Knowledge requirements for automated inference of medical textbook markup

Indexing medical text in journals or textbooks requires a tremendous amount of resources. We tested two algorithms for automatically indexing nouns, noun-modifiers, and noun phrases, and inferring selected binary relations between UMLS concepts in a textbook of infectious disease. Sixty-six percent of nouns and noun-modifiers and 81% of noun phrases were correctly matched to UMLS concepts. Semantic relations were identified with 100% specificity and 94% sensitivity. For some medical sub-domains, these algorithms could permit expeditious generation of more complex indexing.