Electronics Assembly Knowledge, Vision & Wisdom
Medical Device Artificial Intelligence
Medical Device Artificial Intelligence
IDx-DR is the first medical device that uses artificial intelligence for the autonomous detection of diabetic retinopathy without a human interpreting the results.
Technology Briefing

,{url:'http://www.circuitinsight.com/videos/technology_briefing_medical_device_artificial_intelligence.mp4'}], clip:{autoBuffering:true, autoPlay:true, scaling:'scale' } }).ipad();
Technology Briefing is brought to you by association with Audio-Tech, publishers of critically acclaimed programs including: Trends Magazine.

Subscribe to their monthly reports and learn about big ideas, new products, new management techniques, breakthrough concepts, and trailblazing technologies.
Transcript
IDx-DR is the first medical device that uses artificial intelligence for the autonomous detection of diabetic retinopathy without a human interpreting the results. It received FDA authorization in April 2018, following a clinical trial in primary care offices. The results of that trial were published just in Nature Digital Medicine.

Diabetic retinopathy is the leading cause of vision loss in adults and it's one of the most severe complications suffered by the 30.3 million Americans living with diabetes. More than 24,000 people in the U.S. lose their sight to diabetic retinopathy each year. And, early detection and treatment can reduce the risk of blindness by 95 percent, but less than 50 percent of patients with diabetes schedule regular exams with an eye-care specialist.

This clinical trial was the first study to prospectively assess the safety of an autonomous AI system in patient care. In the process, IDx-DR exceeded all pre-specified objectives in terms of:
Sensitivity, which is the ability to correctly identify a patient with a disease;
Specificity, which is the ability to correctly classify a person as disease-free;
Imageability, which is the capability to produce quality images of the retina and determine the severity of the disease.

The AI system's primary role is to identify those people with diabetes who are likely to have diabetic retinopathy, which then requires further evaluation by an eye-care \ provider in order to specify a course of treatment.

The study results demonstrated the safety and effectiveness of an autonomous AI system in bringing specialist-level diagnostics to a primary care setting. Doing so has the potential to increase access and lower cost.

In the study, 900 adult patients with diabetes - but no history of diabetic retinopathy - were examined at ten primary care sites across the U.S. Retinal images of the patients were obtained using a robotic camera, with artificial intelligence assisting the operator in getting good quality images. Once the four images were complete, the diagnostic artificial intelligence made a clinical diagnosis in twenty seconds.

The diagnostic artificial intelligence detects disease just as expert clinicians do, by having detectors for the lesions which characterizes diabetic retinopathy, including microaneurysms, hemorrhages, and lipoprotein exudates. Camera operators in the study were existing staff of the primary care clinics, not physicians or trained photographers.

The lead researcher in the study was Michael D. Abramoff, the founder and president of IDx, the company that created the IDx-DR system and funded the study. As he says, "This was much more than just a study testing an algorithm on an image. We wanted to test it in the places where it will be used, by the people who will use it, and we compared it to the highest standard in the world.

Study participants also had retinal images taken at each of the primary care clinics using specialized widefield and 3D imaging equipment without artificial intelligence but operated by experienced retinal photographers. Complete diagnostic data accomplished by both the artificial intelligence system and human experts' readers was available for 819 of the original 900 study participants.

FPRC readers identified 198 participants with more than mild diabetic retinopathy who were further examined by a specialist. IDx-DR was able to correctly identify 173 of the 198 participants with the disease, resulting in a sensitivity of 87 percent. Among the 621 disease-free participants identified by human experts, AI identified 556 participants, for a specificity of 90 percent.

And, the AI system had a 96 percent imageability rate; that is, of the 852 participants who had an expert human diagnosis, 819 had an artificial intelligence system diagnostic output produced. Following FDA clearance, a clinic in Iowa became the first in the nation to begin using IDx-DR to screen patients.
Submit A Comment

Comments are reviewed prior to posting. Please avoid discussion of pricing or recommendations for specific products. You must include your full name to have your comments posted. We will not post your email address.

Your Name


Company


E-mail


Country


Comments


Authentication

Please type the number displayed into the box. If you receive an error, you may need to refresh the page and resubmit the information.



Related Programs
bullet 3D Printed Food
bullet Self-Driving Vehicles: From Prototypes to Commercial Success
bullet 21st Century Textiles Make Life Better
bullet Wearable Cameras
bullet Neural Networks and Artificial Intelligence
bullet New Methods Extract Lithium from Water
bullet Medical Device Artificial Intelligence
bullet The Portable Smartphone Laboratory
bullet Ultra-Thin Artificial Retina
bullet Ultra-low Power Injectable Biosensors
More Related Programs