Cristiane D Bergerot, Former Postdoc Fellow & Research Consultant at City of Hope, shared a post on X:
“Can AI help patients better understand cancer clinical trials?
A study comparing GPT-4o and Llama-3.2 found important differences in reliability, with fabricated responses occurring in 14.5% of answers.”
Title: Are Large Language Models the Swiss Army Knife or the Scalpel for Clinical Research?
Authors: Peter P. Yu, Tony K.W. Hung
Read the Full Article.
Title: Evaluating the Use of Large Language Models to Answer Patient-Facing Clinical Trial Questions
Authors: Jack Gallifant, Lizhou Fan, Ziqian Liao, Shan Chen, Hugo J.W.L. Aerts, Dmitriy Dligach, Ramez Kouzy, Danielle S. Bitterman
Read the Full Article.
Other articles about AI in oncology on OncoDaily.