Artificial intelligence

News A new AI tool can predict the age of mosquitoes with 98% accuracy to speed up malaria research

Schematic of a deep learning model that uses mosquito spectra as input to predict mosquito age classes. A sort of CNN – No Dimensionality Reduction Applied: Normalized spectral features are passed through four different convolutional layers as input, followed by a fully connected layer with the predicted age category shown as the output layer. Second MLP – Using Dimensionality Reduction: Spectral features reduced using PCA or t-SNE are passed through 6 fully connected layers as input, and the predicted age category is shown as the output layer. Credit: BMC Bioinformatics (2023). DOI: 10.1186/s12859-022-05128-5

Using machine learning to predict the age of different populations of mosquitoes could reduce turnaround time for malaria research and improve surveillance programs BMC Bioinformatics.

Knowing the age of mosquitoes helps scientists understand their potential to transmit malaria, but existing tools for predicting this are costly, labor-intensive and often prone to human error, the researchers said.

With Africa accounting for about 95 percent of the 247 million malaria cases worldwide in 2021, according to the World Health Organization, scientists say innovative tools to control mosquitoes and prevent malaria transmission are key to eliminating the disease.

The study looked at mosquito strains raised in laboratories at the Ifakara Institute of Health in Tanzania and the University of Glasgow in Scotland. The researchers recorded the mosquito’s biochemical composition using an analytical tool called infrared spectroscopy, and used machine learning — a form of artificial intelligence (AI) — to train a model to predict the mosquito’s age.

Emmanuel Mwanga, lead author of the study and a research scientist at the Ifakara Institute of Health, says machine learning is a more effective option than existing laborious and expensive tools for predicting mosquito ages.

“One of the challenges we’ve had with machine learning is that it’s difficult to accurately identify the age of mosquitoes from different locations,” Mwanga said. “This is the main question addressed in this paper. It is important to test the findings in mosquitoes from different places and species.”

However, the scientists stress that further research is needed because the study only looked at one specific type of mosquito, Anopheles arabiensis, which came from only two countries.

The results of the study showed that the machine learning model improved the accuracy of the prediction of the age of the same mosquito to about 98%.

Malaria interventions could be improved if malaria scientists learned more about the precise age, host preference and species of malaria carriers, Mwanga said.

According to the researchers, older mosquitoes are more likely to transmit malaria than younger ones, but mosquitoes that prefer to eat humans are more likely to transmit malaria than those that prefer other animals, so studying their properties is critical to efforts to tackle malaria .

“Accurate prediction of these factors can help identify high-risk populations and target interventions more effectively,” Mwanga explained, adding that using machine learning techniques could “save time and resources that could be spent on malaria control and elimination.” other aspects of work.”

“This will ultimately lead to a reduction in malaria cases and deaths in the region, which is an important step towards zero malaria,” he said.

According to the researchers, these findings show that artificial intelligence can be used to determine the age of different populations of mosquitoes.

“This could help entomologists reduce the time and effort required to dissect large numbers of mosquitoes,” the study said. “Overall, these approaches have the potential to improve model-based surveillance programs, such as assessing the impact of malaria vector control tools, by monitoring the age structure of local vector populations.”

Frank Mussa, head of research and development at Afya Intelligence, a Tanzanian company focused on using artificial intelligence in healthcare, said the findings, if incorporated into malaria interventions, could facilitate the planning of malaria interventions.

“[The] The findings are necessary for policy makers as they will make resource allocation simpler, assist in trend forecasting, and help in the development of sound strategic plans for malaria elimination in Tanzania,” he said.

More information:
Emmanuel P. Mwanga et al. Improving the Generalizability of Machine Learning to Predict Mosquito Age from Mid-Infrared Spectroscopy Using Transfer Learning and Dimensionality Reduction Techniques, BMC Bioinformatics (2023). DOI: 10.1186/s12859-022-05128-5

quote: A New Artificial Intelligence Tool Can Predict Mosquito Age With 98% Accuracy to Accelerate Malaria Research (2023, Jan. 25), accessed Jan. 25, 2023 from 2023-01-ai-tool-mosquitoes-ages retrieve-accuracy.html

This document is protected by copyright. Except for any fair dealing for private study or research purposes, no part may be reproduced without written permission. The content is for reference only.

Related Articles

Leave a Reply

Your email address will not be published. Required fields are marked *

Back to top button