> The artificially intelligent algorithms began to train themselves using existing data to look for patterns and create their own "rules." Then, they began testing these guidelines against other records. And as it turns out, all four of these methods "performed significantly better than the ACC/AHA guidelines," Science reports.
This is merely back testing. It's easy to come up with an algorithm that works with data set A and they works with data set B. People have been claiming back tested algorithms to predict stock market returns and election returns for ages. And in forward testing the algorithms always fail.
This is not to say that a machine-based approach to predicting heart ailments cannot work. But for it to be proven, it has to be forward tested: it has to work with new patients.