TERRE HAUTE, Ind. (Inside INdiana Business) – A Rose-Hulman Institute of Technology professor and three students are working to improve the accuracy and response time of a new COVID-19 screening procedure created by scientists at 12-15 Molecular Diagnostics in Connecticut. The school says the team is applying machine learning, artificial intelligence and modeling to determine if the saliva-based test could be safer, cheaper and more easily disposed.
Rose-Hulman says the testing procedure, called Veralize, is still in development and undergoing clinical testing. If successful, the school says the device will provide coronavirus test results in approximately 20 minutes.
“Our team has joined at the very important time in this project,” says Dr. Michael Jo, assistant professor of electrical and computer engineering. “We are working on constructing the first principle by simulation and to improve their pattern recognition of their test response.”
Rose-Hulman students Daniel Su, Xingheng Lin and Hailey Heidecker are working with 12-15 Molecular Diagnostics Chief Executive Officer Dr. Saion Sinha and Chief Technology Officer Dr. Ewa Kirkor to improve the machine learning framework to improve test response recognition.
The institute says 12-15 Molecular Diagnostics is currently doing real patient testing against SARS-CoV-2, the virus that causes COVID-19, in hopes of gaining U.S. Federal Drug Administration certification. Rose-Hulman says a recent product demonstration from its East Coast partners confirmed that saliva testing could determine a result quickly and accurately.
“The students’ modeling and machine learning work, under guidance of Dr. Jo and with our collaboration, will help us achieve a better understanding of the sensing characteristics within our project,” said Kirkor.
Additionally, Kirkor says the team’s work will also help formulate requirements, design and building of a prototype for detection and differentiation among organisms.