A Study Of Generative Large Language Model For Medical Research And Healthcare
Peng Cheng, Yang Xi, Chen Aokun, Smith Kaleb E, Pournejatian Nima, Costa Anthony B, Martin Cheryl, Flores Mona G, Zhang Ying, Magoc Tanja, Lipori Gloria, Mitchell Duane A, Ospina Naykky S, Ahmed Mustafa M, Hogan William R, Shenkman Elizabeth A, Guo Yi, Bian Jiang, Wu Yonghui. Arxiv 2023
[Paper]
There is enormous enthusiasm and concerns in using large language models (LLMs) in healthcare, yet current assumptions are all based on general-purpose LLMs such as ChatGPT. This study develops a clinical generative LLM, GatorTronGPT, using 277 billion words of mixed clinical and English text with a GPT-3 architecture of 20 billion parameters. GatorTronGPT improves biomedical natural language processing for medical research. Synthetic NLP models trained using GatorTronGPT generated text outperform NLP models trained using real-world clinical text. Physicians Turing test using 1 (worst) to 9 (best) scale shows that there is no significant difference in linguistic readability (p = 0.22; 6.57 of GatorTronGPT compared with 6.93 of human) and clinical relevance (p = 0.91; 7.0 of GatorTronGPT compared with 6.97 of human) and that physicians cannot differentiate them (p < 0.001). This study provides insights on the opportunities and challenges of LLMs for medical research and healthcare.
Similar Work