A research team from across the University of Michigan has been named the grand prize winner in the American Heart Association COVID-19 data challenge.
Brahmajee Nallamothu, M.D., an interventional cardiologist and a professor at the Michigan Medicine Frankel Cardiovascular Center, and Ji Zhu, Ph.D., a professor of statistics and associate chair of the department, led the winning team’s analysis of national data for risk factors of COVID-19 infection.
Nallamothu and Zhu are both members of the Michigan Integrated Center for Health Analytics and Medical Prediction (MiCHAMP) – a “big data” analytics group sponsored by the U-M Department of Internal Medicine and the Michigan Institute for Data Science (MIDAS).
In particular, the MiCHAMP team made up of multiple students in the Department of Statistics studied the status of COVID-19 cases in college and university counties, timed with the start of the fall semester. They found holding in-person classes was associated with greater numbers of new confirmed COVID-19 cases in the local county, while reopening online or in a hybrid mode was associated with a lower number of new confirmed COVID-19 cases.
“Our findings could provide principled guidance on the upcoming winter/spring 2021 semesters,” say Nallamothu, Zhu and colleagues. “For example, due to the impact of enrollment to its neighboring area, regions with universities and colleges should expect a spike of the confirmed cases in the first few weeks after students return to campus.”
The MiCHAMP team is now preparing its analyses for peer-reviewed publication. Additional team members include Yang Li, Cheng Ma, Weijing Tang and Xuefei Zhang, all Ph.D. students in statistics. They combined medical and statistical knowledge to take on this data project about the COVID-19 pandemic.
"The COVID-19 pandemic has impacted everyone's lives and many of us are now studying and working from home. As a Ph.D. student in the Department of Statistics, I am fortunate to be able to use my knowledge to help combat the current pandemic,” Tang says.
Zhang says a cross-disciplinary collaboration like this brings new insights and approaches to the table. “It was a very rewarding learning experience for all of us.”
The American Heart Association data challenge focused on understanding the relationships between COVID-19 and other health conditions, health disparities and social determinants of health that may bring a higher burden of illness or mortality.
A panel of 26 U.S.-based data science and public health experts judged the challenge. Researchers connected their own data with datasets hosted on BurstIQ’s Research Foundry and the American Heart Association Precision Medicine Platform. In addition, sponsor Hitachi Vantara provided more than $100,000 to support the challenge.
“These data challenge projects are providing much-needed insights into the relationships between COVID-19 and underserved and vulnerable communities. Each exploration of these relationships helps drive the science to provide not only knowledge, but potential solutions.” said Jennifer Hall, Ph.D., chief of data science and co-director of the Institute for Precision Cardiovascular Medicine for the American Heart Association.