The Era of Artificial Intelligence in the Fight Against HIV in South Africa
Harvard researchers are conducting field tests to enhance the HIV-LIFT program—operated via the WhatsApp-based Coach Mpilo health application in South Africa—using artificial intelligence.
A Harvard research team led by Milind Tambe is testing an artificial intelligence-based protocol to increase HIV testing and care services in South Africa. The study aims to optimize peer referrals within Coach Mpilo, a WhatsApp-based health coaching application, as part of the HIV-LIFT initiative.
The team, led by Milind Tambe, Professor of Computer Science at the Harvard John A. Paulson School of Engineering and Applied Sciences, is participating in a field trial conducted in South Africa's KwaZulu-Natal province. With approximately 8 million people living with HIV, ranking it first globally, the country aims to reach groups that are less inclined to visit testing centers, particularly men and youth.
Funded by the Gates Foundation and led by principal investigator Alastair van Heerden from Wits University, the HIV-LIFT (Leveraging Innovation and Friendships to Improve HIV Testing) project brings together partners such as the Harvard Teamcore research group, the World Health Organization, and Wits University.
Currently boasting more than 150,000 registered users, the Coach Mpilo application offers free and confidential digital health coaching via WhatsApp; however, men account for only about 15 percent of users. The Harvard team developed a machine learning and optimization approach that more smartly targets financial incentive processes offered to existing users to refer others to testing services. In the planned study, a group in which eligible users are randomly selected is compared against an AI-filtered group that narrows the incentive pool based on past campaign data.
Sources
- seas.harvard.edu · Link