"While ARDA is effective working with sample data, according to three studies including one published in the Journal of the American Medical Association, a recent visit to a hospital in India where it is being tested showed it can struggle with images taken in field clinics. Often they are of such poor quality that the Google tool stops short of producing a diagnosis—an obstacle that ARDA researchers are trying to overcome.
"The stakes are high. If diabetic retinopathy is caught early it can be kept at bay through monitoring and management of the diabetes, said R. Kim, an Indian ophthalmologist who runs the Aravind Eye Hospital in Madurai, Tamil Nadu, where Google is testing ARDA. More advanced stages need laser surgery that can stop progression. If it isn’t treated, the condition can cause blindness."
and later in the article:
"If Google allowed the algorithm to make a diagnosis from blurred images, it could miss small lesions that appear in the early stages of the condition, she said. Google must decide how bad an image can be before ARDA refuses to grade it. “It’s a trade-off. We want them to be able to use cameras that are a little harder to use but at some point it should move into something where it is ungradable,” Dr. Peng said."
This seems like an ideal setting for active learning, where the algorithm could request input from doctors when analyzing certain images. The algorithm should also train on blurrier or lower-quality but doctor-labeled images, so that it can learn some of the higher-level features that are indicative of retinopathy.
Still, props to all the companies working hard to improve the health of people around the world. It's a long road and I'm excited people are starting down it.