MGH Radiology Llama: A Llama 3 70B Model for Radiology
This work addresses the need for better AI tools in radiology to assist radiologists with report generation, but it is incremental as it builds on existing domain-specific models.
The paper tackles the problem of generating accurate radiology impressions from findings by developing MGH Radiology Llama, a model based on Llama 3 70B, which shows significant improvements over general-purpose LLMs using a dataset of over 6.5 million medical reports.
In recent years, the field of radiology has increasingly harnessed the power of artificial intelligence (AI) to enhance diagnostic accuracy, streamline workflows, and improve patient care. Large language models (LLMs) have emerged as particularly promising tools, offering significant potential in assisting radiologists with report generation, clinical decision support, and patient communication. This paper presents an advanced radiology-focused large language model: MGH Radiology Llama. It is developed using the Llama 3 70B model, building upon previous domain-specific models like Radiology-GPT and Radiology-Llama2. Leveraging a unique and comprehensive dataset from Massachusetts General Hospital, comprising over 6.5 million de-identified medical reports across various imaging modalities, the model demonstrates significant improvements in generating accurate and clinically relevant radiology impressions given the corresponding findings. Our evaluation, incorporating both traditional metrics and a GPT-4-based assessment, highlights the enhanced performance of this work over general-purpose LLMs.