- The device, called IDx-DR, is designed to detect vision loss in diabetic patients
- It takes a picture of the eye which is interpreted by an algorithm
- It is the first AI device in the US to be approved to work alone, without a doctor
- As such, it can be used by any doctor – not just eye doctors – including primary care physicians who interact more often with diabetic patients
US health regulators have approved the first ever artificially intelligent medical device that can identify disease without need for a doctor.
The device, called IDx-DR, is designed to detect the most common cause of vision loss among more than 30 million Americans living with diabetes.
Its in-built camera takes a picture of the patient’s eye, which is assessed by an algorithm to determine whether there are signs of diabetic retinopathy.
The move, announced on Wednesday, makes this the first AI device to receive FDA approval to screen without need for a doctor to interpret the results.
It means any doctor could use it, including primary care physicians who interact far more frequently with patients with diabetes, rather than patients having to seek out eye doctors themselves.
The IDx-DR is made to detect the most common cause of vision loss among more than 30 million Americans living with diabetes. It takes a photo of the eye, which an algorithm analyzes
The device was reviewed under new FDA regulations designed to speed to market some devices seen as low- to moderate-risk and for which there is no prior legally marketed device.
It is part of Commissioner Scott Gottlieb’s efforts to streamline approvals on a variety of fronts, including generic drugs and cheaper versions of costly biotech medicines.
‘The FDA will continue to facilitate the availability of safe and effective digital health devices that may improve patient access to needed health care,’ Malvina Eydelman, who oversees the agency’s division of ophthalmic, and ear, nose and throat devices, said in a statement.
IDx-DR will be used to detect diabetic retinopathy, in which high levels of blood sugar lead to damage in the blood vessels of the retina and vision loss.
The IDx-DR program uses AI software to analyze images of the eye taken with a retinal camera.
The software tells the doctor that the patient either has more than mild diabetic retinopathy and should be referred to eye care professional for possible treatment, or is ‘negative’ for more than mild diabetic retinopathy and should be rescreened in 12 months.
‘Many patients with diabetes are not adequately screened for diabetic retinopathy since about 50 percent of them do not see their eye doctor on a yearly basis,’ Eydelman said, noting that early detection is important for managing care.
In a clinical trial, IDx-DR was able to correctly identify the presence of more than mild diabetic retinopathy 87.4 percent of the time and identify those who did not have more than mild disease 89.5 percent of the time.
Advertisement