A schematic representation of deep learning models using mosquito spectra as input to predict mosquito age classes. A CNN – no dimensionality reduction is applied: standardized spectral features are inputted through four different convolutional layers, followed by one fully connected layer, with the predicted age classes shown as the output layer. B MLP – dimensionality reduction is used: Spectral features that have been reduced in dimension using PCA or t-SNE are inputted as inputs through 6 fully connected layers, with the predicted age classes displayed as the output layer. Credit: BMC Bioinformatics (2023). DOI: 10.1186/s12859-022-05128-5
Using machine learning techniques to predict the age of mosquitoes from different populations could shorten the turnaround time of malaria research and improve surveillance programs, says a new study published in BMC Bioinformatics.
Knowing a mosquito’s age helps scientists understand its potential to spread malaria, but the existing tools used to predict this are costly, labor-intensive and often prone to human error, the researchers say.
According to the World Health Organization, the African region accounted for about 95 percent of the 247 million cases of malaria worldwide by 2021, and scientists say the introduction of innovative tools to mosquitoes and preventing the spread of malaria is key to eradicating the disease.
The study focused on mosquito species bred in laboratories at the Ifakara Health Institute in Tanzania and the University of Glasgow in Scotland. Using analytical tools known as infrared spectroscopythe researchers recorded the biochemical composition of mosquitoes and used machine learning – a form of artificial intelligence (AI) – to train models to predict the age of mosquitoes.
Emmanuel Mwanga, lead author of the study and a researcher at the Ifakara Health Institute, says machine learning is a more efficient option than existing tools for predicting the age of mosquitoes, which are labor-intensive and costly.
“There is one challenge we have faced in the field of machine learning, which is the difficulty of accurately identifying the age of mosquitoes from different locations,” says Mwanga. “This is the main problem this article addresses. It is important to test the findings on mosquitoes different places and types.”
However, the scientists stress that further research is needed, as the study only looked at one specific type of mosquito, Anopheles arabiensis, obtained from only two countries.
Findings of the study show that the machine learning models improved the accuracy of the predictions for the same mosquito ages to about 98 percent.
Mwanga says malaria interventions could be improved if malaria scientists better understand the appropriate age, host preferences and species of the malaria-carrying agents.
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 mosquitoes that prefer other animals, making studying their characteristics essential in the fight against malaria.
“Accurately predicting these factors can help identify high-risk populations and target interventions more effectively,” explains Mwanga, adding that the use of machine learning techniques could “save time and resources that could be used for other aspects of malaria control and elimination.”
“This could ultimately lead to a reduction in malaria cases and deaths in the region, which is an important step towards zero malaria,” he says.
According to the researchers, the findings suggest 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 work required to dissect large numbers of mosquitoes,” the study says. “Overall, these approaches have the potential to improve model-based surveillance programs, such as assessing the impact of malaria vector control tools, by tracking the age structures of local vector populations.”
Frank Mussa, a research and development lead at Afya Intelligence, a Tanzania-based company focused on the use of AI in healthcare, says the findings, if incorporated into malaria interventions, could inform planning for malaria interventions. stimulate.
“[The] findings are necessary for policy makers because they will make resource allocation easier and assist in trend forecasting and assist in the development of sound strategic plans for the elimination of malaria in Tanzania,” he says.
Emmanuel P. Mwanga et al., Using transfer learning and dimensionality reduction techniques to improve the generalizability of machine-learning predictions of mosquito ages from mid-infrared spectra, BMC Bioinformatics (2023). DOI: 10.1186/s12859-022-05128-5
Quote: A new AI tool can predict the age of mosquitoes with 98% accuracy to accelerate malaria research (2023, January 25) Retrieved January 25, 2023 from https://phys.org/news/2023-01- ai-tool-mosquitoes-ages -accuracy.html
This document is copyrighted. Other than fair dealing for private study or research, nothing may be reproduced without written permission. The content is provided for informational purposes only.