Semantic interoperability requires consistent use of controlled terminologies. However, non-terminology experts (although perhaps experts in a particular domain) are prone to produce variant coding. We examine this problem by investigating SNOMED CT coding variation for other findings reported on case report forms from a clinical research study on urea cycle disorders. The natural language findings from the forms were normalized, and the associated SNOMED CT concept descriptions were compared. The subset of normalized strings associated with two different concept descriptions were further compared to determine the relationship among the associated SNOMED CT concepts. We found 45% of the concept description pairs were associated with two hierarchically related concepts or with the same concept, while 55% were associated with two unrelated concepts. Clearer guidelines for use of SNOMED CT in particular contexts, or structured data entry tools tailored to the needs of non-expert coders, are needed to better manage coding variation.