Malaria is a life-threatening disease caused by Plasmodium parasites and transmitted through the bites of infected female Anopheles mosquitoes. There are five parasite species that cause malaria in humans of which P. falciparum and P. vivax pose the greatest threat, often progressing to severe illness, multi-organ failure, or death.
In 2019, nearly half of the world's population was at risk of malaria, with an estimated 229 million malaria cases globally, particularly affecting children under the age of 5, accounting for 67% of deaths worldwide. Most malaria cases and deaths occur in sub-Saharan Africa. The WHO African Region holds about 94% of cases and death globally.
Traditional testing methods
There are multiple techniques available to detect malarial parasites, such as clinical diagnosis, polymerase chain reaction (PCR), microscopic diagnosis, and rapid diagnostic test (RDT). Efficiency and accuracy of clinical diagnosis and PCR methods depend on laboratory settings and the level of available expertise, limited commodities in unreached remote areas. The most common tests are therefore microscopy and RDT. However, RDT struggles from lack of sensitivity, high costs, inability to quantify parasite density and differentiate among some species. It is also highly susceptible to damage by heat and humidity, conditions that favor malaria transmission.
Microscopic examination of Giemsa-stained blood smears, taken from a finger prick, is the easiest and most reliable test for malaria. Thick blood smears are most useful for detecting parasite density, which affects whether medicine is provided intravenously instead of orally. Thin blood smears are analyzed to detect the type of parasite present. For example, malaria caused by P. falciparum is more serious than other types and may need different treatment. Microscopy techniques remain the gold standard for laboratory confirmation of malaria. However, accuracy depends on the quality of the reagents, the microscope, and the experience of a trained microscopist.
AI powered diagnosis
Detecting malaria parasites in blood smear can be time-consuming, laborious, and error-prone with conventional microscopy. Combined with limited training of lab technicians, current diagnostic methods are not enough for the large amount of malaria cases in developing countries. Deep learning AI-based methods have the potential to automate the process, aiding lab technicians in optimizing their time and increasing accuracy and efficiency.
AI models can be trained using annotated datasets to find parasites in blood smears, such as Aiforia's AI software as demonstrated in the video below. Through simple annotation of infected cells to train the algorithm, the automation process includes quantifying parasite density, faster and more accurately than human-based microscopy. This reduces turnaround time, improves diagnostic performance and provides consistent and accurate care to patients in a timely manner.
Automated image analysis is particularly beneficial for malaria diagnosis in restricted resource environments, where trained workforce is limited. Healthcare professionals can focus on preparing the slides of blood samples, verifying the results, and tending to patients. AI image analysis solutions are not constrained to malaria detection and can be applied to any microscopical assessment, redefining the future of diagnostics.