{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,22]],"date-time":"2025-06-22T12:40:05Z","timestamp":1750596005162,"version":"3.41.0"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031958373"},{"type":"electronic","value":"9783031958380"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-95838-0_13","type":"book-chapter","created":{"date-parts":[[2025,6,22]],"date-time":"2025-06-22T11:14:37Z","timestamp":1750590877000},"page":"130-139","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Evaluating the\u00a0Confidentiality of\u00a0Synthetic Clinical Texts Generated by\u00a0Language Models"],"prefix":"10.1007","author":[{"given":"Foucauld","family":"Estignard","sequence":"first","affiliation":[]},{"given":"Sahar","family":"Ghannay","sequence":"additional","affiliation":[]},{"given":"Julien","family":"Girard-Satabin","sequence":"additional","affiliation":[]},{"given":"Nicolas","family":"Hiebel","sequence":"additional","affiliation":[]},{"given":"Aur\u00e9lie","family":"N\u00e9v\u00e9ol","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,6,23]]},"reference":[{"unstructured":"Amin-Nejad, A., Ive, J., Velupillai, S.: Exploring transformer text generation for medical dataset augmentation. In: Proceedings of LREC, pp. 4699\u20134708 (2020)","key":"13_CR1"},{"doi-asserted-by":"crossref","unstructured":"Boulanger, H., Hiebel, N., Ferret, O., Fort, K., N\u00e9v\u00e9ol, A.: Using structured health information for controlled generation of clinical cases in French. In: Proceedings of ClinicalNLP, Mexico city, Mexico (2024)","key":"13_CR2","DOI":"10.18653\/v1\/2024.clinicalnlp-1.14"},{"doi-asserted-by":"crossref","unstructured":"Brickell, J., Shmatikov, V.: The cost of privacy: destruction of data-mining utility in anonymized data publishing. In: Proceedings of ACM SIGKDD, pp. 70\u201378. KDD (2008)","key":"13_CR3","DOI":"10.1145\/1401890.1401904"},{"doi-asserted-by":"crossref","unstructured":"Carlini, N., Chien, S., Nasr, M., Song, S., Terzis, A., Tramer, F.: Membership inference attacks from first principles. In: IEEE S &P, pp. 1897\u20131914 (2022)","key":"13_CR4","DOI":"10.1109\/SP46214.2022.9833649"},{"unstructured":"Carlini, N., et\u00a0al.: Extracting training data from large language models. In: USENIX Security, pp. 2633\u20132650 (2021)","key":"13_CR5"},{"doi-asserted-by":"crossref","unstructured":"Chen, T., Guestrin, C.: XGBoost: a scalable tree boosting system. In: Proceedings of ACM SIGKDD, KDD, pp. 785\u2013794. ACM, New York (2016)","key":"13_CR6","DOI":"10.1145\/2939672.2939785"},{"key":"13_CR7","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1007\/BF00994018","volume":"20","author":"C Cortes","year":"1995","unstructured":"Cortes, C., Vapnik, V.: Support-vector networks. Mach. Learn. 20, 273\u2013297 (1995)","journal-title":"Mach. Learn."},{"issue":"3","key":"13_CR8","first-page":"596","volume":"24","author":"F Dernoncourt","year":"2017","unstructured":"Dernoncourt, F., Lee, J.Y., Uzuner, O., Szolovits, P.: De-identification of patient notes with recurrent neural networks. JAMIA 24(3), 596\u2013606 (2017)","journal-title":"JAMIA"},{"doi-asserted-by":"crossref","unstructured":"Dwork, C.: Differential privacy. In: Automata. Languages and Programming, pp. 1\u201312. Springer, Heidelberg (2006)","key":"13_CR9","DOI":"10.1007\/11787006_1"},{"key":"13_CR10","first-page":"601","volume":"15","author":"F Friedlin","year":"2008","unstructured":"Friedlin, F., Mcdonald, C.: A software tool for removing patient identifying information from clinical documents. JAMIA 15, 601\u201310 (2008)","journal-title":"JAMIA"},{"key":"13_CR11","doi-asserted-by":"publisher","first-page":"1441","DOI":"10.1016\/j.datak.2009.07.006","volume":"68","author":"J Gardner","year":"2009","unstructured":"Gardner, J., Xiong, L.: An integrated framework for de-identifying unstructured medical data. Data Knowl. Eng. 68, 1441\u20131451 (2009)","journal-title":"Data Knowl. Eng."