Published on in Vol 27 (2025)

Preprints (earlier versions) of this paper are available at https://preprints.jmir.org/preprint/68427, first published .
Enhancing Bidirectional Encoder Representations From Transformers (BERT) With Frame Semantics to Extract Clinically Relevant Information From German Mammography Reports: Algorithm Development and Validation

Enhancing Bidirectional Encoder Representations From Transformers (BERT) With Frame Semantics to Extract Clinically Relevant Information From German Mammography Reports: Algorithm Development and Validation

Enhancing Bidirectional Encoder Representations From Transformers (BERT) With Frame Semantics to Extract Clinically Relevant Information From German Mammography Reports: Algorithm Development and Validation

Daniel Reichenpfader   1, 2 , MSc ;   Jonas Knupp   3 , BSc ;   Sandro Urs von Däniken   4 , MD ;   Roberto Gaio   5 , MSc ;   Fabio Dennstädt   5 , MD ;   Grazia Maria Cereghetti   4 , PhD ;   André Sander   6 , Dr ;   Hans Hiltbrunner   4 , BA ;   Knud Nairz   4 , MBA, Dr ;   Kerstin Denecke   1 , Prof Dr

1 Institute for Patient-Centered Digital Health, School of Engineering and Computer Science, Bern University of Applied Sciences, Biel/Bienne, Switzerland

2 PhD School of Life Sciences, Faculty of Medicine, University of Geneva, Geneva, Switzerland

3 ID SUISSE AG, St. Gallen, Switzerland

4 Department of Diagnostic, Interventional, and Pediatric Radiology, Bern University Hospital, University of Bern, Bern, Switzerland

5 Department of Radiation Oncology, Bern University Hospital, University of Bern, Bern, Switzerland

6 ID BERLIN, Berlin, Germany

Corresponding Author:

  • Daniel Reichenpfader, MSc
  • Institute for Patient-Centered Digital Health
  • School of Engineering and Computer Science
  • Bern University of Applied Sciences
  • Quellgasse 21
  • Biel/Bienne 2502
  • Switzerland
  • Phone: 41 31 848 60 93
  • Email: daniel.reichenpfader@bfh.ch