Natural language processing system defines medical jargon in EHRs

A natural language processing system that defines medical jargon for patients viewing electronic health record (EHR) notes through portals could improve care outcomes, according to a study published in Journal of Medical Internet Research.

Patients engaged in their own care often take advantage of information in their EHRs, but accessing these notes may confuse patients due to the medical terminology and references. In this study, researchers evaluated the feasibility and quality of NoteAid, an online natural language processing system that helps define EHR terms.

The language processing system contains a lexical resource for the definition of medical terms and a computation unit that links them to definitions. In this study, researchers additionally developed computational methods to prioritized medical terms important to understanding EHRs. User interface and content quality were evaluated by 10 physician domain experts through walkthrough sessions and a post-study questionnaire.

Results showed positive feedback on NoteAid on ease of use, visual display, system speed and adequate definitions. However, improvements to the system were also noted for the display of definitions, the need for more medical terms, handling of terms with varying definitions and standardizing the scope of definitions for medications.

“Physician evaluation yielded useful feedback for content validation and refinement of this innovative tool that has the potential to improve patient EHR comprehension and experience using patient portals,” concluded first author Jinying Chen, PhD, and colleagues. “Future ongoing work will develop algorithms to handle ambiguous medical terms and test and evaluate NoteAid with patients.”