Microsoft Premonition could help predict epidemics before they happen

The advanced forecasting system leverages a vast suite of technologies that could enable agencies to predict the next epidemic similar to the way we forecast the weather, per Microsoft.

microsoft premonition

Image: Microsoft

Artificial intelligence (AI) is playing an increasingly integral role in thwarting catastrophe around the globe. Researchers are using AI models to more aptly predict and prevent wildfires in the western US. Others are applying advanced algorithms to potentially forecast earthquakes and aftershocks. During the coronavirus pandemic, an AI model identified an existing rheumatoid arthritis treatment that could be repurposed to treat patients with COVID-19. On Tuesday, Microsoft released an article outlining an ambitious plan that would enable researchers to predict epidemics "like the weather."

The strategy is based on the capabilities of Microsoft Premonition system; a vast suite of technologies including AI, predictive analytics, robotic sensing, and more. In tandem, these enable Premonition to function as a sophisticated early warning system, forecasting the evolution and dispersal of viruses and microbes as well as animals that carry diseases such as mosquitos, per Microsoft.

SEE: COVID-19 workplace policy (TechRepublic Premium)

By monitoring biomes similar to the way researchers analyze the weather, the company postulates that it could be possible to detect outbreaks earlier in their evolution before becoming larger epidemics. This system could set in motion a proactive approach to epidemics as opposed to a reactive strategy used to contain incidents after the fact.

"Microsoft Premonition changes the paradigm from reacting to known pathogens to continuously looking for them as they evolve," said Ethan Jackson, senior director of Microsoft Premonition, in a press release. "These signals could help us spot potential threats earlier, respond faster and develop new interventions before outbreaks occur."

Diseases that are transmitted to humans from animals, also known as zoonotic diseases, include Ebola, HIV, West Nile virus, and COVID-19. In recent years, these zoonotic diseases have taken tolls on communities around the globe; most notably being the coronavirus pandemic. In July, the UN released a report predicting an increase in zoonotic disease due to unsustainable farming practices, wildlife exploitation, and climate change.

Harris County, TX served as the location for Project Premonition, an initial deployment that would evolve into Microsoft Premonition. In the release, Microsoft details the emergence of the Zika virus in 2016, explaining that a team of researchers had been "researching new monitoring approaches for about a year" before the arrival of the disease in the Americas.

Using early robotic smart traps, which Microsoft described as resembling "scale models of circular, high rise condos," the team was able to attract, capture, and autonomously identify mosquitoes; empowering health officials with previously unavailable data streams, per the release. As part of an expanded partnership, Microsoft and Harris County Public Health are now "building one of the most advanced biothreat detection networks."

"Everything we do now in terms of mosquito treatment is reactive – we see a lot of mosquitoes, we go spray a lot of mosquitoes," Douglas E. Norris, an entomologist who worked on the project, in a press release. "Imagine if you had a forecasting system that shows, in a few days you're going to have a lot of mosquitoes based on all this data and these models – then you could go out and treat them earlier before they're biting, spray, hit them early so you don't get those big mosquito blooms which then might result in disease transmission."

Furthermore, Premonition allows public health agencies to more aptly gauge intervention efficacy as well as the "costs of varying approaches." The sensing platform will allow Premonition to capture and analyze data about small and even microscopic threats, per Microsoft.

"All of the sensor networks that we have today–networks that do things like collect data to predict weather, collect data about the power grid so that we can load balance it, collect information about what traffic is doing so that we can predict it–all of those sensor networks, which are really hundreds and hundreds of millions of sensors–can't see these important species," Jackson said in the press release.

"These life forms we're talking about are invisible to basically all of those sensors that we've deployed across the globe. And that's pretty incredible when you think about it, that we have such a huge blind spot about what's in the environment," Jackson continued.

SEE: Big data's role in COVID-19 (free PDF) (TechRepublic)

At the peak of Zika transmission in 2016, the smart traps situated throughout Harris County were able to identify and "selectively capture relevant mosquitoes" with approximately 90% accuracy, according to Microsoft. With the latest Microsoft Premonition deployment, Harris County will have "continuous biological situational awareness," according to Jackson.

"So, they should be able to look at a map and see in real time what is happening now. Which, from the weather analogy, just doesn't exist today. A 24-hour forecast allows them to plan early for specific interventions in the environment," Jackson said.

As part of the partnership, the team will also look at emerging pathogens using environmental samples, "which we now know is especially important for diseases like COVID-19," said Dr. Umair Shah, executive director of Harris County Public Health, in the press release.

Also see