While recent advances in large language models (LLMs) offer great promise in healthcare, the safety-critical nature of the domain requires a thoughtful strategy to mitigate risks of hallucinations and potential harms. We propose a graph of domain knowledge and empirically validated its effectiveness in graph-augmented LLM generation. This presents a promising approach to safe, factual, and in turn more precise LLM applications. We first introduce the world’s first clinical terminology for the Chinese healthcare community, namely MedCT, accompanied by a clinical foundation model MedBERT and an entity linking model MedLink. The MedCT system enables standardized representation of clinical data, successively stimulating the development of new medicines, treatment pathways, and better patient outcomes. Moreover, the MedCT knowledge graph provides a principled mechanism to minimize the hallucination problem of LLMs, therefore achieving significant levels of accuracy and safety in LLM-based clinical applications. Our experiments show that the MedCT system achieves state-of-the-art (SOTA) performance in semantic matching and entity linking tasks, not only for Chinese but also for English. We also conducted a longitudinal field experiment by applying MedCT and LLMs in a representative spectrum of clinical tasks, including electronic health record (EHR) auto-generation and medical document search. Our study shows a multitude of values of MedCT for clinical workflows and patient outcomes, especially in the new genre of clinical LLM applications. We present our approach in sufficient engineering detail, such that implementing a clinical terminology for other non-English societies should be readily reproducible. To encourage further research on LLM-based healthcare digitalization and promote the wellbeing of humankind, we are releasing our terminology, models, algorithms, and real-world clinical datasets for development.