Image: Game-Changing AI Software That Helps Diagnose Breast and Thyroid Cancers Receives US FDA Clearance (Photo courtesy of Koios Medical)
A new artificial intelligence (AI) enabled software that improves cancer detection with fewer false positives and avoidable procedures has been cleared for use by physicians interpreting ultrasound exams.
Koios Medical, Inc. (New York, NY, USA) has received FDA clearance for Koios DS, its AI-based software platform used to diagnose thyroid and breast cancer. The new system, built using ultrasound data from a network of 48 sites around the world, aids physicians in accurately diagnosing disease and improves speed to treatment while reducing avoidable surgical procedures.
Breast cancer is the second most diagnosed cancer in women worldwide. An ultrasound exam is the standard of care for women with dense breast tissue. Thyroid disease is one of the most complex and challenging radiological interpretations. Diagnostic uncertainty drives a high level of variability across physicians and results in surgical procedures, downstream cost, risk of complication and physician burn-out.
The company performed studies that proved physicians using Koios DS software dramatically improved accuracy, consistency, and efficiency. Physicians’ thyroid cancer detection rates jumped by up to 14% while simultaneously reducing false positive biopsy orders by over 35%. Interpretation variability was lowered by over 50% and time spent per case dropped by 24%.
The patented AI software aligns Koios DS AI generated findings directly to the American College of Radiology’s BI-RADS and TI-RADS rating systems as well as the American Thyroid Association’s system for tissue classification, scoring and patient management. The AMA recently announced new CPT Category 3 codes for whenever Koios DS software is utilized interpreting, classifying and reporting traditional ultrasound exams.
The rigor of the FDA clearance process required that Koios DS be proven to accurately interpret images from all major ultrasound hardware manufacturers. The software is compatible with major PACS workstation viewers and integrated into GE Healthcare’s LOGIQ E10 ultrasound scanner. The system enables real-time decision-making with results that can be exported directly into a patient's record and all major reporting systems, reducing errors and saving time.
“The typical decision-making paradigm relies on tradeoffs; trading sensitivity for specificity, efficiency for thoroughness, but the only thing enforcing this paradigm is the inability to shift off of these tradeoff curves in place of shifting along them,” said Dr. Lev Barinov, VP of Clinical Excellence. “This novel software demonstrates that using AI for decision support physicians can make clinically meaningful shifts in performance improving interpretation efficacy and diagnostic performance, improving sensitivity and reducing false positives. It is exciting to bring these innovations to physicians and ultimately their patients to elevate the level of care broadly.”
“The ability of physicians and health systems to now code and bill for the use of this innovative and effective technology will most certainly accelerate adoption, putting the software into the hands of physicians for the benefit of patients nationwide,” added Graham Anderson, Koios Medical CFO.
“The loss of life globally to cancers found too late, or misdiagnosed, is tragic. When combined with the millions wasted on avoidable procedures we are compelled to relentlessly innovate, building powerful AI models directly into easy-to-use software,” said Koios Medical CEO Chad McClennan. “This new FDA clearance means physicians are now poised to save tens of thousands of lives while freeing up precious time and resources that can be used more effectively and elevate quality of life.”
Koios Medical, Inc.