A research team from Rensselaer is working on developing AI tools to identify high risk COVID-19 patients.
The U.S. death toll for COVID-19 has exceeded 200,000 and continues to grow. Doctors need better screening and treatment options for patients with preexisting conditions like diabetes and lung disease.
The National Institutes of Health (NIH) announced a new grant to fund research in the rapid development and integration of a collection of artificial intelligence algorithms to meet this critical need.
These algorithms will analyze health data — like vital signs and chest computed tomography images — to help healthcare providers assess the disease’s severity and identify treatment options.
AI Lends a Helping Hand
See also: Tech Giants Back National Research Cloud
“Screening out the high-risk patients who may need intensive care later, and monitoring them more closely to provide early intervention, may help save their lives,” says Pingkun Yan. The assistant professor of biomedical engineering and member of the Center for Biotechnology and Interdisciplinary Studies (CBIS) at Rensselaer leads a research team determined to find a solution.
“My group has been focusing on using artificial intelligence and deep learning to analyze medical imaging data with an emphasis on translating the technology from benchside to bedside. This focus built a solid foundation for us. When the crisis emerged, we worked with our clinical collaborator at Massachusetts General Hospital, to quickly identify clinical needs and start working on a solution.”
While current AI tools can determine the severity of lung infections that result from COVID-19, the tools cannot assess underlying conditions. Yan’s team will create a framework of algorithms that can integrate patient information to guide physician assessments. Data will include:
- Patient demographics
- Vital signs
- Bloodwork results
- CT scans
The team plans to incorporate AI algorithms from Yan’s previous project into this research. Those algorithms determined patient risk for heart disease.
“Rensselaer expertise in artificial intelligence, as exhibited by Professor Yan’s work, makes rapid response to the COVID-19 pandemic possible,” says Deepak Vashishth, the director of CBIS. “New and improved tools, like the one targeted here to identify high-risk COVID-19 patients, are essential in this public health crisis.”
