Google has hit the headlines recently – unusually not for the work that it has done on the more usually understood areas of home computing, its own platforms and education but this time in the area of health.
Google Health recently announced the results of a study it says indicates artificial intelligence could be more effective in spotting breast cancer than human oncologists.
This just shows the extent of developments and innovation that is taking place by what are called in some areas of the media the “tech giants.” Increasingly there are concerns around the so called “power and reach” of organisations such as Google but every so often a story comes along which shows the necessary flip side of the innovation that is taking place.
Google has developed its Artificial Intelligence model into such a refinement that it identified breast cancer screening mammograms with greater accuracy, with fewer false positives and false negatives than experts.
Clearly there is already a concern that “the machines are taking over” in some quarters but such innovations cannot be ignored.
Google’s London-based AI subsidiary DeepMind worked with Cancer Research UK Imperial Centre, Northwestern University and Royal Surrey County Hospital to train and deploy the AI model, which scanned data from more than 76,000 women in the U.K. and more than 15,000 women in the U.S.
The AI model was also able to more effectively screen for breast cancer using less information than human doctors, relying solely on X-ray images, while doctors had access to patient histories and prior mammograms.
This work has significant potential and implications because due to the nature of the disease. Early diagnosis of breast cancer can be a challenge to an area of medicine that is already working with incredibly busy staff and the sheer scale of potential of a disease to affect millions of people around the world. The latest research builds on Google’s work with deep learning algorithms, which it developed to help doctors spot breast cancer more quickly and accurately in pathology slides.
But this isn’t the only area where AI is helping to advance the care of patients as studies have also been done in further investigating X rays and in developing processes for identifying some heart conditions.
Ok Google – am I having a heart attack?