Machine Learning Powers COVID-19 Risk Assessment Dashboard

A team from Florida Atlantic University’s (FAU) College of Engineering and Computer Science is leveraging machine learning technology to build a COVID-19 knowledge base and risk assessment dashboard.

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

The project, conducted in partnership with FAU’s Schmidt College of Medicine, will use machine learning and social networks for COVID-19 modeling and risk evaluation. Researchers received a one-year, $90,000 National Science Foundation (NSF) RAPID project grant to fund this effort.

The RAPID: COVID-19 Coronavirus Testbed and Knowledge Base Construction and Personalized Risk Evaluation project will address the many discrepancies that exist in the context of the pandemic.

“COVID-19 is an evolving epidemic and there is little knowledge about its outbreak and spread patterns, or the impact of viral evolution, demography, social behavior, cultural differences, and quarantine policies regarding these outbreaks,” said Stella Batalama, PhD, dean of FAU’s College of Engineering and Computer Science.

“As the battle against COVID-19 continues, a deluge of information is being produced. As a result, the dramatic outbreak differences with respect to diverse geographies, regional policies, and cultural groups is raising confusion, contradictions, and inconsistencies in disease outbreak modeling.”

The team will build a knowledge base of COVID-19 to understand the correlations and roles that different factors play in predicting the spread of the virus. The technology will lead to the implementation of policies to mitigate the impact of the pandemic on public health.

“Academia, news agencies, and governments are continuously publishing advances in the understanding of the virus’ clinical pathologies, its genome sequences, and relevant administrative policies and actions taken,” said Xingquan (Hill) Zhu, PhD, principal investigator of the grant and a professor in FAU’s Department of Computer and Electrical Engineering and Computer Science.

“In addition, the public also responds to the changing environments through social media sites or other online sources, resulting in real-time social sensing opportunities. This is why a knowledge base of COVID-19 using machine learning is so crucial for us to model and understand the spread of COVID-19, and eventually mitigate the negative effects of the virus on public health, society, and the economy.”

The FAU project has two technical aims. First, researchers will build a knowledge base that includes information for modeling outbreak and mutation of COVID-19, which will serve as a benchmark for better understanding of the virus.

“The COVID-19 knowledge base uses graph/network to represent entities and their relationships. The entities are fully compatible to the Unified Medical Language System or UMLS standard for convenient knowledge sharing,” said Zhu.

“Supported by the knowledge base, the public will be able to employ information to estimate their infection risk level using social and behavioral information such as their family size, shopping patterns, and dining patterns, as well as local authority policies such as school, restaurant, and movie theater closures and night time curfews.”

Second, the team will develop multi-source deep neural network-based predictive tool to combine demographics policies, regional infections, and individual risk information for risk evaluation.

“They also will have access to demographic information such as population age, density and income, as well as health conditions like heart disease incidence, cancer prevalence, and substance misuse. Public health officials and the public-at-large also will be able to access regional virus conditions such as the number of infection cases in the area studied and infection rate,” said Zhu.

Since receiving the NSF grant in May, FAU researchers have made significant progress. The team has already implemented a knowledge base dashboard, as well as an infection and social sensing dashboard. The group is currently working on the risk estimation dashboard.

The FAU project adds to the many data visualization efforts that have come from researchers across the healthcare industry. The Parkland Center for Clinical Innovation (PCCI) recently developed a big data analytics dashboard to accurately identify communities at high risk for COVID-19 infection.

“These kinds of precise data insights will help us understand communities and populations at greatest risk to COVID-19 and how to prioritize and tailor community interventions in order to proactively manage current and future outbreaks or other community-wide interventions,” said Steve Miff, PhD, President and CEO of PCCI.

Additionally, a team from Southern Illinois University (SIU) have launched a data visualization tool that uses GPS information to show users the locations of known COVID-19 cases, while protecting the identities of individuals diagnosed with or exposed to the virus.

“This is by far the most critical requirement as without it, the utility for general public will be greatly reduced,” said Koushik Sinha, assistant professor in the School of Computing at SIU. “The tool will provide functionalities that we believe will be useful to both private individuals as well as health officials.”