Carnegie Mellon Maps Offer More Data for COVID-19 Forecasting

Carnegie Mellon University has created five interactive maps intended to paint a more detailed picture of COVID-19 across the country and help in forecasting disease activity. The COVIDcast maps bring together real-time data on symptoms, doctor visits, medical tests and browser searches related to COVID-19, offering some unique insights into what's happening at the state, metropolitan area and county level.

COVIDcast map

Screenshot of CMU's COVIDcast as of April 24, 2020

For example, a national health system is providing statistics on patient visits to doctors and telemedicine visits, allowing CMU researchers to estimate how many patients in a given location are seeking medical attention for COVID-19 symptoms. Similarly, data from Google Health Trends provides an estimate of how often people are searching Google for topics related to COVID-19. And medical test maker Quidel is providing statistics on influenza tests, which are routinely ordered for people suffering COVID-19 symptoms in order to exclude flu as a diagnosis (and therefore can be indicators of possible COVID-19 activity), the university explained in a news announcement.

The researchers are also pulling data from Facebook and Google surveys asking people if they know anyone who is experiencing COVID-19 symptoms such as fever, cough, shortness of breath or difficulty breathing. Self-reported symptoms help CMU make estimates of disease activity, which the researchers have shown "are strongly correlated with test-confirmed cases of COVID-19," the university said.

"All of these signals are just rough indicators of COVID-19," noted Roni Rosenfeld, co-leader of CMU's Delphi Research Group and head of the university's Machine Learning Department, in a statement. "Any one data source may not be conclusive, but if multiple sources indicate the same thing, people can have greater confidence about what is happening or will soon happen in various locales."

COVIDcast was created by Carnegie Mellon's Delphi Research Group and COVID-19 Response Team, which includes a number of volunteer faculty, students and staff. The researchers expect to add more data sources over time; all Delphi estimates are available via a GitHub open API.

"COVIDcast leverages Carnegie Mellon's leadership in machine learning, statistics and data science, and builds upon our partnership with the Centers for Disease Control and Prevention in epidemic forecasting at a time when policymakers and healthcare providers are eager for more insights into the spread of COVID-19," commented CMU President Farnam Jahanian. "Our multidisciplinary team of researchers has worked tirelessly to bring together a variety of data sources to support informed decision-making throughout our global society."

About the Author

Rhea Kelly is editor in chief for Campus Technology, THE Journal, and Spaces4Learning. She can be reached at [email protected].

Featured

  • abstract pattern of shapes, arrows and circuit lines

    Internet2 Announces a New President and CEO to Step Up in October

    Internet2, the member-driven nonprofit offering advanced network technology services and cyberinfrastructure to the research and education community has completed its search, which began this past May, for a new president and CEO to take the helm.

  • shield with an AI microchip emblem hovering above stacks of gold coins

    AI Security Spend Surges While Traditional Security Budgets Shrink

    A new Thales report reveals that while enterprises are pouring resources into AI-specific protections, only 8% are encrypting the majority of their sensitive cloud data — leaving critical assets exposed even as AI-driven threats escalate and traditional security budgets shrink.

  • stack of gold coins disintegrates into digital particles against a dark circuit-board background with glowing AI imagery

    MIT Report: Most Organizations See No Business Return on Gen AI Investments

    A recent report out of the MIT Media Lab found that despite $30-40 billion in enterprise spending on generative AI, 95% of organizations are seeing no business return.

  • young man in a denim jacket scans his phone at a card reader outside a modern glass building

    Colleges Roll Out Mobile Credential Technology

    Allegion US has announced a partnership with Florida Institute of Technology (FIT) and Denison College, in conjunction with Transact + CBORD, to install mobile credential technologies campuswide. Implementing Mobile Student ID into Apple Wallet and Google Wallet will allow students access to campus facilities, amenities, and residence halls using just their phones.