DataRobot Intros ContagionNET

March 9, 2021

ContagionNET is a not-for-profit initiative designed to solve the current COVID-19 pandemic and return life to normal in 60 days, while protecting us from future pandemics. ContagionNET combines at-home affordable antigen checks, anonymous data collection, and AI to dramatically reduce the spread of COVID-19 without sacrificing freedom or privacy. Through frequent, affordable, and anonymous at-home screening as part of community- or organizational-based surveillance programs, users can understand their risk of contagiousness and keep their friends, family, and community safe.

Modeling research (Goyal) has shown that, of those infected, an estimated 20% with the highest viral load cause 80% of new infections. On average, people who test positive for COVID-19 receive their results 7-10 days after initial exposure. Peak viral load – the period when people are most infectious – is within 3-5 days of exposure, and emerging patient studies (Lee) support that individuals with the highest viral loads are the most contagious. That means that by the time people receive their test results, they have likely infected their closest contacts and beyond. Further, questions around immunity length and COVID-19 variants remain largely unanswered.

ContagionNET will provide a suite of tools, including at-home antigen checks and a digital platform, to help identify the most contagious areas in a community and encourage people to take preventative action. The goal is to identify people earlier than traditional testing (i.e., when they are most infectious) to disrupt the chain of transmission. ContagionNET can also predict how many people need to participate on a county-by-county basis by measuring the impact of different participation levels and testing frequency. This specific and localized guidance will allow those with the highest viral load to self-quarantine earlier in the disease lifecycle, preventing further spread of COVID-19.

“The reality is that those most likely to spread COVID-19 aren’t usually aware they are contagious,” said Sally Embrey, DataRobot’s VP of Public Health and Health Technologies. “With the proliferation of frequent, easy-to-use at-home antigen checks, ContagionNET is poised to inform the most contagious of their risk and help them make lifestyle modifications that will significantly reduce spread of the virus.”

Antigen checks are low-cost, simple, and readily available. Though they don’t replace diagnostic tests, they are ideal for identifying high levels of contagion, and are critical for reducing spread of the virus as we wait for the entire U.S. population and globe to be inoculated. There is also broad support for these types of tools; a new national study conducted by COVID Collaborative and Harvard T.H. Chan School of Public Health found that a majority (86%) of Americans are in support of using at-home antigen tools to stop the spread of COVID-19. The ability to rapidly deploy this technology also represents a critical national defense against future pandemics and new virus variants. While vaccines take many months to develop, rapid antigen checks can be developed in a matter of weeks.

“Half a million people in the U.S. didn’t need to die. It’s important we learn from COVID-19 so we never find ourselves in this position again,” said Jeremy Achin, CEO and Co-Founder, DataRobot. “With ContagionNET, we built – from the ground up – a solution that can serve as a center of gravity for pandemic preparedness. ContagionNET preserves individual freedom and privacy while allowing us to both stop the current pandemic and prevent future pandemics from ever occurring.”

Since early 2020, DataRobot has been deeply engaged in the COVID-19 pandemic response, dedicating significant resources to solving the most important data science problem in the world and producing rapid, life-altering solutions. In collaboration with the U.S. government, DataRobot’s COVID-19 forecasting increased the effectiveness and diversity of multiple vaccine trials by helping manufacturers select the right participants and prioritize enrollment in the highest risk locations over each vaccine trial period. DataRobot has since worked with government officials to help fight the pandemic in other ways, particularly using modeling to improve testing distribution, equity, and diagnostic reporting. The culmination of this work has informed its approach to ContagionNET.

ContagionNET will launch pilot programs in key locations across the country. The initiative is looking for partners across state and local governments, public health officials, universities, manufacturers, and more that can support its mission and assist with rollout.