Editorial Commentary: Biomedical Research Investigating Artificial Intelligence Large Language Models Needs to Move Beyond Measuring Accuracy and Focus on Improving Patient Care

Abstract

Orthopaedic surgeons are fascinated with artificial intelligence (AI). Since the release of ChatGPT to the general public on November 30, 2022, there have been a flurry of articles regarding use of large language models (LLMs) in our field. Most of these revolve around the accuracy of the models regarding orthopaedic topics (spoiler alert: the accuracy is good, yet unreliable, but improving). Unfortunately, the research around LLM is largely repetitive, applying the LLMs to the same essential tasks. LLM AI systems show amazing capabilities in data processing, collating and organizing and recognizing patterns. Now, research scientists need to innovate. Journals must encourage authors to investigate how AI systems can improve patient care.