Development of a Chinese Synonym Library: Enhancing Clinical Terminology Standardization and Interoperability

Doctors often use varied expressions to describe the same diseases, leading to challenges in medical data analysis and information sharing. Developing a systematic synonym library for diseases can standardize terminology, reduce confusion, and improve data consistency. Some manually created terminologies cover portions of synonyms. However, relying solely on human efforts to expand and enrich clinical synonym data is a time-consuming, labor-intensive, and ongoing effort. The lack of comprehensive clinical synonym data is a global challenge. In this paper, we develop a hybrid approach that includes rule sets, text similarity calculation, data redirection, and manual review. A Chinese synonym library containing 21,264 pairs of synonyms is constructed by semi-automatically extracting synonyms from terminology standards and web resources. Our synonym library surpasses current research in both size and methodological robustness.