Large language models and rheumatology: are we there yet?

Abstract

The last 2 years have marked the beginning of a golden age for natural language processing in medicine. The arrival of large language models (LLMs) and multimodal models have raised new opportunities and challenges for research and clinical practice. In rheumatology, a specialty rich in data and requiring complex decision-making, the use of these tools may transform diagnostic procedures, improve patient interaction and simplify data management, leading to more personalized and efficient healthcare outcomes. The objective of this article is to present an overview of the status of LLMs in the field of rheumatology while discussing some of the challenges ahead in this area of great potential. What does this research mean for patients?Large language models (LLMs) present both new opportunities and challenges for research and clinical practice in rheumatology. Although these models hold considerable potential, it is essential for rheumatologists to become familiar with their fundamental principles and recognize their limitations before incorporating them into clinical decision-making. Understanding how LLMs are capable of generating fresh answers and how they are trained is vital for maximizing the benefits while mitigating the risks associated with their use in research and patient care. Therefore, this study aims to introduce the basic principles of LLMs for rheumatologists in order to understand their probabilistic nature and mistakes, discuss some potential applications of natural language processing (NLP), explore the utility of training specific rheumatology-related LLMs, and examine the ethical dilemmas associated with their use. Based on the fast and continuous evolution of the NLP field, it is likely that recommendations guidelines or points to consider on the ethical use of LLMs in rheumatology will be essential to evaluate their impact on clinical practice.