UC-created algorithm can help treat chronic health condition

A new study found that an algorithm created by UC San Francisco researchers helped improve the health of thousands of Californians and prevented dozens of deaths.

The study, published Wednesday in the BMJ Open Quality journal, looked at whether the tool, called the UC Way Hypertension Medication Algorithm, helped patients keep their blood pressure in check.

Researchers from multiple UC institutions, including UC San Francisco and UC Berkeley, reported a statistically significant increase in the number of patients who were able to control their blood pressure after the algorithm was implemented in 2023 across the six UC academic health centers, translating to improved health for nearly 5,000 patients.

High blood pressure, or hypertension, affects about 48% of all U.S. adults. Although there are treatments for high blood pressure, about 50% to 80% of people with hypertension do not have their condition under control. The U.S. Centers for Disease Control and Prevention estimated that over 664,000 people died in 2023 due to conditions primarily related to hypertension.

“The challenge isn’t the science — we know how to control blood pressure,” Dr. Sandeep P. Kishore, the study’s lead author and an associate professor of medicine at UCSF, said in a statement. “This is all about having a system-wide focus that actually moves the needle.” 

In an effort to help these patients, a team of UC physicians, nurses, pharmacists and data scientists created the tool with the goal of standardizing blood pressure treatment across the six UC centers. The algorithm, which has a “stepwise approach,” is embedded into the electronic medical records and focuses on affordable medication options, as well as reducing variation among different groups.

During the 2023-2025 study period after the algorithm was implemented, more than 90,000 hypertensive patients were treated in the UC system. The researchers found that the percentage of people able to control their blood pressure reached 73.9% up from 68.5%, translating to about 4,860 people with improved health.

Kishore estimated that the findings translate to “72 strokes, 48 heart attacks and 38 deaths averted.” 

In an emailed statement Kishore said the goal was to make “best practice the every day practice.”

“Even in a complex, decentralized system, you can standardize care at scale — if you keep the approach simple, affordable, and flexible, and pair it with strong clinician engagement and workflow integration,” he said. 

While a relatively small improvement, the medical community has struggled to find ways to help people manage their hypertension. 

“I think there’s a lot of need to better control blood pressure in hypertensive individuals,” said Dr. Matthew Alexander, a cardiologist at the Vanderbilt University Medical Center. He explained that patients may have difficulty getting enough care to properly titrate their medications, may have side effects from medications and may not adhere to strict medication regimens. 

Alexander, who was not affiliated with the study, called the algorithm an “interesting approach” to treating hypertensive patients but said it’s an “open question” if it would work in other institutions.

“The sort of number of resources and different types of providers that were necessary for this more frequent checking up … that’s not clear in terms of its ability to translate to other systems,” he said.