Maintenance Notice

Due to necessary scheduled maintenance, the JMIR Publications website will be unavailable from Wednesday, July 01, 2020 at 8:00 PM to 10:00 PM EST. We apologize in advance for any inconvenience this may cause you.

Who will be affected?

Accepted for/Published in: JMIR Formative Research

Date Submitted: Apr 27, 2022
Date Accepted: Nov 3, 2022

The final, peer-reviewed published version of this preprint can be found here:

German Medical Named Entity Recognition Model and Data Set Creation Using Machine Translation and Word Alignment: Algorithm Development and Validation

Frei J, Kramer F

German Medical Named Entity Recognition Model and Data Set Creation Using Machine Translation and Word Alignment: Algorithm Development and Validation

JMIR Form Res 2023;7:e39077

DOI: 10.2196/39077

PMID: 36853741

PMCID: 10015355

Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.

GERNERMED: An Open German Medical NER Model

  • Johann Frei; 
  • Frank Kramer

ABSTRACT

Background:

Data mining in the field of medical data analysis often needs to rely solely on processing of unstructured data to retrieve relevant data. For German NLP, no open medical neural named entity recognition (NER) model has been published prior to this work. A major issue can be attributed to the lack of German training data.

Objective:

We develop a novel German medical NER model for public access. In order to bypass legal restrictions due to potential data leaks through model analysis, we do not make use of internal, proprietary datasets.

Methods:

The underlying German dataset is retrieved by translation and word alignment of a public English dataset. The dataset serves as foundation for model training and evaluation.

Results:

The obtained dataset consists of 8599 sentences including 30233 annotations. The model achieves an averaged f1 score of 0.82 on the test set after training across seven different NER types. The model is publicly available.

Conclusions:

We demonstrate the feasibility of training a German medical NER model by the exclusive use of public training data. The sample code and the statistical model are available on GitHub.


 Citation

Please cite as:

Frei J, Kramer F

German Medical Named Entity Recognition Model and Data Set Creation Using Machine Translation and Word Alignment: Algorithm Development and Validation

JMIR Form Res 2023;7:e39077

DOI: 10.2196/39077

PMID: 36853741

PMCID: 10015355

Download PDF


Request queued. Please wait while the file is being generated. It may take some time.

© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.