Zero-shot Thoracic Oncologic History Generation for Radiologists Using Retrieval-augmented Large Language Model Pipeline

Background Gathering oncologic history is necessary but inefficient. Recent efforts to generate clinical summaries using large language models (LLMs) have relied on manual information retrieval, prompt tuning, and subjective evaluation, limiting clinical translation. Purpose T...

• Source: Radiology (RSNA) (PRIMARY)
• Type: Research

RadPigeon summaries are original and for information only. They are not clinical advice.