AI and Malaria Control: an Exciting Future Ahead

Matt RomneyArticle, News, Newsletter

A Jerusalem-based start-up ZzappMalaria that uses artificial intelligence (AI) and tech to eliminate malaria has won first place in the IBM Watson AI XPRIZE Competition, securing a $3 million prize, as well as the People’s Choice Award as the “Most Inspiring Team.” 

How Zzapp identifies malaria transmission hotspots 

Zzapp is a software system that supports the planning and implementation of malaria elimination operations, and makes use of AI to identify malaria hotspots and optimize interventions for maximum impact. The map-based mobile app conveys the AI strategies to field workers as simple instructions, ensuring thorough implementation. 

To determine the population density in different areas, Zzapp uses machine vision to identify houses and other structures from satellite imagery. Topographical maps as well as satellite images are analysed to predict the presence of water bodies suitable for mosquito reproduction. 

Through a combination of these data, the malaria transmission hotspots are flagged and prioritized, and appropriate interventions are matched for each location. To account for seasonal weather patterns when timing interventions targeting water bodies, Zzapp – in collaboration with IBM Watson’s AI and Data Science Elite Team – has developed a weather analysis module that predicts the abundance of water bodies based on weather data, allowing Zzapp to better time interventions, and more accurately determine the resources required to implement them. 

Translating data into action 

The Zzapp system effectively conveys detailed AI strategies to large teams of field workers, as well as verifying their implementation. A web dashboard is used to delineate the areas field workers will be tasked with covering. A map-based mobile app then guides workers through the two stages of the operation: mapping the areas for water bodies and treating these water bodies at the correct intervals. The app highlights their path on the map display to allow them to keep track of the coverage achieved. The app reports GPS location, a photo, size, and other characteristics of each identified water body. 

Once the area has been mapped, the app automatically keeps track of the spraying schedule to ensure that no larvae get a chance to develop in the water bodies. The app requires no network connectivity, storing all data on the worker’s mobile device and syncing to the dashboard as soon as internet connection is available, allowing operation managers to keep track of daily progress. 

The dashboard in turn shows both high-level information such as neighbourhoods sprayed and coverage achieved, as well as details about the individual water body, such as how many times it was sprayed, when, and by whom. This empowers managers to identify any issues early and find appropriate solutions.

Outcome from a trial using Zzapp by AngloGold Ashanti Malaria Control Program 

In 2018, a randomized control trial by AGAMal, a leading Ghanaian malaria control organization, demonstrated the value of the app in identification of mosquito breeding sites; it detected 28% more water bodies compared to conventional methods, with an estimated coverage of over 90% in built-up areas. In 2020, a large-scale larviciding operation in Obuasi used the app and reduced the mosquito population by over 60% in as little as three and a half months and at a mere $0.2 per person protected, compared to the approximate cost of $5 for house spraying.

This innovation provides a perfect example of how innovative approaches and AI algorithms may be used to improve mosquito control operations and provide AI-based solutions to collaborators in the field.

Matt RomneyAI and Malaria Control: an Exciting Future Ahead