CMU COVID-19 Data Capture Project Adds Mask Usage, Testing Questions

CMU COVIDcast

Carnegie Mellon University is tracking mask use across the country, along with testing availability for COVID-19 and the test results, as part of a symptom survey distributed each day.

The university's Delphi research group, which focuses on epidemiological forecasting, has been collecting data daily through Facebook since April from volunteers on self-reported COVID-19 symptoms. Now the tiny survey has added questions about how respondents are addressing public health recommendations, such as mask use, and whether they're getting COVID-19 testing when they want it. More than a million U.S. residents have responded since the university's expanded survey was introduced at the beginning of September.

The aggregated results are updated each day and posted to the institution's COVIDcast website, accessible by anybody. The data with a greater level of detail is also shared with health researchers. Delphi uses the results to produce localized forecasts of COVID-19 activity.

According to Alex Reinhart, assistant teaching professor in the Department of Statistics and Data Science and a member of the Delphi group, monitoring mask use and how it changes over time and in different counties will help researchers better understand where the virus is most likely to spread and show what activities prove most effective in preventing its spread.

In New England, a region "hit hard" by the first wave of COVD-19, the survey showed that most people wear masks — consistently around 95 percent in Boston, for example. However, the lowest rates of mask use are in the central United States, such as North Dakota and South Dakota, and those regions are showing a rapid rise in case rates.

"Our survey doesn't replace official public health reporting on COVID testing and case counts, but it can provide insights not available any other way," said Reinhart. "By providing these signals to the public, we hope to give researchers, public health officials and journalists the information they need to form a more complete picture of the pandemic."

The CMU work isn't the only COVID-19 data collection taking place across the country. The CDC uses forecasting from 29 different modeling projects. The University of Maryland is running an effort similar to CMU, in that it also uses a daily survey distributed by Facebook to gather international data on the pandemic. As part of the Data for Good program, the social media company distributes the surveys to a selection of its users each day. Facebook itself doesn't gather the information; the universities run the surveys off of Facebook and manage the findings.

About the Author

Dian Schaffhauser is a former senior contributing editor for 1105 Media's education publications THE Journal, Campus Technology and Spaces4Learning.

Featured

  • interconnected cloud icons with glowing lines on a gradient blue backdrop

    Report: Cloud Certifications Bring Biggest Salary Payoff

    It pays to be conversant in cloud, according to a new study from Skillsoft The company's annual IT skills and salary survey report found that the top three certifications resulting in the highest payoffs salarywise are for skills in the cloud, specifically related to Amazon Web Services (AWS), Google Cloud, and Nutanix.

  • a hobbyist in casual clothes holds a hammer and a toolbox, building a DIY structure that symbolizes an AI model

    Ditch the DIY Approach to AI on Campus

    Institutions that do not adopt AI will quickly fall behind. The question is, how can colleges and universities do this systematically, securely, cost-effectively, and efficiently?

  • minimalist geometric grid pattern of blue, gray, and white squares and rectangles

    Windows Server 2025 Release Offers Cloud, Security, and AI Capabilities

    Microsoft has announced the general availability of Windows Server 2025. The release will enable organizations to deploy applications on-premises, in hybrid setups, or fully in the cloud, the company said.

  • digital brain made of blue circuitry on the left and a shield with a glowing lock on the right, set against a dark background with fading binary code

    AI Dominates Key Technologies and Practices in Cybersecurity and Privacy

    AI governance, AI-enabled workforce expansion, and AI-supported cybersecurity training are three of the six key technologies and practices anticipated to have a significant impact on the future of cybersecurity and privacy in higher education, according to the latest Cybersecurity and Privacy edition of the Educause Horizon Report.