The diagnosis algorithm was reportedly trained on data from more than 5,000 confirmed cases of COVID-19, the illness caused by the novel coronavirus from China. Researchers who developed the AI said it can distinguish between the virus and ordinary viral pneumonia from CT scans with up to 96 percent accuracy.
The diagnostic tool reportedly takes only 20 seconds to analyze a CT scan, a significant reduction from the five to 15 minutes it typically takes physicians to assess imaging data and make a diagnosis.
Read more here.
More articles on AI:
NewYork-Presbyterian-backed startup unveils ambient, autonomous voice assistant
IBM, Kaiser Permanente find combined AI, human expertise boosts mammogram readings
UCSF developing AI to speed prostate cancer diagnosis
