Science
Medical AI models rely on shortcuts, can cause misdiagnosis – The Tribune India
Models ignored clinically significant indicators and relied instead on characteristics such as text markers or patient positioning
New York, June 1
Artificial Intelligence (AI) models like humans have a tendency to look for shortcuts. In the case of an AI-assisted disease detection, these shortcuts could lead to diagnostic errors if deployed in clinical settings, warn researchers.
A team from the University of Washington in the US, examined multiple models recently put forward as potential tools for accurately detecting Covid-19 from chest radiography, otherwise known as chest X-rays.
The findings, published in the journal…
-
Business16 hours agoThis ASX 200 healthcare stock crashed 14% to 4-year low. Here’s what happened
-
Business12 hours agoDicker Data rides the AI trend to double digit growth
-
Business20 hours agoThis leading broker thinks the CSL share price can climb 40%
-
Noosa News20 hours agoOld Translink app canned, and new version ‘worse than paper map from 2015’