"Researchers Test Large Language Model that Preserves Patient Privacy"

According to a new study conducted by the National Institutes of Health Clinical Center (NIH CC), locally run Large Language Models (LLMs) may be a feasible option for extracting data from text-based radiology reports while protecting patient privacy. ChatGPT and GPT-4, two recently released LLM models, have garnered much attention but are incompatible with healthcare data due to privacy constraints. This article continues to discuss the research on locally run LLMs being a workable option for extracting data from text-based radiology reports while preserving patient privacy.

RSNA reports "Researchers Test Large Language Model that Preserves Patient Privacy"

Submitted by grigby1