Exploring Machine Learning to Map Yellow Fever Risk

PAHO’s Health Emergencies Department and UNICEF’s Office of Innovation joined forces to explore the potential of machine learning to predict areas of yellow fever incidence in the Americas and assess the importance of geographic and environmental factors, employing PAHO’s seminal work and unique datasets. Increasing availability of digital data and development of Machine Learning techniques, and Artificial Intelligence in general, has proven extremely useful in understanding patterns of disease and health dynamics in populations. This trend of popular field of research called digital epidemiology uses digital data collected and generated inside and outside the public health system.

How do we keep socio-economic estimates up-to-date?

Accurate estimates of population demographics are vital in order to understand social and economic inequalities, and are essential to UNICEF’s work, as knowing where the most vulnerable children and families live is important for resource allocation. Traditional methods of collecting such estimates, however, are both time-consuming and expensive. Here, we explore a complementary approach. 

Why Context Is King For Unicef's Innovative Life-Saving Solutions

A few years ago UNICEF met with a group of about 40 entrepreneurs in Silicon Valley looking for creative solutions to some of the most pressing problems facing people in the poorest parts of the world. But after a week of brain-storming ideas, it was clear that they were on the wrong track. This week of co-creation resulted in solutions like subscription-based smartphone health apps that would cost someone living in poverty an entire day’s income, or water purifying solutions that would have to be delivered on a large truck to remote villages that were only accessible by footpaths.

Drones vs mosquitoes: Fighting malaria in Malawi

In the middle of a muddy field next to a reservoir in north-western Malawi, a team of scientists are hard at work. Boxes of equipment lie scattered around a patch of dry ground, where a scientist programmes an automated drone flight into a laptop perched on a metal box. The craggy peak of Linga Mountain (‘watch from afar’ in the local language) looms over the lake, casting its reflection in the water.

With a high-pitched whirr of rotor blades, the drone takes off and starts following the shoreline, taking photos as it goes. Once the drone is airborne, the team switch from high-tech to low-tech mode. They collect ladles, rulers and plastic containers and squelch through mud until they reach the water’s edge.

The scientists measure the water depth with a ruler and carefully ladle water into the containers. Using a mobile app, they record the GPS location of each sample. Back on dry ground, they count the number of mosquito larvae in each container.