Article: How Scientists Are Using Satellites to Predict Disease

Photo Source: Pexels

Mosquitos, fleas, and ticks spread disease worldwide, causing untold suffering and death. NASA, the military, and national health organizations have teamed up to build systems that can predict the time and location of disease outbreaks with information collected from space and on Earth. Getting a head start on disease outbreaks aids health authorities in applying mitigation strategies such as vaccines, bug nets, and insect control. Vector-borne diseases number over 100 and include infamous diseases such as malaria, yellow fever, bubonic plague, dengue fever, Lime disease, zika, and lesser-known ones such as West Nile and Eastern Equine Encephalitis. The World Health Organization (WHO) estimates that 17% of all human communicable diseases come from bug bites, resulting in over 700,000 deaths yearly. (who.int) Malaria alone infects 219 million people annually, with more than 400,000 succumbing to the disease.

Vector-borne diseases such as malaria cannot spread directly from person to person as the flu or measles can. Instead, an insect plays a crucial role in disease transmission by picking up the disease from an infected person and then giving it to someone else during a blood meal. Moreover, certain species of insects can only transmit certain diseases. For example, dengue fever and chikungunya (translated from the East African language, Kimakonde, meaning “to become contorted” with pain) get transmitted by two types of mosquitos—Aedes aegypti and Aedes albopictus, also called the Asian tiger mosquito, due to its distinct striped markings.

Predicting when a vector-borne disease will break out requires a wide variety of information. For any particular disease, a model needs to know the presence of the disease in people or other animals, if the right bug vectors exist to carry the disease, and if the right environmental factors to sustain a healthy lifecycle of the bugs. For example, mosquitos need 7-14 days of warm weather, proper habitat, and moisture to support their maturation from egg to adult mosquito.

Given the global reach of so many vector-borne diseases, gathering such data appears nearly impossible without the help of thousands of people reporting at all the locations where diseases could break out. Fortunately, NASA has deployed an earth-observing satellite called Terra. Terra, launched in 1999, circles the earth gathering information about the earth’s surface, including temperature, soil moisture, and pictures of the earth’s surface. Building from the data from Terra, a consortium of researchers from NASA, the US military, and national health groups formed to use this data and additional data sources to build predictive models for disease outbreaks.

One model called CHIKRisk predicts the outbreak of chikungunya. The model also uses weather data from NOAA, human population data from NASA’s Socioeconomic Data and Applications Center, disease data from ProMed, and vector bug data from the Walter Reed Biosystematics unit. Using artificial intelligence, the CHIKRisk model predicts chikungunya outbreaks three months in advance. (CHIKRisk app) The model provides detailed predictions across the globe.

Vector-borne diseases plague people worldwide. Startlingly, vectors such as mosquitos, fleas, and ticks transmit over 100 known diseases through bites, and nearly one in 10 people will suffer from a vector-borne illness this year. That translates to over 700,000 dying yearly, not to mention the suffering and loss of productivity. Many diseases, such as malaria, dengue fever, yellow fever, and zika, get transmitted through mosquito bites. In addition, different species of mosquito transmit various diseases. Public health officials and the military can better prepare for disease outbreaks with vaccinations (if available), mosquito nets, and insecticide applications. Still, they need predictive models of where the outbreaks will happen to use limited resources best. In collaboration with public health groups such as the Pan American Health Organization and the military, researchers at NASA have built models that take advantage of publicly available data from NASA and other organizations. The data collected from space and on the ground uses weather, topography, temperature, disease presence, and history to predict months out of the outbreak of chikungunya. More models are under development for predicting malaria, yellow fever, and zika. This demonstration of the power of analytics and diverse data sources to help protect public health shows how artificial intelligence can work for the good.

Dr. Smith’s career in scientific and information research spans the areas of bioinformatics, artificial intelligence, toxicology, and chemistry. He has published a number of peer-reviewed scientific papers. He has worked over the past seventeen years developing advanced analytics, machine learning, and knowledge management tools to enable research and support high-level decision making. Tim completed his Ph.D. in Toxicology at Cornell University and a Bachelor of Science in chemistry from the University of Washington.

You can buy his book on Amazon in paperback and in kindle format here.