Transparency"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3593013.3593982","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3593013.3593982","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:48:02Z","timestamp":1750178882000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3593013.3593982"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,12]]},"references-count":139,"alternative-id":["10.1145\/3593013.3593982","10.1145\/3593013"],"URL":"https:\/\/doi.org\/10.1145\/3593013.3593982","relation":{},"subject":[],"published":{"date-parts":[[2023,6,12]]},"assertion":[{"value":"2023-06-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}