Published on in Vol 9, No 2 (2021): February

Preprints (earlier versions) of this paper are available at https://preprints.jmir.org/preprint/22795, first published .
Adapting Bidirectional Encoder Representations from Transformers (BERT) to Assess Clinical Semantic Textual Similarity: Algorithm Development and Validation Study

Adapting Bidirectional Encoder Representations from Transformers (BERT) to Assess Clinical Semantic Textual Similarity: Algorithm Development and Validation Study

Adapting Bidirectional Encoder Representations from Transformers (BERT) to Assess Clinical Semantic Textual Similarity: Algorithm Development and Validation Study

Klaus Kades   1, 2 * , MSc ;   Jan Sellner   1, 3 * , MSc ;   Gregor Koehler   1 , MSc ;   Peter M Full   1, 4 , BSc ;   T Y Emmy Lai   1, 5 , MSc ;   Jens Kleesiek   1, 2, 3, 6 * , MD, PhD ;   Klaus H Maier-Hein   1, 2, 3, 4 * , PhD

1 German Cancer Research Center (DKFZ), Heidelberg, Germany

2 Partner Site Heidelberg, German Cancer Consortium (DKTK), Heidelberg, Germany

3 Helmholtz Information and Data Science School for Health, Karlsruhe/Heidelberg, Germany

4 Heidelberg University, Heidelberg, Germany

5 Hochschule Mannheim, University of Applied Sciences, Mannheim, Germany

6 Institute for Artificial Intelligence in Medicine (IKIM), University Medicine Essen, Essen, Germany

*these authors contributed equally

Corresponding Author:

  • Klaus Kades, MSc
  • German Cancer Research Center (DKFZ)
  • Im Neuenheimer Feld 280
  • Heidelberg, 69120
  • Germany
  • Phone: 49 6221420
  • Email: k.kades@dkfz.de