Bernstein Joseph

Effective real-time surveillance of infectious diseases must strike a balance between reliability and timeliness for early detection. Traditional syndromic surveillance utilizes limited sections of the EMR, such as chief complaints and/or diagnosis. However, other sections of the EMR may contain more pertinent information than what is captured in a brief chief complaint. These other EMR sections may provide relevant information earlier in the patient encounter than at the diagnosis or disposition stage, which can appear in the EMR up to 24 hours after the patient’s discharge. Comprehensive analysis may identify the most relevant section of EMRs for surveillance of all major infectious diseases, including ILI.

Objective

To investigate which section(s) of a patient’s electronic medical record (EMR) contains the most relevant information for timely detection of influenza-like illness (ILI) in the emergency department (ED).

In recent years, the threat of pandemic influenza has drawn extensive attention to the development and implementation of syndromic surveillance systems for early detection of ILI. Emergency department (ED) data are key components for syndromic surveillance systems. However, the lack of standardization for the content in chief complaint (CC) free-text fields may make it challenging to use these elements in syndromic surveillance systems. Furthermore, little is known regarding how ED data sources should be structured or combined to increase sensitivity without elevating false positives. In this study, we constructed two different models of ED data sources and evaluated the resulting ILI rates obtained in two different institutions.

Objective

To compare the influenza-like illness (ILI) rates in the emergency departments (ED) of a community hospital versus a large academic medical center (AMC).

Processing free-text clinical information in an electronic medical record (EMR) may enhance surveillance systems for early identification of ILI outbreaks. However, processing clinical text using NLP poses a challenge in preserving the semantics of the original information recorded. In this study, we discuss several NLP and technical issues as well as potential solutions for implementation in syndromic surveillance systems.

Objective

To review the natural language processing (NLP) and technical challenges encountered in an automated influenza-like illness (ILI) surveillance system.