Skip to content Skip to navigation

Algorithms can identify undiagnosed hypertension

August 4, 2014
by Richard R. Rogoski
| Reprints

Researchers at Northwestern Medicine have found that using algorithms to search electronic health records can identify patients with undiagnosed hypertension.

Results of the study, "A Technology-Based Quality Innovation to Identify Undiagnosed Hypertension Among Active Primary Care Patients," were published in the July/August issue of Annals of Family Medicine.

According to a press release, the study reviewed the EHRs of 1,033 patients using three EHR algorithms. Of those patients, 361 had been diagnosed with hypertension while 290 were diagnosed with related blood pressure conditions such as prehypertension.

Using the same three EHR algorithms, the study also identified additional at-risk patients, who were then observed over a period of two years. They remained on their physician's at-risk list until an automated office blood pressure (AOBP) test yielded a complete evaluation or a firm diagnosis was entered into their chart.

"With this study, we created a surveillance system that notifies the medical staff and the primary care physician anytime a patient who is at risk arrives in the office," said principal investigator Michael K. Rakotz, MD, a family medicine physician at Northwestern Medicine Evanston. "Once these patients are identified we proceed with an AOBP to more accurately measure their blood pressure and make a diagnosis. This surveillance system never stops running, so any patient that meets the EHR algorithm criteria for possible hypertension will automatically be flagged. In doing so we hope to put an end to undiagnosed hypertension."