05/13/2021 at 8:33 AM CEST
Citizen science, with the help of artificial intelligence, is becoming an effective weapon to identify the tiger mosquito (Aedes albopictus), an invasive species from Southeast Asia and a transmitter of serious diseases, whose presence has been confirmed in about half a thousand Spanish municipalities, located throughout the Mediterranean, including the Balearic Islands, Aragon, Navarra, the Basque Country and Madrid. Now, scientists have discovered a momentous improvement to the app used to identify the tiger mosquito.
Until now, through the Mosquito Alert app the thousands of photographs of mosquitoes that the aid workers were sending of mosquitoes were collected. Then the entomologists analyzed the images, one by one, to determine if they were specimens of species capable of transmitting global diseases, such as dengue, Zika, or West Nile fever.
But now researchers from Mosquito Alert, a cooperative and non-profit citizen science project, together with experts from the University of Budapest, have taken a giant step: they have discovered an artificial intelligence algorithm of deep learning, which is capable of correctly identifying 96% of tiger mosquito photographs.
The results of the study, published in Scientific Reports, have been obtained by applying a novel deep learning technology, an aspect of artificial intelligence that seeks to emulate the way of learning of humans and that has previously been used in the health field to interpret medical images (X-rays of patients with covid-19 to detect pneumonia, or facial features to detect heart disease, among others).
The deep learning algorithm has been trained with more than 7,000 anonymous photos, received in the Mosquito Alert app between 2015 and 2019, as it requires a lot of training data to “learn & rdquor ;.
“The initial idea is to get the machine to classify the simplest photos, and leave it to the experts to identify the most problematic images that require consensus & rdquor ;, explains John Palmer, researcher at Pompeu Fabra University (UPF) and co-director of Mosquito Alert.
“As the artificial system learns from expert classifications, we will be able to expand the range of automatically cataloged species & rdquor ;, adds the scientist.
Those responsible for Mosquito Alert believe that This milestone will mark “a before and after & rdquor; in the surveillance and monitoring of the tiger mosquito and other mosquitoes capable of transmitting disease.
“We are training a social immune system against these species. The faster the threat is detected, the faster you can act on it & rdquor ;, he says Frederic Bartumeus, co-director of Mosquito Alert and researcher at the Catalan Institution for Research and Advanced Studies (ICREA).
Mosquito Alert citizen science allows anyone to be part of this new social immune system and contribute photos of mosquitoes. And artificial intelligence speeds up the process of classifying received photos and helps public health experts make better and faster decisions about mosquito management.
“In times of greatest need, such as in the months of greatest mosquito activity or in a context of epidemiological crisis, artificial intelligence can help us so that the system can absorb a greater amount of information, controlling its quality at all times, which it is key if the data is to be used for decision-making in public health & rdquor ;, adds Bartumeus.
It is a very important advance, because the presence of the tiger mosquito in Spain poses a threat to public health. In Europe, the tiger mosquito has been implicated every year since 2007 in small outbreaks of local transmission of viral diseases against which no vaccines are available.
In Spain since 2004
In Spain, the first detection was notified in August 2004, in Sant Cugat del Vallès (Catalunya). It has been included in the Spanish Catalog of Invasive Alien Species since 2013. And the International Union for the Conservation of Nature (IUCN) has included it in the list of the 100 most harmful alien species in the world.
The only preventive measure is to control mosquitoes. And evaluating the risk and the action measures necessary to mitigate it requires having accurate information on tiger mosquito populations, a costly and laborious task that requires manual placement and inspection of traps and their subsequent analysis in the laboratory where the insects are identified. A methodology that is not feasible to cover large geographic areas.
This is where Mosquito Alert citizen science plays a key role, since by allowing anyone to notify the presence of a mosquito through a mobile application, large geographic areas can be covered. And the integration of artificial intelligence in the process speeds up the classification and allows the development of risk maps in near real time to improve the management of the tiger mosquito.
However, artificial intelligence also has limitations. “It will take time until a machine can have the same capacity as an expert eye, especially for other species less characteristic than the tiger mosquito & rdquor; highlights Roger Eritja, scientist at the Center for Ecological Research and Forestry Applications (CREAF) and entomological director of Mosquito Alert.
“In Spain 62 species of mosquitoes have been described, many of which currently cannot be classified from an image, but must be examined under a microscope. In some other cases, even genetic testing is required to identify them & rdquor ;, Eritja says.
Citizens who collaborate with Mosquito Alert must include with the images the location of the observation and all possible information to help in the identification of the species.
The information obtained through the Mosquito Alert app complements scientific work in the surveillance of invasive mosquitoes, and can be used by public health managers to monitor and control these mosquitoes in neighborhoods and cities.
The software used in the application Mosquito Alert is free and open source. It can be downloaded like any other app through the mobile phone. It is distributed under a license that allows you to use, change, improve and redistribute the software, either in its modified form or in its original form.
In addition to the tiger mosquito, the project analyzes the presence in Europe of the yellow fever mosquito (Aedes aegypti), the Japanese mosquito (Aedes japonicus), the Korean mosquito (Aedes koreicus) and the common mosquito (Culex pipiens).
It may interest you: 2020 doubles alerts for tiger mosquitoes in Spain