},{"doi-asserted-by":"publisher","unstructured":"Grouin, C., Griffon, N., N\u00e9v\u00e9ol, A.: Is it possible to recover personal health information from an automatically de-identified corpus of French EHRs? In: Proceedings of LOUHI, pp. 31\u201339 (2015). https:\/\/doi.org\/10.18653\/v1\/W15-2604","key":"13_CR12","DOI":"10.18653\/v1\/W15-2604"},{"doi-asserted-by":"crossref","unstructured":"Hiebel, N., Ferret, O., Fort, K., N\u00e9v\u00e9ol, A.: Can synthetic text help clinical named entity recognition? a study of electronic health records in French. In: Proceedings of EACL, pp. 2320\u20132338. ACL, Dubrovnik (2023)","key":"13_CR13","DOI":"10.18653\/v1\/2023.eacl-main.170"},{"doi-asserted-by":"publisher","unstructured":"Le\u00a0Scao, T., Others: BLOOM: a 176B-parameter open-access multilingual language model. arXiv (2022). https:\/\/doi.org\/10.48550\/arxiv.2211.05100","key":"13_CR14","DOI":"10.48550\/arxiv.2211.05100"},{"doi-asserted-by":"crossref","unstructured":"Li, N., Li, T., Venkatasubramanian, S.: t-closeness: privacy beyond k-anonymity and l-diversity. In: ICDE, pp. 106\u2013115 (2007)","key":"13_CR15","DOI":"10.1109\/ICDE.2007.367856"},{"doi-asserted-by":"crossref","unstructured":"Machanavajjhala, A., Gehrke, J., Kifer, D., Venkitasubramaniam, M.: $$\\ell $$-diversity: privacy beyond k-anonymity. In: ICDE, pp. 24\u201324 (2006)","key":"13_CR16","DOI":"10.1109\/ICDE.2006.1"},{"doi-asserted-by":"crossref","unstructured":"Melamud, O., Shivade, C.: Towards automatic generation of shareable synthetic clinical notes using neural language models (2019). https:\/\/arxiv.org\/abs\/1905.07002","key":"13_CR17","DOI":"10.18653\/v1\/W19-1905"},{"doi-asserted-by":"crossref","unstructured":"Narayanan, A., Shmatikov, V.: Robust de-anonymization of large sparse datasets. In: Proceedings of IEEE Symposium on Security and Privacy (2008)","key":"13_CR18","DOI":"10.1109\/SP.2008.33"},{"doi-asserted-by":"crossref","unstructured":"Raschka, S.: MLxtend: providing machine learning and data science utilities and extensions to Python\u2019s scientific computing stack. JOSS 3(24) (2018)","key":"13_CR19","DOI":"10.21105\/joss.00638"},{"doi-asserted-by":"crossref","unstructured":"Salem, A., Zhang, Y., Humbert, M., Berrang, P., Fritz, M., Backes, M.: ML-Leaks: model and data independent membership inference attacks and defenses on machine learning models (2018). https:\/\/arxiv.org\/abs\/1806.01246","key":"13_CR20","DOI":"10.14722\/ndss.2019.23119"},{"issue":"6","key":"13_CR21","doi-asserted-by":"publisher","first-page":"1010","DOI":"10.1109\/69.971193","volume":"13","author":"P Samarati","year":"2001","unstructured":"Samarati, P.: Protecting respondents identities in microdata release. IEEE Trans. Knowl. Data Eng. 13(6), 1010\u20131027 (2001)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"doi-asserted-by":"crossref","unstructured":"Shokri, R., Stronati, M., Song, C., Shmatikov, V.: Membership inference attacks against machine learning models. In: 2017 IEEE Symposium on Security and Privacy (SP), pp. 3\u201318. IEEE (2017)","key":"13_CR22","DOI":"10.1109\/SP.2017.41"},{"unstructured":"Sweeney, L.: Replacing personally-identifying information in medical records, the Scrub system. In: Proceedings of AMIA Fall Symposium, pp. 333\u20137 (1996)","key":"13_CR23"},{"unstructured":"Sweeney, L.: Simple Demographics Often Identify People Uniquely (2000). http:\/\/dataprivacylab.org\/projects\/identifiability\/","key":"13_CR24"},{"unstructured":"Tang, R., Han, X., Jiang, X., Hu, X.: Does synthetic data generation of LLMs help clinical text mining? (2023). https:\/\/arxiv.org\/abs\/2303.04360","key":"13_CR25"},{"issue":"5","key":"13_CR26","first-page":"564","volume":"14","author":"B Wellner","year":"2007","unstructured":"Wellner, B., et al.: Rapidly retargetable approaches to de-identification in medical records. JAMIA 14(5), 564\u2013573 (2007)","journal-title":"JAMIA"}],"container-title":["Lecture Notes in Computer Science","Artificial Intelligence in Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-95838-0_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,22]],"date-time":"2025-06-22T12:01:37Z","timestamp":1750593697000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-95838-0_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031958373","9783031958380"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-95838-0_13","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"23 June 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The code used is available at: .","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Code Availability"}},{"value":"AIME","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Intelligence in Medicine","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pavia","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 June 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 June 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"aime2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/aime25.aimedicine.info\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}