MedEx: a medication information extraction system for clinical narratives

Abstract

Medication information is one of the most important types of clinical data in electronic medical records. It is critical for healthcare safety and quality, as well as for clinical research that uses electronic medical record data. However, medication data are often recorded in clinical notes as free-text. As such, they are not accessible to other computerized applications that rely on coded data. We describe a new natural language processing system (MedEx), which extracts medication information from clinical notes. MedEx was initially developed using discharge summaries. An evaluation using a data set of 50 discharge summaries showed it performed well on identifying not only drug names (F-measure 93.2%), but also signature information, such as strength, route, and frequency, with F-measures of 94.5%, 93.9%, and 96.0% respectively. We then applied MedEx unchanged to outpatient clinic visit notes. It performed similarly with F-measures over 90% on a set of 25 clinic visit notes.

Figure 1

An overview of the MedEx system.

Figure 2

A simplified model to represent medication findings and signature modifiers in the notation of conceptual graphs. A concept is enclosed in square brackets and followed by the relations associated with it. Each relation appears in parentheses and its values are specified by another concept that follows the relations after an arrow (‘→’). The number of values that a relation is permitted to have (its cardinality) is defined by following constraint:{*} means that the relation must have 0 or more values;{*}@>0 means that the relation must have 1 or more values; and:{*}@<2 means that the relation must have 0 or 1 values; the default cardinality is exactly 1.

Figure 3

An example of the sequential semantic tagger.

Figure 4

Partial representation of the semantic grammar.