Deep Learning Approaches Outperform Conventional Strategies in De-Identification of German Medical Reports
Open Access
- 1 January 2019
- book chapter
- Published by IOS Press
- Vol. 267, 101-109
Abstract
One of the major obstacles for research on German medical reports is the lack of de-identified medical corpora. Previous de-identification tasks focused on non-German medical texts, which raised the demand for an in-depth evaluation of de-identification methods on German medical texts. Because of remarkable advancements in natural language processing using supervised machine learning methods on limited training data, we evaluated them for the first time on German medical reports using our annotated data set consisting of 113 medical reports from the cardiology domain. We applied state-of-the-art deep learning methods using pre-trained models as input to a bidirectional LSTM network and well-established conditional random fields for de-identification of German medical reports. We performed an extensive evaluation for de-identification and multiclass named entity recognition. Using rule based and out of domain machine learning methods as a baseline, the conditional random field improved F2-score from 70 to 93% for de-identification, the neural approach reached 96% in F2-score while keeping balanced precision and recall rates. These results show, that state-of-the-art machine learning methods can play a crucial role in de-identification of German medical reports.Keywords
This publication has 13 references indexed in Scilit:
- De-identification of clinical notes via recurrent neural network and conditional random fieldJournal of Biomedical Informatics, 2017
- The UAB Informatics Institute and 2016 CEGS N-GRID de-identification shared task challengeJournal of Biomedical Informatics, 2017
- Automatic de-identification of electronic medical records using token-level and character-level conditional random fieldsJournal of Biomedical Informatics, 2015
- Combining knowledge- and data-driven methods for de-identification of clinical narrativesJournal of Biomedical Informatics, 2015
- Automated systems for the de-identification of longitudinal clinical narratives: Overview of 2014 i2b2/UTHealth shared task Track 1Journal of Biomedical Informatics, 2015
- De-identification of clinical notes in French: towards a protocol for reference corpus developmentJournal of Biomedical Informatics, 2014
- Evaluating the impact of pre-annotation on annotation speed and potential bias: natural language processing gold standard development for clinical named entity recognition in clinical trial announcementsJournal of the American Medical Informatics Association, 2014
- Automatic de-identification of textual documents in the electronic health record: a review of recent researchBMC Medical Research Methodology, 2010
- A de-identifier for medical discharge summariesArtificial Intelligence in Medicine, 2008
- Rapidly Retargetable Approaches to De-identification in Medical RecordsJournal of the American Medical Informatics Association, 2007