[DAR-ES-SALAAMI] Using machine learning techniques to predict the lifespan of mosquitoes from different populations can reduce response time for malaria research and improve monitoring programmes, study Says.
Knowing the age of the mosquito helps scientists understand its ability to spread malaria, researchers say, but the current tools used to predict this are expensive, labor-intensive and often prone to human error.
according to World Health OrganizationThe African region accounted for about 95 percent of the 247 million cases malaria globally in 2021, scientists say adopt innovative Mosquito control tools and preventing the spread of malaria are key to eradicating the disease.
The study targeted strains of mosquitoes reared in laboratories at the Ifakara Health Institute in Tanzania and the University of Glasgow in Scotland.
Using analytical tools known as infrared spectroscopy, the researchers recorded the mosquito’s biochemical composition, and used machine learning — a form of artificial intelligence (AI) — to train models that can predict the mosquito’s lifespan.
says Emmanuel Mwanga, lead author of the study and one of the team Research Scientist at the Ifakara Health Institute. “This is the main problem that this paper addresses.”
Machine learning is a more efficient option, Mwanga says, compared to current tools for predicting mosquito lifespans that are laborious and expensive.
“It’s important to test the results on mosquitoes from different locations and species,” explains Mwanga.
However, the scientists stress that more research is needed because the study looked at only one species of mosquito, Anopheles arabiensisobtained from only two countries.
The results of the study have been published in BMC Bioinformatics This month (9 In January, machine learning models were able to improve the accuracy of predictions for the same mosquito ages to about 98 percent.
Muwanga says SciDev.Net Network Malaria interventions can be improved if malaria scientists understand the exact age and preferences of the host and the types of malaria carriers.
According to the researchers, old mosquitoes are more likely to transmit malaria than young ones, but mosquitoes that prefer to feed on humans are more likely to transmit malaria than those that prefer other animals, making studying their characteristics vital in malaria control efforts.
“Accurate prediction of these factors can help identify high-risk populations and target interventions more effectively,” Mwanga explains, adding that the use of machine learning techniques can “save time and resources that can be used in other aspects of malaria control and elimination efforts.” .
“This could eventually lead to a decrease in the number of malaria cases and deaths in the region, which is an important step towards achieving total malaria eradication,” he says.
“Accurate prediction of these factors can help identify high-risk populations and target interventions more effectively.”
Emmanuel Mwanga, Ifakara Health Institute
According to the researchers, the results indicate that artificial intelligence can be used to determine the age of mosquitoes from different populations.
“This could help entomologists reduce the amount of time and labor required to dissect large numbers of mosquitoes,” the study says. “Overall, these approaches have the potential to improve model-based surveillance programmes, such as evaluating the impact of malaria vector control tools, by observing the age structures of local vector populations.”
Frank Moses, Head of Research and Development Wellness intelligence Tanzania based company focused on using artificial intelligence in Health CareSays SciDev.Net Network The findings, if integrated into malaria interventions, could inform the planning of malaria-specific interventions.
“[The] Results are essential to policy makers Because it will make resource allocation simpler, help forecast trends and help develop sound strategic plans for malaria eradication in Tanzania,” he says.
This piece was produced by SciDev.Net Sub-Saharan Africa in English.