Formalizing UMLS Relations using Semantic Partitions in the context of task-based Clinical Guidelines Model

Objectives To formalize the relations between the different Semantic Types in the Semantic Network of the Unified Medical Language System (UMLS) in the context of computer interpretable task-based clinical guidelines model. Design We used the Semantic Type Collections as our basis in the formalization. We defined some operators based on the relations which we considered were applicable to all the Semantic Types in the Collection. Measurement We separated the relations dealing with the Semantic Types Diagnostic Procedure, Laboratory Procedure and Therapeutic or Preventive Procedure. We calculated the ratio of the total relations in UMLS Semantic Network to the adjacent relations of these Semantic Types and also the percentage of Semantic Types who have an adjacent relations with these Semantic Types. Result Without the consideration of Semantic Type Collection, the total adjacent relations for these three Semantic Types was 6.87% of the total and these covered almost half of the total Semantic Types on an average. With the consideration of Semantic Type Collection, we were able to represent these relations and also cover the whole UMLS Semantic Network. Conclusion With the formalization of the mapping operators for the adjacent Semantic Types with respect to the three Semantic Types, the next step would be to map the non-adjacent ones to those three Semantic Types following a path with least distance. Index Terms Clinical Practice Guidelines, UMLS, Semantic Types, Semantic Network, Graph Theory, Minimal Spanning Network