Free-text Mining

In 2010, as rules for the Centers for Medicaid and Medicare Electronic Heatlh Record (EHR) Incentive Programs (Meaningful Use)(1), were finalized, ISDS became aware of a trend towards new EHR systems capturing or sending emergency department (ED) chief complaint (CC) data as structured variables without including the free-text. This perceived shift in technology was occurring in the absence of consensus-based technical requirements for syndromic surveillance and survey data on the value of free-text CC to public health practice. On 1/31/11, ISDS, in collaboration with CDC BioSense, recommended a core set of data for public health syndromic surveillance (PHSS) to support public health's participation in Meaningful Use.

Objective

This study was conducted to better support a requirement for ED CC as free-text, by investigating the relationship between the unstructured, free-text form of CC data and its usefulness in public health practice. To better inform health IT standardization practices, specifically related to Meaningful Use, by describing how US public health agencies use unstructured, free-text EHR data to monitor, assess, investigate and manage issues of public health interest.

Automated syndromic surveillance systems often classify patients into syndromic categories based on free-text chief complaints. Chief complaints (CC) demonstrate low to moderate sensitivity in identifying syndromic cases. Emergency Department (ED) reports promise more detailed clinical information that may increase sensitivity of detection. Objective: Compare classification of patients based on chief complaints against classification from clinical data described in ED reports for identifying patients with an acute lower respiratory syndrome.

Standard syndrome definitions for ED visits in ESSENCE rely on chief complaints. Visits with more words in the chief complaint field are more likely to match syndrome definitions. While using ESSENCE, we observed geographic differences in chief complaint length, apparently related to differences in electronic health record (EHR) systems, which resulted in disparate syndrome matching across Idaho regions. We hypothesized that chief complaint and diagnosis code co-occurrence among ED visits to facilities with long chief complaints could help identify terms that would improve syndrome match among facilities with short chief complaints.

Objective:

We sought to use free text mining tools to improve emergency department (ED) chief complaint and discharge diagnosis data syndrome definition matching across facilities with differing robustness of data in the Electronic Surveillance System for the Early Notification of Community-based Epidemics (ESSENCE) application in Idaho’s syndromic surveillance system.