AI related developments have come a long way over last couple of years. Throughout last year, we have seen a number of new use cases of AI in different fields. For instance, researchers used AI to look into dark matter for the first time in September. Healthcare industry can certainly benefit from the improve AI and now, Google has revealed that it has created an AI model that detects the breast cancer more accurately than doctors.
In the blog post, the search engine giant revealed that it has worked with Cancer Research UK Imperial Centre, Northwestern University, and Royal Surrey County Hospital to develop the AI. Thanks to the collaboration, DeepMind was able to spot 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.
In order to find out the accuracy of the new model, the researchers used de-identified mammograms from more than 76,000 women in the United Kingdom and more than 15,000 women in the United States. Afterwards, the trained model was then evaluated by a dataset of over 25,000 women in the United Kingdom and over 3,000 women in the United States.
The company revealed that the system produced a 5.7 percent reduction of false positives in the U.S, and a 1.2 percent reduction in the U.K. It produced a 9.4 percent reduction in false negatives in the U.S., and a 2.7 percent reduction in the U.K.
This latest development is certainly great achievement considering the limited amount of information that were available to the AI. Thanks to the latest development, Google expects that the AI will see increased accuracy moving forward to improve the efficiency of screening programs.