JMIR Publications

ABSTRACT

As healthcare continues to evolve with technological advancements, the integration of artificial intelligence (AI) into clinical practices has shown promising potential to enhance patient care and operational efficiency. Among the forefront of these innovations are large language models (LLMs), a subset of AI designed to understand, generate, and interact with human language at an unprecedented scale. This review describes the role of LLMs in improving diagnostic accuracy, automating documentation, and advancing specialist education and patient engagement within the field of gastroenterology and gastrointestinal endoscopy. The most important benefit would be the possibility of clinical reasoning from LLMs. Emotional support is the unexpected another benefit of LLMs. Language vision models (LVMs) or foundation model with multimodal function is expected to be the next generation mainstream of AI in medical practice. Systematic review revealed that potential for disseminating general medical knowledge, providing consultation recommendations, automatic generation of procedure reports, or causal inference of presumptive diagnosis of complex medical disorders. Despite promising benefits, such as increased efficiency and improved patient outcomes, challenges related to data privacy, accuracy, and interdisciplinary collaboration remain. We highlight the importance of navigating these challenges to fully leverage LLMs in transforming gastrointestinal endoscopy practices.