Radiology-GPT: A Large Language Model for Radiology
This work addresses the problem of improving AI tools for radiology professionals by creating a domain-specific model that ensures privacy compliance, though it is incremental as it adapts existing methods to a new medical specialty.
The authors tackled the need for specialized language models in radiology by developing Radiology-GPT, which outperforms general models like StableLM, Dolly, and LLaMA in radiological tasks such as diagnosis, research, and communication.
We introduce Radiology-GPT, a large language model for radiology. Using an instruction tuning approach on an extensive dataset of radiology domain knowledge, Radiology-GPT demonstrates superior performance compared to general language models such as StableLM, Dolly and LLaMA. It exhibits significant versatility in radiological diagnosis, research, and communication. This work serves as a catalyst for future developments in clinical NLP. The successful implementation of Radiology-GPT is indicative of the potential of localizing generative large language models, specifically tailored for distinctive medical specialties, while ensuring adherence to privacy standards such as HIPAA. The prospect of developing individualized, large-scale language models that cater to specific needs of various hospitals presents a promising direction. The fusion of conversational competence and domain-specific knowledge in these models is set to foster future development in healthcare AI. A demo of Radiology-GPT is available at https://huggingface.co/spaces/allen-eric/radiology-gpt.