Rensselaer Polytechnic Institute is developing an artificial intelligence algorithm that can extract health data from computed tomography scans to improve screening for COVID-19.
And a new 12-month, $200,000 grant from the National Institutes of Health will help America’s first technological research university quickly finish and integrate a series of such AI models into clinical use, according to a July 29 announcement.
Project leader Pingkun Yan, an assistant professor of biomedical engineering at RPI, said that the algorithms will analyze various pieces of information, including CT images and vital signs, to help clinicians determine disease severity and predict patient outcomes.
“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,” Yan added in the Wednesday statement.
While many existing algorithms fail to account for comorbidities during screening, Yan said his team will incorporate such information, including scan data to assess lung function, demographic information, vital signs and laboratory blood tests.
Many imaging societies, including the American College of Radiology, have urged physicians to avoid using CT as a first-line tool to screen patients during the pandemic. Other countries, including hard-hit Northern Italy, however, have leaned heavily on the modality.
Yan is among the latest in a long line of projects harnessing the power of AI to spot people at higher risk for the novel virus.
“It is tremendously important to me and my team that we can contribute our knowledge and skills to fight the COVID-19 pandemic,” Yan said. “It is our way to answer, ‘Why not change the world?’ — the unofficial Rensselaer motto.”
Massachusetts General Hospital is also partnering with RPI to bring this project to fruition.