Medical AI Models Rely on Shortcuts That Could Lead to Misdiagnosis of COVID-19 itnonline.com - get the latest breaking news, showbiz & celebrity photos, sport news & rumours, viral videos and top stories from itnonline.com Daily Mail and Mail on Sunday newspapers.
University of Washington researchers discovered that AI models ignored clinically significant indicators on X-rays and relied instead on characteristics such as
‘Lazy’ AI: UW researchers find that tech can misdiagnose COVID-19 by taking shortcuts
June 3, 2021 at 12:30 pm
Left to right: University of Washington researchers Alex DeGrave, Su-In Lee and Joseph Janizek. (University of Washington Photo)
The future use of artificial intelligence in medical contexts could be beneficial in improving efficiency, but a new University of Washington research study published in Nature found that AI relied on shortcuts rather than actual medical pathology in diagnosing COVID-19.
The researchers examined chest X-rays used to detect COVID-19. They found that the AI relied more on specific datasets than significant medical factors to predict whether a patient had contracted the virus.
AI tools found using shortcuts to diagnose Covid-19 theiet.org - get the latest breaking news, showbiz & celebrity photos, sport news & rumours, viral videos and top stories from theiet.org Daily Mail and Mail on Sunday newspapers.
E-Mail
Artificial intelligence promises to be a powerful tool for improving the speed and accuracy of medical decision-making to improve patient outcomes. From diagnosing disease, to personalizing treatment, to predicting complications from surgery, AI could become as integral to patient care in the future as imaging and laboratory tests are today.
But as University of Washington researchers discovered, AI models like humans have a tendency to look for shortcuts. In the case of AI-assisted disease detection, these shortcuts could lead to diagnostic errors if deployed in clinical settings.
In a new paper published May 31 in
Nature Machine Intelligence, UW researchers examined multiple models recently put forward as potential tools for accurately detecting COVID-19 from chest radiography, otherwise known as chest X-rays. The team found that, rather than learning genuine medical pathology, these models rely instead on shortcut learning to draw spurious associations between me