EHR algorithm identifies hypertensive patients

Researchers developed an algorithm that when applied to EHR data was highly successful at classifying patients with hypertension. They reported their study results in the Journal of the American Medical Informatics Association.

Researchers evaluated four phenotyping algorithms, which are algorithms that use EHR data to classify patients with specific diseases and outcomes. They used varying degrees of ICD-9 data, medications, vital signs, narrative-text search results and Unified Medical Language system concepts as data inputs to review records of 631 patients.

The algorithms were able to correctly identify patients with hypertension, even algorithms using just billing codes or blood pressure readings, according to the study. "However, even simple combinations of input categories improve performance," the authors note. "The most complex algorithms classified hypertension with excellent recall and precision."

More articles on EHRs:

The connected hospital: Wireless technology shapes the future of healthcare 
From novelty to care tool: The evolving usability of EHRs 
Small, rural hospitals lag in interoperability: 7 findings from the ONC 

© 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