Researchers say they used Artificial Intelligence together with a citizen-submitted smartphone photo to identify what they believe was the first Anopheles stephensi detected in Madagascar. The discovery started with a close-up image of a larva collected from a tyre in Antananarivo. The image was taken in 2020 and only surfaced two years later when scientists reviewed historical records; the results were published in the journal Insects and the work was led by Ryan Carney.
The team trained AI image-recognition algorithms on thousands of smartphone photos of verified Anopheles stephensi and other local species. With these algorithms they built a citizen science tool that they say could confirm the species of the larva spotted five years ago. The researchers present the case as an example of how local communities and digital technology can fill surveillance gaps in dense urban areas that are hard to monitor by conventional methods.
Anopheles stephensi is particularly susceptible to the malaria parasite and highly resistant to pesticides. It thrives in cities and breeds in artificial containers such as tyres and buckets, enabling year-round malaria transmission in densely populated areas; a previous study indicated its spread could put an additional 126 million people at risk across Africa. The team points to three free apps—iNaturalist, Mosquito Alert and NASA’s GLOBE Observer—available globally and offering languages including Swahili and Arabic.
The researchers advise that public health agencies use the Global Mosquito Observations Dashboard, which aggregates photos and location data to help target surveillance and control. They also note clear limitations: many people in Madagascar lack smartphones or reliable internet, many are unaware the apps exist, and the AI was trained on photos taken with a 60x clip-on lens, so technical requirements can be a barrier. To increase participation they recommend that malaria control programmes and public health agencies help citizens obtain the correct lens and raise awareness, and some experts stress the importance of placing tools directly in community hands as international aid for disease control declines.
Difficult words
- algorithm — a set of rules a computer followsalgorithms
- surveillance — regular watching or monitoring to detect problems
- larva — immature stage of an insect before becoming adult
- susceptible — likely to be affected or harmed by something
- resistant — able to withstand or not be harmed by
- aggregate — to collect and combine items into one groupaggregates
- container — an object that holds liquid or other materialcontainers
- participation — the act of taking part in an activity
Tip: hover, focus or tap highlighted words in the article to see quick definitions while you read or listen.
Discussion questions
- What are the main benefits and risks of using citizen-submitted photos and AI for disease surveillance in cities? Give reasons.
- How could public health agencies help reduce the barriers mentioned (lack of smartphones, technical lens requirements) in communities like Madagascar?
- Do you think community access to tools and apps is better supported by local programmes or international aid? Explain your view with examples.
Related articles
Experimental vaccine gives lasting protection in mice against CCHF
A new mouse study reports an experimental vaccine that produced rapid protection and antibodies that lasted up to 18 months. Researchers say a booster strengthened and extended immune responses and plan manufacturing steps before human trials.
Smart textiles could monitor and protect health
Researchers reviewed studies on MXenes, microscopic metal-based materials that can give fabrics new functions. MXene-based smart textiles can measure vitals, show antimicrobial behaviour and harvest solar energy, but they face limits like oxidation and sustainability.
Electric car batteries can power homes and cut costs
A University of Michigan study finds that using electric vehicle batteries to power homes (vehicle-to-home, V2H) can save owners thousands of dollars and reduce greenhouse gas emissions. Results differ across regions and the technology is still being tested.
