About 1.6 million people in the southeast African country of Mozambique live with HIV. Antiretroviral therapy can prevent its spread, but only 74 percent of patients who start HIV treatment are still taking the medicines a year later.
In November 2011, the U.K.-based children’s organization ARK began a two-year test of sending text messages to HIV-positive people in urban and rural areas of Mozambique’s Maputo Province to remind them about treatments and appointments. About 15.5 million mobile phones are already connected in the country of 25.8 million people, and use of the technology is growing.
ARK’s study followed 830 men and women undergoing antiretroviral therapy for an average of 16 months, and 522 HIV-positive expectant mothers until eight weeks after giving birth. Patients were randomly assigned to receive the text reminders or to continue regular treatment with no reminders.
Using a database of electronic patient records, a computer program sent out automated text reminders at times including a week before an appointment, two days before the appointment, and two days after any missed appointments. HIV-positive pregnant women also received educational messages about testing and treatments.
The SMS messages helped some patients improve their treatment regimen, but not all. The messages significantly helped urban and recently diagnosed HIV patients stick with treatment. Such patients who didn’t receive text messages were nearly twice as likely to fall off the program, failing to consistently pick up drugs or attend appointments. Results at the rural centers were disappointing, possibly because of transportation issues, limited cellular coverage, migration to other provinces, and a limited sample size.
The texts did help persuade mothers to test their newborns for HIV, but overall the program didn’t make them more likely to complete pre-birth treatment or to give birth in a health center.
Now that texting has been shown to help some patients, several groups are launching a much bigger messaging program in another Mozambican province. This program could reach 58,000 patients by the time it concludes in 2016. Researchers will examine how cost-effective the trial is, how to improve technology in rural areas, and how best to support patients who are most at risk of not completing treatment.
This new data poisoning tool lets artists fight back against generative AI
The tool, called Nightshade, messes up training data in ways that could cause serious damage to image-generating AI models.
The Biggest Questions: What is death?
New neuroscience is challenging our understanding of the dying process—bringing opportunities for the living.
Rogue superintelligence and merging with machines: Inside the mind of OpenAI’s chief scientist
An exclusive conversation with Ilya Sutskever on his fears for the future of AI and why they’ve made him change the focus of his life’s work.
How to fix the internet
If we want online discourse to improve, we need to move beyond the big platforms.
Get the latest updates from
MIT Technology Review
Discover special offers, top stories, upcoming events, and more.