Building a De-identification System for Real Swedish Clinical Text Using Pseudonymised Clinical Text

Hanna Berg, Taridzo Chomutare, Hercules Dalianis


Abstract
This article presents experiments with pseudonymised Swedish clinical text used as training data to de-identify real clinical text with the future aim to transfer non-sensitive training data to other hospitals. Conditional Random Fields (CFR) and Long Short-Term Memory (LSTM) machine learning algorithms were used to train de-identification models. The two models were trained on pseudonymised data and evaluated on real data. For benchmarking, models were also trained on real data, and evaluated on real data as well as trained on pseudonymised data and evaluated on pseudonymised data. CRF showed better performance for some PHI information like Date Part, First Name and Last Name; consistent with some reports in the literature. In contrast, poor performances on Location and Health Care Unit information were noted, partially due to the constrained vocabulary in the pseudonymised training data. It is concluded that it is possible to train transferable models based on pseudonymised Swedish clinical data, but even small narrative and distributional variation could negatively impact performance.
Anthology ID:
D19-6215
Volume:
Proceedings of the Tenth International Workshop on Health Text Mining and Information Analysis (LOUHI 2019)
Month:
November
Year:
2019
Address:
Hong Kong
Venues:
EMNLP | Louhi | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
118–125
Language:
URL:
https://www.aclweb.org/anthology/D19-6215
DOI:
10.18653/v1/D19-6215
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/D19-6215.pdf