Shravya Shetty, M.S. and Daniel Tse, M.D., for Google Health Blog:
These findings show that our AI model spotted breast cancer in de-identified screening mammograms (where identifiable information has been removed) with greater accuracy, fewer false positives, and fewer false negatives than experts. This sets the stage for future applications where the model could potentially support radiologists performing breast cancer screenings.
We also wanted to see if the model could generalize to other healthcare systems. To do this, we trained the model only on the data from the women in the U.K. and then evaluated it on the data set from women in the U.S. In this separate experiment, there was a 3.5 percent reduction in false positives and an 8.1 percent reduction in false negatives, showing the model’s potential to generalize to new clinical settings while still performing at a higher level than experts.
News like these ones are always impressive. The rate of false positives dropped and this is something to celebrate. This is scenario that I always thought of when the “Artificial Intelligence and Humans” topic is discussed.