Using a custom artificial intelligence algorithm called CV19-Net, a UW research team dug into a vast database of COVID-19 chest X-rays to show its method could identify pneumonia caused by COVID-19 at a sensitivity of 88%—a rate that investigators were able to prove is better than the human eye, according to Guang-Hong Chen, PhD, professor of medical physics and radiology. The team is currently determining how to use the new technology to help health care workers identify COVID-19 pneumonia in just minutes. Funded in part by the Wisconsin Partnership Program, the work may help to create a more universal algorithm for COVID-19 screening, even in people with mild or no pneumonia findings.
Learn more about how an AI algorithm recognizes COVID-19 pneumonia