GERNERMED: An open German medical NER model

Frei, Johann

doi:10.1016/j.simpa.2021.100212

Cited by 22 publications

(16 citation statements)

References 6 publications

(9 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To avoid inadequate evaluation issues such as missing UMLS references or ambiguous mappings between non-isomorphic knowledge bases, we consider the annotation task as a binary text segmentation task at which the annotation spans define the binary segmentation mask. For clinical contexts, we randomly drew 50 samples from the GERNERMED [ 55 ] test set and manually corrected incorrect annotation spans, since the dataset is based on an automated translation of the n2c2 2018 ADE and Medication Extraction Challenge [ 50 ] dataset with automated annotation alignments. All labels except for Drug were omitted for comparison reasons.…”

Section: Resultsmentioning

confidence: 99%

DrNote: An open medical annotation service

Frei

Soto-Rey

2022

PLOS Digit Health

Self Cite

View full text Add to dashboard Cite

In the context of clinical trials and medical research medical text mining can provide broader insights for various research scenarios by tapping additional text data sources and extracting relevant information that is often exclusively present in unstructured fashion. Although various works for data like electronic health reports are available for English texts, only limited work on tools for non-English text resources has been published that offers immediate practicality in terms of flexibility and initial setup. We introduce DrNote, an open source text annotation service for medical text processing. Our work provides an entire annotation pipeline with its focus on a fast yet effective and easy to use software implementation. Further, the software allows its users to define a custom annotation scope by filtering only for relevant entities that should be included in its knowledge base. The approach is based on OpenTapioca and combines the publicly available datasets from WikiData and Wikipedia, and thus, performs entity linking tasks. In contrast to other related work our service can easily be built upon any language-specific Wikipedia dataset in order to be trained on a specific target language. We provide a public demo instance of our DrNote annotation service at https://drnote.misit-augsburg.de/.

show abstract

Section: Resultsmentioning

confidence: 99%

DrNote: An open medical annotation service

Frei

Soto-Rey

2022

PLOS Digit Health

Self Cite

View full text Add to dashboard Cite

show abstract

“…We convert two of these labels into entity types required for our target task: (Procedure -> Treatment), (Disorder -> Diagnosis). Beyond the English n2c2 corpus, we use the GERNERMED (Frei and Kramer, 2021), which was created by automatically translating a subset of English sentences from n2c2. We refer to it as German n2c2.…”

Section: Discussionmentioning

confidence: 99%

Cross-lingual German Biomedical Information Extraction: from Zero-shot to Human-in-the-Loop

Liang¹,

Hartmann²,

Sonntag³

2023

Preprint

View full text Add to dashboard Cite

This paper presents our project proposal for extracting biomedical information from German clinical narratives with limited amounts of annotations. We first describe the applied strategies in transfer learning and active learning for solving our problem. After that, we discuss the design of the user interface for both supplying model inspection and obtaining user annotations in the interactive environment.

show abstract

“…As an exception, mEx [31] is freely available, but the model weights must be requested and legal restrictions on the models' usage are imposed. For German medical NER tasks, no public and open neural model is available to the best of our knowledge, except for GERMERMED [11].…”

Section: Related Workmentioning

confidence: 99%

“…The dataset retrieval pipeline for German texts follows the approach proposed in GERNERMED [11]: As a starting point, the 2018 n2c2 shared task on ADE and medication extraction in EHR dataset serves as English source dataset of medical entities from anonymized electronic health records. The source dataset is decomposed into sentences as initial preprocessing step.…”

Section: Dataset Acquisitionmentioning

confidence: 99%

GERNERMED++: Transfer Learning in German Medical NLP

Frei¹,

Frei-Stuber²

2022

Preprint

Self Cite

View full text Add to dashboard Cite

We present a statistical model for German medical natural language processing trained for named entity recognition (NER) as an open, publicly available model. The work serves as a refined successor to our first GERNERMED model which is substantially outperformed by our work. We demonstrate the effectiveness of combining multiple techniques in order to achieve strong results in entity recognition performance by the means of transfer-learning on pretrained deep language models (LM), word-alignment and neural machine translation. Due to the sparse situation on open, public medical entity recognition models for German texts, this work offers benefits to the German research community on medical NLP as a baseline model. Since our model is based on public English data, its weights are provided without legal restrictions on usage and distribution. The sample code and the statistical model is available at: https://github.com/frankkramer-lab/GERNERMED-pp

show abstract

GERNERMED: An open German medical NER model

Cited by 22 publications

References 6 publications

DrNote: An open medical annotation service

DrNote: An open medical annotation service

Cross-lingual German Biomedical Information Extraction: from Zero-shot to Human-in-the-Loop

GERNERMED++: Transfer Learning in German Medical NLP

Contact Info

Product

Resources

About