Beyond Human Limits: The Promise and Pitfalls of Large Language Models in Radiology Research.

Abstract

This review examines the applications and challenges of large language models (LLMs), like OpenAI's ChatGPT, in radiology research. ChatGPT can assist radiology researchers in generating new ideas, finding and summarizing research papers, designing studies, analyzing data, and facilitating manuscript writing. LLMs are powerful tools with numerous applications in radiology research. However, users should be mindful of potential pitfalls, such as producing incorrect or biased outputs and inconsistent responses, along with ethical and privacy concerns. We discuss approaches to optimize models and address these issues, including prompting techniques like chain-of-thought prompting, retrieval-augmented generation, and fine-tuning. For researchers, prompt engineering can be particularly effective. This review seeks to demonstrate how researchers can utilize ChatGPT for radiology research while offering strategies to mitigate associated risks. We aim to help researchers harness these potent tools to safely boost their productivity.