A new natural language processing system can define EHR 'jargon': 5 things to know

A team of researchers evaluated the usability of NoteAid, an online natural language processing system that links medical terms found in EHRs to "lay definitions," according study results published in the Journal of Medical Internet Research.

The mission behind NoteAid — a system developed by researchers at the University of Massachusetts Medical School in Worcester — is to improve patient comprehension by providing definitions for clinical terms that can be "easily understood by lay people."

"Many health care systems now allow patients to access their EHR notes online through patient portals," the study authors note. "Medical jargon in EHR notes can confuse patients, which may interfere with potential benefits of patient access to EHR notes."

Here are five things to know about the evaluation.

1. Jinying Chen, PhD, a quantitative health sciences researcher at UMass Medical School, led the nine-person research team to conduct the study. The researchers hailed from various institutions, including UnitedHealthcare subsidiary Optum and Stanford (Calif.) University School of Medicine.

2. For the study, researchers asked 10 physician experts to evaluate the user interface and content quality of NoteAid. The physicians completed a cognitive walkthrough session and a post-session questionnaire.

3. Physicians provided mixed feedback on NoteAid. Some physicians said the system was easy to use, had a good visual display, operated at a satisfactory speed and housed adequate lay definitions.

4. However, some physicians suggested the NoteAid team improve definitions for partially matched terms and terms whose definitions varied depending on context. They also recommended the team include more medical terms in the lexical resource.

5. In response to the study, the NoteAid team added 4,502 more definitions and improved the system's user interface. "Future ongoing work will develop algorithms to handle ambiguous medical terms and test and evaluate NoteAid with patients," the study authors noted.

More articles on EHRs & interoperability:
Astria Health selects Cerner CommunityWorks for EHR, RCM system
Researchers use EHR timestamps to map clinical workflow
Indiana hospital to implement Meditech Web EHR

© Copyright ASC COMMUNICATIONS 2019. Interested in LINKING to or REPRINTING this content? View our policies by clicking here.

 

Top 40 Articles from the Past 6 Months