AI helps HIV patients avoid adverse side effects
Researchers have used AI technology to ensure HIV patients experience fewer significant side effects during treatment, according to new findings published in Advanced Therapeutics.
Antiretroviral therapy (ART) has made a big impact on HIV patients throughout the world, the study’s authors explained, but the side effects associated with ART can be so severe that some patients stop taking their medication altogether. The team’s goal was to help healthcare providers find the right balance for patients, lowering the dose to reduce certain side effects without making ART less effective.
For their clinical trial, the authors focused on a treatment recommended by the World Health Organization: the combination therapy of tenofovir (TDF), efavirenz (EFV) and lamivudine (3TC). While 3TC was consistently administered at a dose of 300 mg, EFV was administered at 400 mg and three different doses—150 mg, 200 mg and 300 mg—were tested for TDF. Ten male test subjects with asymptomatic HIV infection participated in the study, which included 144 weeks of data.
Use of an AI-powered Parabolic Response Surface (PRS) platform helped them determine that reducing TDF, the medication most commonly associated with serious adverse effects, from 300 mg to 200 mg did not affect patient outcomes.
“For the first time, we successfully applied artificial intelligence-based PRS technology to determine the lowest and safest dose for a specific HIV patient,” author Chih-Ming Ho, PhD, a distinguished research professor of mechanical and aerospace engineering at the UCLA Samueli School of Engineering, said in a prepared statement. “This HIV regimen proof-of-concept can also be applied to a general population of HIV patients, as well as to other diseases.”
The authors acknowledged that their research included a limited patient cohort, noting that “further clinical validation” is needed.
“However, it is important to note that small cohort-based studies are being increasingly utilized, especially for cases where each patient is receiving a unique drug/dose regimen,” the authors wrote.
Portions of the team’s study were supported by the Bill & Melinda Gates Foundation.
Michael has more than 18 years of experience as a professional writer and editor. He has written at length about cardiology, radiology, artificial intelligence and other key healthcare topics.