Artificial intelligence (AI) has advanced, but it's still far from perfect. AI systems can make biased decisions, due to the data they're trained on or the way they're designed, and a new study suggests that clinicians using AI to help diagnose patients might not be able to spot signs of such bias.
The research, published Tuesday (Dec. 19) in the JAMA, tested a specific AI system designed to help doctors reach a diagnosis. They found that it did indeed help clinicians more accurately diagnose patients, and if the AI "explained" how it made its decision, their accuracy increased even more.
