COVID-19 Claims Enhance Real-Time Data at the County Level

Change Healthcare and Carnegie Mellon University’s Delphi Research Group have enhanced Delphi’s COVIDcast real-time data stream with COVID-19 claims information.

Since April, Delphi has been collecting real-time data on self-reported COVID-19 symptoms and other disease indicators nationwide. This county-level information is updated continuously and shared with both the public and health researchers. Now, researchers behind the COVIDcast effort are taking the service a step further by adding de-identified COVID-19 claims from Change Healthcare to their combination of survey, testing, and mobility data.

"Tracking and forecasting the spread of a novel disease such as COVID-19 is a challenging task that requires new types and sources of data," said Ryan Tibshirani, an associate professor of statistics and co-director of Delphi.

"We are always evaluating our data streams and looking at ways of filling gaps in our knowledge. Change Healthcare has stepped up in the biggest way possible to give us crucial information for understanding the current state of the pandemic. We are extremely appreciative of their contributions to our effort."

Carnegie Mellon leverages its expertise in machine learning, statistics, and data science, as well as its partnership with the CDC, to offer a more complete and real-time picture of COVID-19 than previously possible. The Delphi Research Group aims to advance the theory and practice of epidemic forecasting.

Enhanced with Change Healthcare’s de-identified claims, COVIDcast helps researchers better understand the pandemic’s impact at the community level by providing comprehensive, geographically detailed, and continuously updated indicators of pandemic activity.

Understanding the impact of pandemic on individual communities can help researchers learn patterns and identify trends that will enable providers to improve patient treatment within each community. The data used by COVIDcast is de-identified in accordance with HIPAA privacy regulations.

"Delphi group's vision is to make epidemiological forecasting as universally accepted and useful as weather forecasting," said Tim Suther, senior vice president of data solutions at Change Healthcare.

"The addition of de-identified COVID-19 claims from Change Healthcare allows COVIDcast to present a more complete, multi-dimensional picture of the pandemic and its impact."

Throughout the pandemic, the healthcare industry has leveraged both real-time and county-level data to better grasp trends and patterns in COVID-19 spread, and to reduce the virus’s transmission.

In March 2020, a group of private sector organizations partnered to form the COVID-19 Healthcare Coalition, a collaborative effort that aims to provide real-time data analytics to those on the frontlines of the outbreak.

“Applying real-time data analytics and best practice guidance to a pandemic can flatten the curve of infection and change its course, as seen with Ebola and H1N1,” said Dr. Jay Schnitzer, MITRE’s chief technology and medical officer and member of the COVID-19 Healthcare Coalition.

“The business and research communities have mobilized to address COVID-19 and give this data analysis to the healthcare system leaders and public health officials to make evidence-based decisions that can save lives.”

County-level data has also provided healthcare organizations with a clearer view of how the pandemic is impacting different parts of the country. A recent report from the Commonwealth Fund showed significant racial and ethnic disparities in care, with the virus disproportionately affecting black and Hispanic populations.

“Troubling racial inequalities have emerged in the COVID-19 pandemic; city and state health departments have raised alarms about the impact on communities of color,” Laurie Zephyrin, MD, David C. Radley, Yaphet Getachew, Jesse C. Baumgartner, and Eric C. Schneider, MD wrote in the report.

“Not long after the virus started spreading, counties with relatively larger black populations faced higher case counts, higher COVID-19-related mortality, and a faster pace of progression compared to counties with a lower share of black people.”

As the pandemic wears on, data collected quickly and at a more granular level will help inform healthcare leaders about best practices and mitigation strategies.