A computer algorithm was able to diagnose breast cancer more accurately than a radiologist—and just as well as two doctors examining a mammogram. That’s according to a new study published Wednesday in the journal Nature. Researchers from Google and Imperial College London teamed up to teach a computer model how to recognize cancer by feeding it the scans of 29,000 women. Then they put it to the test. According to the BBC, artificial intelligence had 1.2 percent fewer false positives and 2.7 percent fewer false negatives than the humans—who also had patient health histories to help them.