MedBot vs RealDoc: efficacy of large language modeling in physician-patient communication for rare diseases.
This study assesses the abilities of 2 large language models (LLMs), GPT-4 and BioMistral 7B, in responding to patient queries, particularly concerning rare diseases, and compares their performance with that of physicians.
Author(s): Weber, Magdalena T, Noll, Richard, Marchl, Alexandra, Facchinello, Carlo, Grünewaldt, Achim, Hügel, Christian, Musleh, Khader, Wagner, Thomas O F, Storf, Holger, Schaaf, Jannik
DOI: 10.1093/jamia/ocaf034