A group of researchers at Makerere University in Kampala, Uganda have developed an app that uses photos of blood samples to diagnose malaria within 2 minutes
A group of researchers at Makerere University in Uganda have developed an app that uses photos of blood samples to diagnose malaria quickly. This technology is a huge step towards helping patients in shorter spaces of time.
Malaria was reportedly the leading cause of death in Uganda as of 2016. 27% of deaths in the region resulted from the mosquito-borne disease. The country also has the highest recorded rate of malaria in the world, with nearly 480 per 1,000 people contracting the disease annually.
A CNN report paints a picture of the Kiruddu General Hospital, Kampala Uganda. Doctors in white coats flood the hallways moving to and fro past tired looking patients in Kitenge fabrics.
On the floor above, lab technicians take on a heavy pile of slides for microscopic examination. The technicians look through the eyepieces of their equipment trying to figure out if the samples contain malaria parasites or the bacteria that causes tuberculosis.
The process takes a very long time and can be quite exhausting as the technicians have to adjust the slide gently about a hundred before a proper diagnosis can be given.
The usual practice is that technicians could handle only 25 samples in a day but in situations like this, they handle about four times that amount. A team at Uganda’s first Artificial Intelligence lab at Makerere University is helping to lighten the load on technicians.
Alfred Andama, a doctor at the lab, spoke to CNN, saying “We have so many patients who may require malaria and TB tests, and we have one technician looking at all these slides”, “Apart from affecting their eyes, this also compromises their ability to report correctly what they see.”
How Does The App Works
A smartphone is clamped on the microscope’s eyepiece. It then illuminates an image of a blood sample. Malaria parasites are then circled in red by the Artificial Intelligence software. The results are later reviewed by technicians, who are responsible for training the software to help map them efficiently.
Correct diagnosis usually takes up to 30 minutes to reach but could now be cut to just 2 minutes. The software is still only being used in select hospitals in Kampala, but researchers are hopeful that it will reach rural communities soon.
Photo Credit: CNN / Africa Tech Rising