Since 2014, VisionQuest’s Senior Scientist Vinayak Joshi (PhD) has been working with leading researchers in tropical medicine to develop inexpensive, easy-to-use artificial intelligence based software and portable cameras capable of detecting the retinal abnormalities that indicate cerebral malaria. Cerebral malaria kills hundreds of thousands of children every year in sub-Saharan Africa. Many more die because traditional clinical diagnoses do not reveal other underlying causes of disease. However, the system developed by Dr. Joshi and colleagues provides any health-care provider with immediate feedback, enabling accurate diagnosis and correct treatment.
VisionQuest had something marvelous to offer doctors. When Vinayak approached me with an idea for developing a camera with an algorithm that could analyze pictures and determine whether [a child had] malarial retinopathy or not, I was very skeptical. Sometimes it’s nice to be proven wrong.Dr. Susan Lewallen
A Picture Begins to Emerge
Beginning in the 1980s, Dr. Taylor studied cerebral malaria in the children she treated, always trying to improve their chances of survival. She explored the shortcomings of the clinical diagnosis and sought to understand why children who met the WHO criteria and were treated appropriately were still dying.
Dr. Lewallen began visiting Dr. Taylor’s patients, and by the end of the malaria season, her data showed that children with unusual retinal features were dying more often than ones with normal retinas. As they began to publish their findings on malarial retinopathy, doctors like Professor Simon Harding directed resources and expertise toward solving the problem. A picture began to emerge: malarial retinopathy was a compelling indicator of cerebral malaria, malaria parasites in the blood vessels of the brain.
Other researchers have since confirmed the unique association between malarial retinopathy and cerebral malaria: comatose, malarial children with malarial retinopathy have cerebral malaria; comatose, malarial children without malarial retinopathy do not have cerebral malaria and thus can be investigated further for other non-malarial illnesses and treated accordingly.
Overcoming Barriers to Treatment
For the past several years Dr. Joshi has been working with Dr. Taylor, Dr. Lewallen, and others to develop new tools that overcome barriers to treatment. They are testing cameras and AI techniques that can be used by anyone, anywhere: doctors, nurses, and community health-care workers in the hospital and in the field. The portable cameras and smartphone- or cloud-based software use algorithms engineered by Dr. Joshi to detect the biomarkers of malarial retinopathy—hemorrhage, whitening, and vessel discoloration—and to provide results in real time. In other words, a health-care worker who travels to a rural clinic with the camera and software in their backpack can take retinal photographs, process the images, and receive the results of the analysis all in a few moments.
“When things are like that,” says Dr. Moira Gandiwa, an ophthalmologist in Malawi, “patients are more willing to accept treatment. If it means they can go to a district hospital, for example, be seen quickly, [have] pictures taken, a diagnosis made immediately—they’ll be more willing to come back for another checkup. For most of our patients, when there’s good news, they spread the good news.”
Our collaboration could be characterized in a number of ways: it is a unique application of artificial intelligence and personalized medicine in the developing world; it is a project that aims to support, not supplant, the Malawian health-care system by putting powerful diagnostic tools into the hands of local caregivers; it is an effort to bring inexpensive, portable, easy-to-use technology into remote and underserved communities; and above all, it is an attempt to save children’s lives.
The Road Ahead
With funding from the US National Institute of Allergy and Infectious Diseases and support from the Malawi Ministry of Health, Dr. Joshi has been working with Taylor and other doctors in Malawi to demonstrate the effectiveness of our system, make improvements, and prepare for distribution. We plan to add previously developed tools to the new system—such as an automatic detector of diabetic retinopathy—to increase its usefulness and cost-effectiveness, and we are approaching organizations that would be able to assist us in reaching the populations most in need of this singular technology.
The first time Dr. Joshi developed software for malarial retinopathy diagnosis, it was just another piece of code. The real work began when he visited a malaria clinic in Malawi. He realized that he would need to think about developing tools that would be affordable and accessible to the patients who need them. The work has been challenging, both technically and personally, as well as incredibly rewarding. “We’ve taken the first steps toward solving an important problem,” says Dr. Joshi, “and we’re ready to put this technology into the hands of the people who need it most.”