Assessing the Limitations of Large Language Models in Clinical Practice Guideline–Concordant Treatment Decision-Making on Real-World Data: Retrospective Study

Assessing the Limitations of Large Language Models in Clinical Practice Guideline–Concordant Treatment Decision-Making on Real-World Data: Retrospective Study

Authors of this article:

Tobias Roeschl^{1, 2, 3, 4, 5} ;   Marie Hoffmann^{2, 4, 5} ;   Djawid Hashemi^{1, 2, 3, 4} ;   Felix Rarreck^{2, 5} ;   Nils Hinrichs^{2, 4, 5} ;   Tobias Daniel Trippel^{1, 2, 4} ;   Matthias I Gröschel^{2, 6} ;   Axel Unbehaun^{2, 5} ;   Christoph Klein^{2, 5} ;   Jörg Kempfert^{2, 5} ;   Henryk Dreger^{1, 2} ;   Benjamin O'Brien^{2, 7, 8} ;   Gerhard Hindricks^{1, 2} ;   Felix Balzer^{2, 9} ;   Volkmar Falk^{2, 4, 5, 10} ;   Alexander Meyer^{2, 4, 5, 11}