Big Data Analytics Show COVID-19 Spread, Outcomes by Region

September 21, 2020 - With the COVID-19 pandemic impacting US communities in different ways, research and provider institutions have increasingly turned to big data analytics tools to track and monitor the virus’s spread and its effect on patient outcomes.

For more coronavirus updates, visit our resource page, updated twice daily by Xtelligent Healthcare Media.

A team from Mayo Clinic recently introduced a tracking tool that features the latest COVID-19 data for every county in all 50 states and Washington, DC.

The tool, the US Coronavirus Map: What Do the Trends Mean for You?, is an interactive map included in Mayo Clinic’s COVID-19 online resource center. The map represents key data and trends in an easy-to-use format, and displays figures like the total number of cases in each county and state, new cases per day, positive test rate and fatality rate, presented with trends over time.

"COVID-19 infections continue to rise and fall in many areas of the country, and information at the local level on the prevalence of disease and future trends are more important than ever to help people prevent the spread of infection," said Henry Ting, MD, a cardiologist, health services researcher and educator at Mayo Clinic.

READ MORE: How Big Data Analytics Models Can Impact Healthcare Decision-Making

"This interactive map, enriched with Mayo Clinic expertise, is designed to be easy to use, with the most current data available and correlated with the latest Mayo Clinic guidance."

To create the map, data scientists developed content sources, validated information, and correlated expertise for the tracker, all of which will be enhanced with more real-time data and predictive analytics.

"From our experience in treating patients and talking with them about their concerns, we believe there's a need for easy-to-access local data on COVID-19 trends and what it means," Ting said.

"This tracker enables people to see ongoing and emerging hot spots across the U.S. ― where they live, where their family and friends live, and where they might travel, along with information from Mayo Clinic experts about risk, diagnoses and treatments."

The map is part of Mayo Clinic’s COVID-19 resource center, which provides guidance on properly wearing a mask, social distancing, handwashing, and cleaning and disinfecting surfaces.

READ MORE: How Big Data Analytics Can Mitigate COVID-19 Health Disparities

The center also features a self-assessment tool for users to determine whether they have symptoms and should seek medical care, as well as information for how COVID-19 survivors can donate plasma to help other patients.

This new map adds to Mayo Clinic’s COVID-19 response. In March, the organization announced an early test to detect COVID-19 infection, and Mayo Clinic Laboratories has processed over 1.4 million COVID-19 tests to date. Throughout the pandemic, Mayo researchers and experts have also provided expertise to guide the public health response, and clinical staff have been on the frontlines providing care for patients infected with the virus.

Mayo Clinic expects that this new COVID-19 tracking tool will provide key insights into the spread and impact of the virus in specific counties.

"Much remains to be learned about the COVID-19 virus and how it affects a person's health in the short term and longer term," said Ting. "It's vital that people become more aware of local information, what the trends are, and take appropriate action to protect their health and the health of others."

At West Virginia University (WVU), researchers are also using big data analytics tools to measure COVID-19’s impact in particular areas of the country – and in particular patient populations.

READ MORE: Big Data Analytics Dashboard Shows Greatest Risk Factors for COVID-19

A team is using machine learning to study how being a coal miner impacts COVID-19 outcomes, as well as the effect vaping, smoking, and having a chronic lung condition influence how COVID-19 patients fare.

Using demographic and health data associated with COVID-19 patients in West Virginia, researchers will develop a machine learning model that predicts patients’ outcomes based on multiple variables drawn from the WVU COVID-19 registry.

“One of the features of machine learning is that it can develop personalized predictive models,” said Larissa Casaburi, an associate professor of radiology at WVU School of Medicine. “It’s precise medicine. It’s a novel approach to improve patients’ care, and there's a lot of research interest in it.”

The model will determine whether patients have asthma, chronic obstructive pulmonary disease, or other lung conditions. The tool will appraise CT scans of patients’ lungs and will also take into account whether individuals have chronic lung disease, whether they smoke or vape, and whether they have worked in a coal mine and other factors.

Using the machine learning algorithm, researchers will be able to more precisely determine patients’ outcomes.

“The artificial intelligence will make the analysis more accurate than traditional statistical models,” Casaburi said.

Researchers also noted that West Virginia is well-suited to test the impact of these factors in COVID-19 patients. West Virginia has a large population of coal miners, and the state is tied with Maine for the highest prevalence of asthma. COPD is also prevalent here – in 2011, 8.9 percent of West Virginians had been diagnosed with the disease.

“West Virginia is uniquely positioned to test our hypothesis, mainly because of the high percentage of smokers here,” Casaburi said. “Approximately 25 percent of the population has a history of smoking.”

As the pandemic continues, organizations will continue to develop big data analytics tools to advanced individualized care for COVID-19 patients, rather than taking a one-size-fits-all approach.