Protocol Automation Using LLMs

Choosing the right scanning protocol for patients, based on their clinical referrals, is a crucial step in the radiological process. This decision ensures accurate diagnosis and optimal patient care. However, radiologists often spend hours each day determining the most appropriate protocol for each patient, diverting time away from their primary diagnostic tasks.

Our project aims to address this challenge by exploring the potential of Large Language Models (LLMs), to automate this decision-making process. Our goal is to harness the capabilities of Large Language Models (LLMs), such as GPT, to optimize the workflow, allowing radiologists to dedicate more time to their primary diagnostic responsibilities.