We are excited by the potential to use machine learning to augment the abilities of doctors and healthcare practitioners. As just one example of the possibilities, in a paper published in the Journal of the American Medical Association (JAMA), we demonstrated that a machine-learning driven system for diagnosing diabetic retinopathy from a retinal image could perform on-par with board-certified ophthalmologists. With more than 400 million people at risk for blindness if early symptoms of diabetic retinopathy go undetected, but too few ophthalmologists to perform the necessary screening in many countries, this technology could help ensure that more people receive the proper screening. We are also doing work in other medical imaging domains, as well as investigating the use of machine learning for other kinds of medical prediction tasks. We believe that machine learning can improve the quality and efficiency of the healthcare experience for doctors and patients, and we’ll have more to say about our work in this area in 2017.
Source: Research Blog: The Google Brain team — Looking Back on 2016