Agile text mining for the 2014 i2b2/UTHealth Cardiac risk factors challenge

Abstract

This paper describes the use of an agile text mining platform (Linguamatics' Interactive Information Extraction Platform, I2E) to extract document-level cardiac risk factors in patient records as defined in the i2b2/UTHealth 2014 challenge. The approach uses a data-driven rule-based methodology with the addition of a simple supervised classifier. We demonstrate that agile text mining allows for rapid optimization of extraction strategies, while post-processing can leverage annotation guidelines, corpus statistics and logic inferred from the gold standard data. We also show how data imbalance in a training set affects performance. Evaluation of this approach on the test data gave an F-Score of 91.7%, one percent behind the top performing system.

Keywords: Clinical natural language processing; Information extraction; Text mining.

Figure 1

Distribution of annotations per risk factor

Figure 2

System outline

Figure 3

Concrete example of the query refinement strategy

Figure 4

Smoking Categorization evidence

Figure 5

Plain text table

Figure 6

Extracting temporal information for Medications

Figure 7

Extracting temporal information for A1C

Figure 8

F-scores of individual categories