Quantcast

Researchers Use AI to Safely Lower Drug Dosage for HIV Patients

A first-of-its kind method to determine the drug cocktail for HIV patients that avoids serious side effects has been developed by a UCLA engineer, Chih-Ming Ho, and international collaborators. The technique uses artificial intelligence to determine the lowest and safest dose, and thereby less toxic, combination therapy for HIV patients.

The team’s finding is published in Advanced Therapeutics, and could pave the way to effectively lower dosage for other diseases, such as cancer and tuberculosis.

HIV therapy drugs have successfully extended the lives of individuals, but they also can cause serious side effects including kidney failure, the softening of bones or pancreatitis. Under current practice, the various prescriptions used in combination therapy are maintained at the same level even if there is a significant decline of the virus, potentially leading to an excess of the medication in the bloodstream.

Until now, lowering the dose without sacrificing effectiveness has proven challenging since guidelines are typically set by determining the maximum tolerated dose through trial-and-error testing.

In this prospective pilot clinical trial, the researchers focused on the combination therapy of tenofovir (TDF), efavirenz (EFV) and lamivudine (3TC), first-line drugs recommended by the World Health Organization for the long-term maintenance of HIV.

Enabled by neural networks analysis, the researchers discovered drug-dose combination is related to the efficacy through a Parabolic Response Surface (PRS), which can identify the optimized regimen customized to a specific patient.

Using the PRS platform, researchers were able to demonstrate that lowering the dose by one-third of TDF, the medication that causes serious long-term adverse effects, did not result in a relapse of the virus.

“For the first time, we successfully applied artificial intelligence-based PRS technology to

determine the lowest and safest dose for a specific HIV patient,” said study author Ho, distinguished research professor of mechanical and aerospace engineering at the UCLA Samueli School of Engineering. “This HIV regimen proof-of-concept can also be applied to a general population of HIV patients, as well as to other diseases.”

Previously, Ho and other researchers have demonstrated the approach could be used to design faster, more effective treatments for diseases such as tuberculosis, other infectious diseases, cancers, and for organ transplants. This is the first time any AI-based technique has been used to find the lowest effective dose.

Additional senior authors on the study are Yinzhong Shen and Hong-Zhou Lu of Fudan University in China; Tingyi “Leo” Liu of the University of Massachusetts, Amherst; Xianting Ding of Shanghai Jiao Tong University; and Dean Ho of National University of Singapore. The study was partially supported by a grant from the Bill & Melinda Gates Foundation.

UCLA Samueli is a tightly knit community of 185 full-time faculty members, more than 6,000 undergraduate and graduate students, as well as 40,000 active alumni. Known as the birthplace of the internet, UCLA Samueli is also where countless other fields took some of their first steps – from artificial intelligence to reverse osmosis, from mobile communications to human prosthetics. UCLA Samueli is consistently ranked in the Top 10 among U.S. public engineering schools. The school’s online master’s program ranks in the Top 3.




The material in this press release comes from the originating research organization. Content may be edited for style and length. Want more? Sign up for our daily email.