Artificial intelligence is an important innovation in diagnostics, because it can learn to recognize abnormalities that a doctor would also label as a disease. But the way these systems work is opaque, and doctors have a better “overall picture” when they make the diagnosis. In this publication, Radboudumc researchers show how they can make the AI show how it’s working, as well as let it diagnose more like a doctor, thus making AI more relevant to clinical practice.
- Race plays a role in children’s food allergies
- A compound that slows bone loss, and a resource for developing treatments to slow aging
- Cell ‘bones’ mystery solved with supercomputers
- UMass Amherst researchers develop technique to replicate bone-remodeling processes
- Mouse study identifies novel compound that may help develop diabetes drugs