Researchers develop algorithm to identify bone fracture risk

Jeff Rowe
By analyzing existing images, AI can help identify patients at risk for potentially life-threatening fractures without exposing them to more radiation.

New developments in AI are generally viewed as a step forward when it comes to collecting and analyzing new health data, but out of Israel comes news of how AI algorithms can be used to utilize existing CT scan data to identify patients at high risk for osteoporotic fractures.

According to a statement from Zebra Medical Vision and the Israel-based Clalit Research Institute, the novelty in the algorithmic research “is in the algorithm's ability to calculate bone density and identify existing vertebral compression fractures using CT scans that were already performed for other purposes. This approach enables leveraging existing CTs to identify populations at risk of osteoporosis, without the need for additional procedures or radiation exposure.”

For the study, Zebra Medical Vision's technology for assessing bone fragility characteristics in CT scans was successfully translated into an accurate fracture risk predictor by the Clalit research team, with the results being as accurate as, “and sometimes even more predictive than,” the current best technology.

“There are hidden medical insights in imaging studies that the human eye cannot capture, but have the potential to save lives,” noted Prof. Ran Balicer, the director of the Clalit Research Institute. “We will continue our joint efforts to develop AI-based medical applications, providing physicians with the best tools and the most novel technologies. To this end, we are on the verge of developing a system that will present improved fracture prediction risk scores to all Clalit physicians and patients."

According to the statement, treating osteoporosis costs nearly $18 billion annually in the U.S. alone, and it is estimated that 1 in 3 women and 1 in 5 men over that age of 50 will suffer an osteoporotic fracture. Moreover, the risk of death in the first year after sustaining a hip fracture is over 20 percent.

"We have always been aware that this is a common disease with a high risk of fatality, and even though there are some treatment options for prevention, we don't identify at-risk patients early enough," noted Dr. Eldad Elnekave, CMO at Zebra Medical Vision. "Together with our partner, Clalit, we found that all the information we need pertaining to at-risk patients already exists in CT tests done for other reasons. It's time to utilize that information."

The study, titled "Automated opportunistic osteoporotic fracture risk assessment using computed tomography scans to aid in FRAX underutilization," can be found in Nature Medicine Journal,