% IMPORTANT: The following is UTF-8 encoded.  This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.

@ARTICLE{Dada:277860,
      author       = {A. Dada and T. L. Ufer and M. Kim and M. Hasin and N.
                      Spieker and M. Forsting and F. Nensa and J. Egger and J.
                      Kleesiek$^*$},
      title        = {{I}nformation extraction from weakly structured
                      radiological reports with natural language queries.},
      journal      = {European radiology},
      volume       = {34},
      number       = {1},
      issn         = {0938-7994},
      address      = {Heidelberg},
      publisher    = {Springer},
      reportid     = {DKFZ-2023-01528},
      pages        = {330-337},
      year         = {2024},
      note         = {2024 Jan;34(1):330-337},
      abstract     = {Provide physicians and researchers an efficient way to
                      extract information from weakly structured radiology reports
                      with natural language processing (NLP) machine learning
                      models.We evaluate seven different German bidirectional
                      encoder representations from transformers (BERT) models on a
                      dataset of 857,783 unlabeled radiology reports and an
                      annotated reading comprehension dataset in the format of
                      SQuAD 2.0 based on 1223 additional reports.Continued
                      pre-training of a BERT model on the radiology dataset and a
                      medical online encyclopedia resulted in the most accurate
                      model with an F1-score of $83.97\%$ and an exact match score
                      of $71.63\%$ for answerable questions and $96.01\%$ accuracy
                      in detecting unanswerable questions. Fine-tuning a
                      non-medical model without further pre-training led to the
                      lowest-performing model. The final model proved stable
                      against variation in the formulations of questions and in
                      dealing with questions on topics excluded from the training
                      set.General domain BERT models further pre-trained on
                      radiological data achieve high accuracy in answering
                      questions on radiology reports. We propose to integrate our
                      approach into the workflow of medical practitioners and
                      researchers to extract information from radiology reports.By
                      reducing the need for manual searches of radiology reports,
                      radiologists' resources are freed up, which indirectly
                      benefits patients.• BERT models pre-trained on general
                      domain datasets and radiology reports achieve high accuracy
                      $(83.97\%$ F1-score) on question-answering for radiology
                      reports. • The best performing model achieves an F1-score
                      of $83.97\%$ for answerable questions and $96.01\%$ accuracy
                      for questions without an answer. • Additional
                      radiology-specific pretraining of all investigated BERT
                      models improves their performance.},
      keywords     = {Information extraction (Other) / Machine learning (Other) /
                      Natural language processing (Other)},
      cin          = {ED01},
      ddc          = {610},
      cid          = {I:(DE-He78)ED01-20160331},
      pnm          = {899 - ohne Topic (POF4-899)},
      pid          = {G:(DE-HGF)POF4-899},
      typ          = {PUB:(DE-HGF)16},
      pubmed       = {pmid:37505252},
      doi          = {10.1007/s00330-023-09977-3},
      url          = {https://inrepo02.dkfz.de/record/277860},
}