Revolutionizing patient safety with artificial intelligence: The potential of natural language processing and large language models

Abstract

Patient safety is a critical aspect of modern health care. Adverse events, half of them preventable, related to unsafe care are among the top ten causes of death and disability worldwide [1, 2]. Insecure care results in significant incremental expenses when, e.g. hospital-acquired infections, account for high rates of morbidity and mortality, as well as considerable costs [3]. Despite efforts to improve safety in the health-care system, issues still persist, and progress has been unsatisfactory over the last 30 years [4]. Artificial intelligence (AI) has the potential to address challenges in health care by providing solutions to predict and prevent harm [1]. In this editorial, we will discuss the potential of advanced AI, specifically natural language processing (NLP) and large language models (LLMs), to improve patient safety while also acknowledging the risks and challenges associated with their implementation...