New Tool May Identify People at Risk for HIV
A potential analytical tool may help providers identify those at risk for HIV in efforts to offer pre-exposure prophylaxis (PrEP). Using a machine-learning algorithm to predict who could become infected with HIV during a three-year period, researchers were able to flag 2.2% of 3.7 million patients as high or very high risk.1
Researchers at Kaiser Permanente San Francisco, the Kaiser Permanente Division of Research, Beth Israel Deaconess Medical Center, and Harvard Medical School analyzed a study population of HIV-negative adult members of Kaiser Permanente Northern California. The participants were not yet using PrEP and had at least two years of previous health plan enrollment with at least one outpatient visit from Jan. 1, 2007, to Dec. 31, 2017. The researchers discovered that 44 of 81 electronic health record (EHR) variables were most relevant for predicting HIV risk. A tool that used these 44 variables identified 2.2% of the population as having a high or very high risk of HIV infection within three years. The high-risk group included 38.6% of all new HIV infections; 32 of 69 men were diagnosed with HIV during the study period, but none of the 14 women were found to be infected during the same period.1
Researchers noted that the tool is limited in identifying women at risk of contracting HIV, since the risk for females may depend on risk factors of their partners, which are not captured by the variables included in the tool. The tool also does not perform as well among patients for whom the EHR contains fewer data due to initial enrollment in the system or less use of healthcare services, investigators stated.
“It is critical that we identify our patients at risk of HIV acquisition,” Jonathan Volk, MD, MPH, an infectious disease physician who treats patients with HIV at Kaiser Permanente San Francisco Medical Center, said in a statement. “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.” (View the statement online at: https://k-p.li/2ztfLaQ.)
Recent data indicate that the majority of new HIV diagnoses are attributed to male-to-male sexual contact.2 Injection drug use also is linked to HIV infection; the prevalence of HIV infection among those who inject drugs is estimated at 1.9%.3 According to 2017 statistics, males ages 13 years and older represented 81% of new diagnoses of HIV infection.4 While the majority of these new diagnoses were attributed to male-to-male sexual contact, about 10% were attributed to heterosexual contact, 4% to injection drug use, and 4% to both male-to-male sexual contact and injection drug use.4 In adolescent females ages 13 years and older, 87% of all new diagnoses were attributed to heterosexual contact and 12% to injection drug use.4
PrEP Push Is On
The U.S. Preventive Services Task Force (USPSTF) issued final recommendations that providers screen for HIV in everyone ages 15-65 years and all pregnant women, as well as younger adolescents and older adults at greater risk for HIV.5-7 PrEP also should be offered to people at high risk of HIV, USPSTF states.8,9
The new predictive tool directly addresses this gap and may be more effective than current efforts to identify those who may be good PrEP candidates, said Volk. While the tool does not replace the clinical judgment of medical providers, it could save them time and address misconceptions about HIV risk, he stated. While investigators were able to access a wide variety of patient information from Kaiser Permanente’s electronic records system, other healthcare organizations could build similar algorithms using fewer EHR variables. Study findings indicated that simpler models that included only six variables still helped identify patients at risk for HIV.
Such a tool could be incorporated in EHRs to alert providers to speak with patients most likely to benefit from discussions about PrEP, researchers said. Clinicians also could explain the availability of drug manufacturer and publicly funded programs that may cover all or part of PrEP copays.
“Embedding our algorithm in the electronic health record could support providers in discussing sexual health and HIV risk with their patients, ultimately increasing the uptake of PrEP and preventing new HIV infections,” lead author Julia Marcus, PhD, MPH, a former Kaiser Permanente Division of Research member who is now at Harvard Medical School and Harvard Pilgrim Health Care Institute, said in the statement.
REFERENCES
- Marcus JL, Hurley LB, Krakower DS, et al. Use of electronic health record data and machine learning to identify candidates for HIV pre-exposure prophylaxis: A modelling study. Lancet HIV 2019;doi:10.1016/S2352-3018(19)30137-7.
- Singh S, Song R, Johnson AS, et al. HIV incidence, prevalence, and undiagnosed infections in U.S. men who have sex with men. Ann Intern Med 2018;168:685-694.
- Dailey AF, Hoots BE, Hall HI, et al. Vital signs: Human immunodeficiency virus testing and diagnosis delays — United States. MMWR Morb Mortal Wkly Rep 2017;66:1300-1306.
- Centers for Disease Control and Prevention. HIV Surveillance Report 2017;29:20.
- US Preventive Services Task Force, Owens DK, Davidson KW, Krist AH, et al. Screening for HIV infection: US Preventive Services Task Force recommendation statement. JAMA 2019;doi: 10.1001/jama.2019.6587.
- Chou R, Dana T, Grusing S, et al. Screening for HIV infection in asymptomatic, nonpregnant adolescents and adults: Updated evidence report and systematic review for the US Preventive Services Task Force. JAMA 2019;doi:10.1001/jama.2019.2592.
- Selph SS, Bougatsos C, Dana T, et al. Screening for HIV infection in pregnant women: Updated evidence report and systematic review for the US Preventive Services Task Force. JAMA 2019;doi:10.1001/jama.2019.2593.
- US Preventive Services Task Force, Owens DK, Davidson KW, Krist AH, et al. Preexposure prophylaxis for the prevention of HIV infection: US Preventive Services Task Force recommendation statement. JAMA 2019;321:2203-2213.
- Chou R, Evans C, Hoverman A, et al. Preexposure prophylaxis for the prevention of HIV infection: Evidence report and systematic review for the US Preventive Services Task Force. JAMA 2019;321:2214-2230.
A potential analytical tool may help providers identify those at risk for HIV in efforts to offer pre-exposure prophylaxis (PrEP). Using a machine-learning algorithm to predict who could become infected with HIV during a three-year period, researchers were able to flag 2.2% of 3.7 million patients as high or very high risk.
Subscribe Now for Access
You have reached your article limit for the month. We hope you found our articles both enjoyable and insightful. For information on new subscriptions, product trials, alternative billing arrangements or group and site discounts please call 800-688-2421. We look forward to having you as a long-term member of the Relias Media community.