no code implementations • 9 Mar 2024 • Rui Yang, Haoran Liu, Edison Marrese-Taylor, Qingcheng Zeng, Yu He Ke, Wanxin Li, Lechao Cheng, Qingyu Chen, James Caverlee, Yutaka Matsuo, Irene Li
Large Language Models (LLMs) have significantly advanced healthcare innovation on generation capabilities.
no code implementations • 26 Jan 2024 • Yu He Ke, Rui Yang, Sui An Lie, Taylor Xin Yi Lim, Hairil Rizal Abdullah, Daniel Shu Wei Ting, Nan Liu
Results: In a total of 80 responses evaluating both initial and final diagnoses, the initial diagnosis had an accuracy of 0% (0/80), but following multi-agent discussions, the accuracy for the top differential diagnosis increased to 71. 3% (57/80), and for the final two differential diagnoses, to 80. 0% (64/80).