An algorithm developed by Kaiser Permanente researchers could identify more patients at risk of getting HIV. Pictured, KP member Vincent Sparacio rides in the AIDS/LifeCycle, a 545 mile bike ride from San Francisco to Los Angeles that raises money for HIV/AIDS causes.
Thirty years after the HIV/AIDS crisis began, medicine now has a highly effective way to keep people from getting the virus: a daily preventive pill (known as preexposure prophylaxis, or PrEP), which thousands of Kaiser Permanente Northern California members currently use.
Kaiser Permanente researchers, working with colleagues in Boston, have found a way to identify more people at risk for HIV who could benefit from preventive therapy. They published a study in July describing an analytical tool that performed better than existing prediction methods by looking at dozens of risk factors in the electronic medical record.
The investigators developed a machine-learning algorithm to predict who would become infected with HIV during a 3-year period, and it flagged 2.2% of 3.7 million Kaiser Permanente patients. The method identified nearly half of the men who acquired HIV, many more than existing prediction tools.
“We have analyzed 81 variables in the electronic health record, finding 44 of them most relevant for predicting HIV risk,” said senior author Jonathan Volk, MD, MPH, an infectious disease physician who treats patients with HIV at Kaiser Permanente San Francisco Medical Center. “We used our electronic medical record to develop a tool that could be implemented in a busy clinical practice to help providers identify patients who may benefit most from PrEP.”
Addressing the Gap
The Centers for Disease Control and Prevention estimates that just 7% of the people who could benefit from PrEP are taking it. Relying on the CDC’s indications for PrEP — sexual orientation and a history of sexually transmitted infections — underestimates risk for some populations, including African American men who have sex with men, who have relatively high HIV incidence and low PrEP use.
“Our predictive model directly addresses this gap and may be substantially more effective than current efforts to identify individuals who may be good PrEP candidates,” Dr. Volk said. He emphasized that it does not replace the clinical judgment of medical providers but could save them time and address misconceptions about HIV risk.
The accuracy of the tool is possible because of Kaiser Permanente Northern California’s comprehensive electronic health records, which track many demographic and clinical data points for its members. “Development of the tool required a setting like Kaiser Permanente Northern California that had high-quality, individual-level data on enough people to identify new HIV infections, which are rare events,” explained co-author Michael Silverberg, PhD, MPH, from the Kaiser Permanente Division of Research.
A Connection to Life-Saving Care
As a physician who treats people with HIV, Dr. Volk wants to see more use of preventive therapy. “In PrEP, we have an incredibly powerful tool to stop HIV transmission,” he said.
Kaiser Permanente member Vincent Sparacio, 26, an engineer in San Francisco, has been taking PrEP since 2014. Sparacio said he’s really benefited from Kaiser Permanente’s model of PrEP care because of the careful follow-up and how quickly he can get seen for an appointment or laboratory testing.
“The communities most impacted by HIV, including queer folks of color, have historical reasons to distrust the medical establishment,” he said. “This tool could be an important way to rebuild that trust and help get them connected to life-saving care.”