Researchers at Edith Cowan University (ECU) and the University of Manitoba have developed an automated program that can identify cardiovascular problems in routine bone density scans and reduce risks.
This may make it easier to detect serious health problems before they are life-threatening.
The algorithm was developed by ECU researcher Dr. Cassandra Smith and Senior Researcher Dr. Marc Sim, PhD., which is analysed by analyzing vertebrae fracture assessment (VFA) images taken during standard bone density tests, which are often part of an osteoporosis treatment program.
By assessing the presence and extent of abdominal aortic calcification (AAC) in these scans, the program can quickly label patients with heart disease, stroke and dangerous falls.
What is really impressive is how fast the algorithm works. While it may take five to six minutes for experienced human readers to calculate AAC scores from a scan, machine learning programs can predict scores for thousands of images in less than a minute.
This level of efficiency can be a significant benefit for health systems that want to screen large populations for hidden health risks.
The need for such screening is obvious. exist ResearchDr. Smith found that older people with a conventional bone density scan had surprisingly moderate to high levels of AAC.
What is even more worrying is that one in four of these patients is completely unaware of their increased risks.
“Women are considered under-screened and treated for cardiovascular disease,” Dr. Smith noted. “This study shows that we can use widely available low-radiation bone density machines to identify women at high risk for cardiovascular disease, which will enable them to seek treatment.”
But the algorithm’s predictive power does not prevent heart health. Using the same program, Dr. SIM found that patients with moderate to high AAC scores also had a greater risk of hospitalization and breakage associated with falls compared to patients with low scores.
“The higher the artery calcification, the higher the risk of falls and fractures,” explains Dr. Sim. Although traditional fall risk factors such as previous falls and low bone density are well known, vascular health is rarely considered.
“Our analysis found that AAC is a great contribution to the risk of falling and is actually more important than other factors that are clinically identified as risk factors for falls.”
Like any new technology, before this AI-assisted screening becomes standard practice, there are some questions to be answered and challenges to be overcome need to be overcome.
First, the algorithm needs to be validated in a larger, more diverse patient population and seamlessly integrated into existing clinical workflows.
But if these challenges can be met, a simple skeleton scan (which millions of older people have experienced frequently) could become an early warning system for some of the most common and devastating health problems we face.
