This survey explores the integration of clinical knowledge into large language models, creating more effective medical AI systems for real-world healthcare applications.

• Examines how clinical expertise on disease causes, diagnosis, treatment and prognosis enhances LLM performance
• Highlights breakthrough medical AI systems like DoctorGPT and Pangu-Drug
• Reviews methods for merging specialized medical knowledge with general-purpose LLMs
• Discusses practical applications in diagnosis, treatment planning, and patient education

This research is crucial for advancing medical AI that can effectively support healthcare professionals, improve diagnostic accuracy, and ultimately enhance patient outcomes through knowledge-informed language models.

Merging Clinical Knowledge into Large Language Models for Medical Research and Applications: A Survey