Clinical Text Anonymization, its Influence on Downstream NLP Tasks and the Risk of Re-IdentificationIyadh Ben Cheikh Larbi; Aljoscha Burchardt; Roland Roller
In: Elisa Bassignana; Matthias Lindemann; Alban Petit (Hrsg.). EACL 2023 - Proceedings of the Student Research Workshop. Conference of the European Chapter of the Association for Computational Linguistics: Student Research Workshop (EACL-2023), May 2-4, Pages 105-111, ISBN 978-1-959429-48-7, ACL, 5/2023.
While text-based medical applications have become increasingly prominent, access to clinical data remains a major concern. To resolve this issue, further de-identification and anonymization of the data are required. This might, however, alter the contextual information within the clinical texts and therefore influence the learning and performance of possible language models. This paper systematically analyses the potential effects of various anonymization techniques on the performance of state-of-the-art machine learning models based on several datasets corresponding to five different NLP tasks. On this basis, we derive insightful findings and recommendations concerning text anonymization with regard to the performance of machine learning models. In addition, we present a simple re-identification attack applied to the anonymized text data, which can break the anonymization.
vALID - Artificial-Intelligence-Driven Decision-Making in the Clinic: Ethical, Legal and Societal Challenges