Researchers Use AI to Predict Severe COVID-19-Related Illness

August 11, 2020 - NIH is funding a project that will use artificial intelligence to identify children at risk of Multisystem Inflammatory Syndrome in Children (MIS-C), an illness believed to be a severe complication of COVID-19.

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

Most children exposed to COVID-19 develop only mild symptoms. However, some go on to develop MIS-C, a severe and sometimes fatal inflammation of the organs and tissues, including the heart, lungs, kidneys, eyes, brain, and skin. The new effort will aim to encourage studies of genetic, immune, viral, environmental, and other factors that influence the severity of COVID-19 cases and the chances of developing MIS-C.

NIH will award up to $20 million to successful research proposals over four years.

“We urgently need methods to distinguish children at high risk for MIS-C from those unlikely to experience major ill effects from the virus, so that we can develop early interventions to improve their outcomes, ” said Diana W. Bianchi, MD, director of NIH’s Eunice Kennedy Shriver National Institute of Child Health and Human Development (NICHD).

The NICHD-led project, called Predicting Viral-Associated Inflammatory Disease Severity in Children with Laboratory Diagnostics and Artificial Intelligence (PreVAIL kIds) is part of NIH’s Rapid Acceleration of Diagnostics (RADx) initiative. The RADx initiative seeks to speed innovation in the development, commercialization, and implementation of technologies for COVID-19 testing.

The effort is a national call for scientists and organizations to bring their innovative ideas for new COVID-19 testing approaches and strategies. Funded projects may also include new applications of existing technologies that make tests easier to use, easier to access, and more accurate.

“We expect that RADxUP will foster continued use of common data sets around the pandemic, and create a model about how this can be done well. The initiative can serve as a data resource that people can use for years going forward,” Lis Nielsen, PhD, director of the Division of Behavioral and Social Research at the National Institute on Aging (NIA), told HealthITAnalytics.com.

PreVAIL kIds will aim to encourage the development of cutting-edge approaches for understanding the underlying factors influencing the spectrum of conditions that may occur in children and youth infected with COVID-19. These range from no symptoms at all to fever and cough, abdominal pain and diarrhea, and inflammation of the coronary arteries. The goal of the initiative is to understand the range of symptoms of COVID-19 and factors leading to MIS-C.

Studies funded through the PreVAIL kIds will evaluate genes and other biomarkers in COVID-19 pediatric cases, as well as examine how the virus interacts with its host and how the immune system responds. Researchers will leverage artificial intelligence and machine learning to sort and categorize the data they acquire to understand the disease patterns they uncover.

The initiative will add to NIH’s many efforts to further combat and understand COVID-19 using innovative tools. The organization recently launched the Medical Imaging and Data Resource Center (MIDRC), which will use artificial intelligence and medical imaging to enhance COVID-19 detection and treatment.

The effort will be led by the National Institute of Biomedical Imaging and Bioengineering (NIBIB), and will work to create new tools that physicians can use for personalized therapies for COVID-19 patients.

“This program is particularly exciting because it will give us new ways to rapidly turn scientific findings into practical imaging tools that benefit COVID-19 patients,” said Bruce J. Tromberg, PhD, NIBIB Director. “It unites leaders in medical imaging and artificial intelligence from academia, professional societies, industry, and government to take on this important challenge.”