Support for text searching methods in improving injury surveillance

A study undertaken recently in Australia compared methods for interrogating text fields for identifying work-related injuries.
 
The findings of this study provide strong support for continued development of text searching methods to obtain information from routine emergency department data, to improve the capacity for comprehensive injury surveillance. It has been highlighted that the effectiveness of text searching depends both on the technical capabilities of the software and on the extent to which the text has the required information to address the problem under investigation.
 
The purpose of this study was to compare methods for interrogating text fields for identifying potential work-related injuries presenting at Emergency departments (EDs) in Queensland to inform future surveillance of work-related injury using narrative text.
 
The specific aims were to:
 
1. Describe and compare different text interrogation methods for identifying potential work-related injury cases.
 
2. Examine sensitivity, specificity, and positive predictive value of each text interrogation method against the coded injury surveillance Activity code meaning injured while ‘Working for an income’.
 
Three approaches were used to interrogate an injury description text field to classify cases as work-related: keyword search, index search, and content analytic text mining. Sensitivity and specificity were examined by comparing cases flagged by each approach to cases coded with an Activity code during triage. Methods to improve the sensitivity and/or specificity of each approach were explored by adjusting the classification techniques within each broad approach.
 
The basic keyword search detected 58% of cases (Specificity 0.99), an index search detected 62% of cases (Specificity 0.87), and the content analytic text mining (using adjusted probabilities) approach detected 77% of cases (Specificity 0.95).
 
Work-related injuries in Australia are estimated to cost around $57.5 billion annually, however there are currently insufficient surveillance data available to support an evidence-based public health response. Emergency departments (ED) in Australia are a potential source of information on work-related injuries though most ED’s do not have an ‘Activity Code’ to identify work-related cases with information about the presenting problem recorded in a short free text field.