Encoding and Processing Patient Allergy Information in EHRs (Massachusetts)

Project Details - Ended

Project Categories


Allergies are linked to an important group of chronic and serious illnesses such as asthma, sinusitis, hay fever, and atopic eczema. For some people, allergic reactions can be severe and even fatal. As such, obtaining allergy information is critical to safe prescribing, preventing adverse drug events, and reducing the cost of care. Clinical decision support (CDS) systems have been shown to reduce medication errors attributed to known allergies by an estimated 56 percent. For CDS to be effective, correct electronic documentation and exchange of a patient’s allergy information is required, but it is challenging due to a lack of well-adopted standard terminologies for representing allergies, frequent free-text entry of allergy information, and the lack of an allergy reconciliation process.

This project will develop and evaluate a natural language processing (NLP) system for allergy information and then assess its ability to improve patients’ allergy lists. While the clinical application of NLP to extract and encode free-text has been an active area of research for more than two decades, using it with allergies is a new application domain.

The specific aims of this project are as follows:

  • Build a comprehensive knowledge base for allergy information
  • Develop and evaluate an NLP system for processing allergy information 
  • Use NLP output to facilitate allergy reconciliation 
  • Disseminate the methods used and the resulting tool

The knowledge base will be created by obtaining a clear understanding of how an allergy is defined and represented within a standard terminology; examining the capability of a terminology to encode an allergy; and looking at how to combine multiple terminologies if needed. In order to understand how clinicians currently document allergies, the researchers will examine a large allergy repository. From this research, an information model representing allergy information will be built.

From there, a new NLP Module, Allergy Information Extraction and Encoding (AIEE), will be developed and integrated into an existing NLP system, Medical Text Extraction, Reasoning and Mapping System (MTERMS). MTERMS was developed by the researchers under a previously AHRQ-funded project titled Improving Outpatient Medication Lists Using Temporal Reasoning and Clinical Texts.

The resulting tool will be evaluated against a large sample of free-text clinical documents from two academic medical centers, including discharge summaries, outpatient visit notes, and emergency room notes. The researchers will look at how the tool is able to improve the “correctness” and “completeness” of allergy lists extracted from electronic clinical texts, and if so, whether it will help improve medication management and CDS.

This project does not have any related annual summary.
This project does not have any related resource.
This project does not have any related survey.
This project does not have any related project spotlight.
This project does not have any related survey.
This project does not have any related story.
This project does not have any related emerging lesson.