Extracting family history diagnoses from clinical texts

Abstract

Family history information is an important part of understanding a patient's total health, and it is spread in text throughout the clinical record; mostly untagged and often very unstructured. We have performed a syntactic analysis of family history in 1274 sample clinical texts and created an algorithm to extract specific family history information. Using the Stanford NLP Parser, we created patterns of dependency relations to map specific family members to specific diseases. Preliminary results are promising with a precision and recall of .82 and .52, respectively. We find that this is of sufficient accuracy to drive meaningful, actionable clinical presentation of this information.