Dependency Parsing for Extracting Family History

Family history is an important part of the clinical record. Automatically extracting family history from clinical reports requires an understanding of how clinicians describe family history as well as an understanding of how they discuss diseases. We perform a characteristic analysis of family history sentences and compare them with sentences which contain a family member term but no family history. We observe the frequency of family history in clinical reports, the reliability of using family member mentions to indicate family history, as well as the frequency that family history is labeled. We develop a top down processing syntactic approach to extracting family history, perform an analysis on the distribution of syntactic context in family history, and compare the use of a phrase structure parser versus a dependency parser for extraction.