Clinical Text Anonymization, its Influence on Downstream NLP Tasks and the Risk of Re-Identification

Iyadh Ben Cheikh Larbi, Aljoscha Burchardt, Roland Roller


Abstract
While text-based medical applications have become increasingly prominent, access to clinicaldata 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.
Anthology ID:
2023.eacl-srw.11
Volume:
Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics: Student Research Workshop
Month:
May
Year:
2023
Address:
Dubrovnik, Croatia
Editors:
Elisa Bassignana, Matthias Lindemann, Alban Petit
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
105–111
Language:
URL:
https://aclanthology.org/2023.eacl-srw.11
DOI:
10.18653/v1/2023.eacl-srw.11
Bibkey:
Cite (ACL):
Iyadh Ben Cheikh Larbi, Aljoscha Burchardt, and Roland Roller. 2023. Clinical Text Anonymization, its Influence on Downstream NLP Tasks and the Risk of Re-Identification. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics: Student Research Workshop, pages 105–111, Dubrovnik, Croatia. Association for Computational Linguistics.
Cite (Informal):
Clinical Text Anonymization, its Influence on Downstream NLP Tasks and the Risk of Re-Identification (Ben Cheikh Larbi et al., EACL 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.eacl-srw.11.pdf
Video:
 https://aclanthology.org/2023.eacl-srw.11.mp4