GatorTronGPT Model

GatorTronGPT™ is a foundation model that can be adopted in many clinical research and healthcare applications involving healthcare text analytics. GatorTronGPT improves biomedical natural language processing for medical research. 

The GatorTronGPT model is a decoder-only large language model developed using the GPT-3 architecture, a neural network architecture used by ChatGPT. GatorTronGPT is a generative clinical LLM that can generate human-like context and responses known as generative artificial intelligence. 

In addition to the applications that can be solved using GatorTron, GatorTronGPT is a generative AI to support conversational applications such as handling patient inquiries and consultations as virtual assistants, assisting document patient information, generating summarization of patient reports, facilitating patient recruitment of trials and education of medical students and patients.  

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).