Large language models for clinical decision support in gastroenterology and hepatology

Clinical decision making in gastroenterology and hepatology has become increasingly complex and challenging for physicians. This growing complexity can be addressed by computational tools that support clinical decisions. Although numerous clinical decision support systems (CDSS) have emerged, they have faced difficulties with real-world performance and generalizability, resulting in limited clinical adoption. Generative artificial intelligence (AI), particularly large language models (LLMs), are introducing new possibilities for CDSS by offering more flexible and adaptable support that better reflects complex clinical scenarios. LLMs can process unstructured text, including patient data and medical guidelines, and integrate various information sources with high accuracy, especially when augmented with retrieval-augmented generation. Thus, LLMs can provide dynamic, context-specific support by generating personalized treatment recommendations, identifying potential complications based on patient history, and enabling natural language interactions with health-care providers. However, important challenges persist, particularly regarding biases, hallucinations, interoperability barriers, and proper training of health-care providers. We examine the parallel evolution of the complexity in clinical management in gastroenterology and hepatology, and the technical developments leading to current generative AI models. We discuss how these advances are converging to create effective CDSS, providing a conceptual basis for further development and clinical adoption of these systems.