Critical assessment of transformer-based AI models for German clinical notes.
Manuel LentzenSumit MadanVanessa Lage-RupprechtLisa KühnelJuliane FluckMarc JacobsMirja MittermaierMartin WitzenrathPeter BruneckerMartin Hofmann-ApitiusJoachim WeberHolger FröhlichPublished in: JAMIA open (2022)
General-purpose language models perform remarkably well on biomedical and clinical NLP tasks. If larger corpora become available in the future, domain-adapting these models may improve performances.