Evaluation of the content coverage of SNOMED CT: ability of SNOMED clinical terms to represent clinical problem lists

Abstract

Objective: To evaluate the ability of SNOMED CT (Systematized Nomenclature of Medicine Clinical Terms) version 1.0 to represent the most common problems seen at the Mayo Clinic in Rochester, Minn.

Material and methods: We selected the 4996 most common nonduplicated text strings from the Mayo Master Sheet Index that describe patient problems associated with inpatient and outpatient episodes of care. From July 2003 through January 2004, 2 physician reviewers compared the Master Sheet Index text with the SNOMED CT terms that were automatically mapped by a vocabulary server or that they identified using a vocabulary browser and rated the "correctness" of the match. If the 2 reviewers disagreed, a third reviewer adjudicated. We evaluated the specificity, sensitivity, and positive predictive value of SNOMED CT.

Results: Of the 4996 problems in the test set, SNOMED CT correctly identified 4568 terms (true-positive results); 36 terms were true negatives, 9 terms were false positives, and 383 terms were false negatives. SNOMED CT had a sensitivity of 92.3%, a specificity of 80.0%, and a positive predictive value of 99.8%.

Conclusion: SNOMED CT, when used as a compositional terminology, can exactly represent most (92.3%) of the terms used commonly in medical problem lists. Improvements to synonymy and adding missing modifiers would lead to greater coverage of common problem statements. Health care organizations should be encouraged and provided incentives to begin adopting SNOMED CT to drive their decision-support applications.