For the first time, US health regulators UU They have given the green light to sell a medical device that bypasses doctors and uses artificial intelligence software to detect an eye disease that affects more than 30 million Americans living with diabetes. Nicknamed the IDx-DR, the device (undoubtedly named for its parent company IDx LLC in Iowa) is presented in the form of a software program. Any doctor, not just an eye doctor, takes images of a person’s eye with a special retina camera and then uploads digital photos to a server in the cloud where the software is installed. IDx-DR indicates whether or not the image has sufficient quality to obtain a result and, if it is, the program uses an artificial intelligence algorithm to analyze the images. It produces two results. The first will refer a patient to a vision professional if a “more than mild diabetic retinopathy” is detected. If the results are negative, IDx-DR refers the patient to another test in 12 months. The FDA evaluated data from a clinical retinal imaging study of 900 patients with diabetes in 10 facilities to assess the accuracy of IDx-DR. They found that in mild cases it was correct 87.4 percent of the time, and 89.5 percent in “more than mild” cases. A doctor is not needed to interpret the results, which means that any health care provider can recommend the next steps for the patient. IDx-DR only detects diabetic retinopathy, which affects the eye when an excess of sugar in the blood damages the blood vessels in the back. It is the most common vision complication for people with diabetes, with around 200,000 cases in the United States each year. But it does not work for everyone: people with a history of laser treatment, surgery or injections in the eye, or a list of other conditions (persistent loss of vision, blurred vision, floaters, to name a few) should not be analyzed using IDx -DR. The new device joins the range of other artificial intelligence technologies that are transferred to the medical field, such as this intelligent software that can diagnose prostate cancer or this other algorithm capable of recognizing conditions such as age-related vision loss and retinopathy diabetic While a recent study suggests that consumers are more comfortable using AI in their health care than in retail or with their financial institutions, the use of AI raises some ethical questions, such as who is responsible for an incorrect diagnosis, how to protect privacy or prevent piracy, and even the threat of bioterrorism through nanotechnology.
Video credits to fuki Zeny YouTube channel