Over the coming years, new applications of machine learning will add capability and efficiency to industries ranging from transportation to manufacturing. But among all these possible applications, here is one that stands out as an incredible opportunity to benefit humanity: the application of machine intelligence to healthcare. We believe that machine learning is poised to transform medicine, delivering new technologies that will empower doctors to better serve their patients. Working with clinicians and medical providers, Google is developing tools to drastically improve the availability and accuracy of medical services.
Medical imaging is one area we are currently exploring. Deep learning has revolutionized the field of computer vision, making practical in-your-pocket technologies out of what seemed like science fiction just a few years ago. If these new computer vision systems can reach human-level accuracy in identifying dog breeds, is there any hope that those same systems could learn to identify disease in medical images? Almost two years ago, we began exploring this possibility for a disease of the eye called diabetic retinopathy.
Diabetic retinopathy is the fastest growing cause of blindness globally. The condition is normally diagnosed by a highly trained doctor carefully examining a scan of the eye. If caught early, effective treatments are available. But if caught late, the disease progresses into irreversible blindness. In much of the world, there simply are not enough doctors available to support the volume of screening required to protect the population.
In a close collaboration with doctors and international healthcare systems, Google has developed a state-of-the-art computer vision system for reading retinal fundus images for diabetic retinopathy. Our early results are very encouraging, and we are looking forward to sharing these results in a peer-reviewed publication shortly. However, there is still much work to do. Ultimately, we hope to help real doctors and clinics expand global screening capacity to cover all the at-risk individuals in the world.
There are countless opportunities for machine intelligence to improve the accuracy and availability of healthcare. We hope that our work in retinopathy will serve as one of many demonstrations of this potential. To that end, we are actively engaged in many other healthcare projects in collaboration with doctors and medical systems.
Note: We are always open to research collaborations on large medical datasets of all types, not just ophthalmic imaging. If you know of an organization that would like to partner with us, please contact email@example.com.