IOWA CITY, Iowa—Today, IDx Inc. announced its founder and president, Michael Abràmoff, MD, PhD, has been awarded U.S. Patent No. 9,924,867 for a system that can automatically measure arterial and venous diameters in blood vessels, an important predictor of cardiovascular health.
IDx is an AI diagnostic systems company focused on developing clinically-aligned autonomous algorithms that identify disease in medical images. The company says its mission is to transform the quality, accessibility, and affordability of global healthcare through the automation of medical diagnosis and treatment.
“It is exciting that we have developed a more efficient and accurate way of capturing this measure of cardiovascular health,” said Abràmoff. “This represents one component of the work we are doing to develop an autonomous AI diagnostic system that accurately identifies patients at high risk of cardiovascular events.”
Since 2011, IDx has researched how algorithms can be used to assess cardiovascular health and plans to incorporate this patented tool into its existing AI platform. By combining blood vessel measurements with BMI, blood pressure, and other health measures, IDx hopes to provide physicians with a new level of understanding of early indicators of cardiovascular risk.
Measurement of arteries and veins have long been studied as important predictors of an increased risk of stroke, cerebral atrophy, cognitive decline, and myocardial infarction. Yet these measurements when done by human experts are sometimes inaccurate, and may result in missing early warning signs that would allow physicians to initiate outcome-changing interventions. Using AI, the new patented method and systems overcomes these limitations to obtain more accurate measurements.
In February, IDx also completed an FDA clinical trial for its first product, IDx-DR, an AI-based diagnostic system for the autonomous detection of diabetic retinopathy that is currently under review by the FDA. The device is not currently available for sale in the United States, but a clearance determination is expected in 2018. If cleared, IDx-DR is expected to be the first autonomous, AI-based diagnostic system intended for use in the front lines of healthcare.
According to their website, “IDx-DR is an advanced algorithmic solution designed to detect diabetic retinopathy and diabetic macular edema. Created through the combination of classical image analysis, deep learning techniques, and ophthalmic expertise, IDx-DR was designed to provide fast results through a secure cloud and enable DR screening at the front lines of care.”
IDx-DR was developed to assess for diabetic retinopathy during routine office visits with primary care providers, with results available in minutes. Diabetic retinopathy is a leading cause of blindness in the U.S., but vision loss is preventable if the disease is detected and treated early.
“We are very pleased with the diagnostic accuracy and look forward to FDA’s expedited review,” said Abràmoff. Published results in a peer-reviewed journal are pending.
Findings from the IDx study used real world data collected during the patient care process, rather than data or images procured retrospectively. All tests were performed in a primary care setting by non-clinician staff who received an average of four hours training on the IDx-DR system.
Clinical trial sites have offered favorable feedback. “This technology has great utility and would be solving a real problem,” said John Parker, MD, principal investigator at PMG-Research of Wilmington. “IDx-DR may not only help to identify disease requiring treatment, but the diagnosis also may prompt patients to change their lifestyle and play a more active role in managing their diabetes.”