Pilot Award Recipient: Sydney Bornstein

"There is an urgent need to expand the uptake of evidence-based HIV prevention tools to continue to prevent HIV transmission among people who inject drugs (PWID), particularly in light of recent federal policy shifts. Pre-exposure prophylaxis (PrEP) is an evidence-based form of biomedical HIV prevention that reduces HIV incidence among all populations, including PWID. There are currently two FDA-approved oral and two FDA-approved long-acting injectable (LAI) forms of PrEP, allowing people at risk of HIV infection to identify the best method for themselves. However, despite expressed interest in oral and LAI PrEP, awareness is low and uptake is rare among PWID. Machine learning can be leveraged to increase PrEP awareness and uptake by developing tools to more effectively provide and tailor discussions during HIV testing and counseling. The purpose of this study is to develop a novel, preliminary tool to promote tailored PrEP discussions and referrals among PWID during HIV post-test counseling. Through Aim 1, Bornstein and team will assess the acceptability of integrating machine learning-based tools into HIV post-test counseling among both PWID and providers. Through Aim 2, they will develop a machine learning-based tool that uses data from the NHBS system in Washington, DC to predict interest in PrEP among PWID and support tailored discussions and referrals during HIV post-test counseling."

Project Summary provided by investigator.