Google and Verily, Alphabet’s life sciences and healthcare arm, have created a machine learning algorithm to help screen for diabetic retinopathy and diabetic macular edema, according to a Google blog post.
The development of the algorithm has been a three-year project, which also involved the organizations conducting a global clinical research program focused on India. Verily has received a CE mark for the algorithm.
Now, they’ve revealed the first real-world clinical use of the algorithm is happening at Aravind Eye Hospital in Madurai, India.
At the hospital, the process works like this: Technicians use a fundus camera to take one image of each of the patient’s eyes. The image is then uploaded to the screening algorithm. The machine learning screens for diabetic retinopathy and diabetic macular edema. Based on the results, technicians can determine whether the patient should be referred to an eye care physician.
“Thousands of patients come through the doors of our hospitals and vision centers every day, and we want to provide them with the best possible eye care,” Dr. R. Kim, Aravind Eye Hospital’s CMO and chief of retina services, said in a statement in a Verily blog post. “By integrating Verily and Google’s retinal diagnostic program into our screening process, we can improve our efficiency, giving physicians like myself more time to work closely with patients on treatment and management of their disease while increasing the volume of screenings we can perform.”
Google and Verily are bringing their machine learning algorithm to other areas of the world as well. In December, they announced a partnership with Rajavithi Hospital, which is operated by the Ministry of Public Health in Thailand. A research pilot with the hospital will explore how AI can be used to detect diabetic retinopathy.
Additionally, in 2016, Verily joined forces with Nikon subsidiary Optos to develop solutions for earlier detection of diabetic retinopathy and diabetic macular edema.
Photo: Jay_Zynism, Getty Images
