Construction of the cervical cancer common terminology for promoting semantic interoperability and utilization of Chinese clinical data

• DOI: 10.1186/s12911-021-01672-x
• Publication Date: 2021-11-17T11:03:18Z
• Authors: Na Hong; Fengxiang Chang; Zhengjie Ou; Yishang Wang; Yating Yang; Qiang Guo; Jianhui Ma; Dan Zhao
• Keywords: China; Research; Computer applications to medicine. Medical informatics; R858-859.7; Uterine Cervical Neoplasms; Interoperability; Common terminology; Semantics; 3. Good health; 03 medical and health sciences; 0302 clinical medicine; Cervical cancer; Electronic health records; Humans; Female; Clinical terms; Language; Natural Language Processing

Abstract Background We aimed to build a common terminology in the domain of cervical cancer, named Cervical Cancer Common Terminology (CCCT), that will facilitate clinical data exchange, ensure quality and support large scale analysis. Methods The standard concepts relations CCCT were collected from ICD-10-CM Chinese Version, ICD-9-PC officially issued commonly used terms, guidelines for diagnosis treatment cancer medical book Lin Qiaozhi Gynecologic Oncology. 2062 electronic records (EMRs) 16 hospitals, belong different regions hospital tiers, enrichment building terms relations. Concepts hierarchies, relationships built using Protégé. performance natural language processing results was evaluated by average precision, recall, F1-score. usability coverage. Results A total 880 concepts, 1182 6 attributes defined CCCT, which organized levels 11 classes. Initial evaluation demonstrated F1-score percentages 96%, 72.6%, 88.5%. coverage three classes manifestation, treatment, pathology, 87.22%, 92.63%, 89.85%, respectively. Flexible expressions exist between regions, traditions, cultures, habits within country, linguistic variations settings diverse translation introduced western are main reasons uncovered terms. Conclusions Our study initial construction. This is an ongoing work, with update knowledge, more be added in, EMRs analyzed, term continuing improved. In future, effectively analysis scale.