A new Johns Hopkins and FDA tool, G-AUDIT, identifies risky patterns in medical AI datasets before they cause errors, bias, or health disparities. ✍️: @danyasaperstein

A new Johns Hopkins and FDA tool, G-AUDIT, identifies risky patterns in medical AI datasets before they cause errors, bias, or health disparities. ✍️: @danyasaperstein Link New tool designed to detect biases hidden in medical AI data sets, identifies flaws in training "We train models to be the most predictive, but we have zero control over what the model uses to make the prediction," AI-assisted medicine expert Unberath added.