Translating and evaluating historic phenotyping algorithms using SNOMED CT

• Published in: Journal of the American Medical Informatics Association : JAMIA Vol. 30; no. 2; pp. 222 - 232
• Main Authors: Elkheder, Musaab, Gonzalez-Izquierdo, Arturo, Qummer Ul Arfeen, Muhammad, Kuan, Valerie, Lumbers, R Thomas, Denaxas, Spiros, Shah, Anoop D
• Format: Journal Article
• Language: English
• Published: England 18-01-2023
• Subjects: Algorithms; Asthma; Databases, Factual; Electronic Health Records; Humans; Systematized Nomenclature of Medicine; phenotype; SNOMED CT; electronic health records; terminology; ontology
• ISSN: 1067-5027; 1527-974X
• DOI: 10.1093/jamia/ocac158

Patient phenotype definitions based on terminologies are required for the computational use of electronic health records. Within UK primary care research databases, such definitions have typically been represented as flat lists of Read terms, but Systematized Nomenclature of Medicine-Clinical Terms (SNOMED CT) (a widely employed international reference terminology) enables the use of relationships between concepts, which could facilitate the phenotyping process. We implemented SNOMED CT-based phenotyping approaches and investigated their performance in the CPRD Aurum primary care database.
We developed SNOMED CT phenotype definitions for 3 exemplar diseases: diabetes mellitus, asthma, and heart failure, using 3 methods: "primary" (primary concept and its descendants), "extended" (primary concept, descendants, and additional relations), and "value set" (based on text searches of term descriptions). We also derived SNOMED CT codelists in a semiautomated manner for 276 disease phenotypes used in a study of health across the lifecourse. Cohorts selected using each codelist were compared to "gold standard" manually curated Read codelists in a sample of 500 000 patients from CPRD Aurum.
SNOMED CT codelists selected a similar set of patients to Read, with F1 scores exceeding 0.93, and age and sex distributions were similar. The "value set" and "extended" codelists had slightly greater recall but lower precision than "primary" codelists. We were able to represent 257 of the 276 phenotypes by a single concept hierarchy, and for 135 phenotypes, the F1 score was greater than 0.9.
SNOMED CT provides an efficient way to define disease phenotypes, resulting in similar patient populations to manually curated codelists.