Cardiovascular Risk: AI Detection | New Algorithm
- An automated machine learning programme can now detect potential cardiovascular incidents and fracture risks using routine bone density scans.
- The algorithm drastically reduces screening time, predicting AAC scores from thousands of images in under a minute.
- Cassandra Smith said that during testing, 58% of older individuals screened showed moderate to high AAC levels.
A groundbreaking AI algorithm now identifies cardiovascular risks and predicts fracture risks using routine bone density scans.This new technology, developed by Edith Cowan University, analyzes bone density images to detect abdominal aortic calcification (AAC) in older women, a key indicator of potential heart problems and increased fall risk. The sophisticated system drastically cuts down screening time, providing results in under a minute, compared to the several minutes traditionally needed. News Directory 3 reports that testing revealed that many individuals screened were unaware of their elevated AAC levels,placing them at heightened risk. Early detection is vital.Discover what’s next for this innovative approach to proactive healthcare and see how it could transform fall risk assessment.
AI Identifies Cardiovascular, Fracture Risks in Bone Density Scans
Updated May 30, 2025
An automated machine learning programme can now detect potential cardiovascular incidents and fracture risks using routine bone density scans. Developed by Edith Cowan University (ECU) and the University of Manitoba, the artificial intelligence analyzes vertebral fracture assessment (VFA) images to identify abdominal aortic calcification (AAC) in older women.
The algorithm drastically reduces screening time, predicting AAC scores from thousands of images in under a minute. An experienced reader would take five to six minutes to assess a single image.
ECU research fellow Dr. Cassandra Smith said that during testing, 58% of older individuals screened showed moderate to high AAC levels. One in four were unaware of their high AAC, placing them at increased risk of heart attack and stroke.
ECU senior research fellow Dr. Marc Sim found that patients with moderate to high AAC scores also faced a greater risk of fall-related hospitalizations and fractures.
“Women are recognized as being under screened and under-treated for cardiovascular disease. This study shows that we can use widely available, low radiation bone density machines to identify women at high risk of cardiovascular disease, which would allow them to seek treatment,” Dr. Smith said.
Sim emphasized that vascular health is an frequently enough-overlooked risk factor for falls and fractures. The AI algorithm, when applied to bone density scans, could provide clinicians with more information about a patient’s vascular health, improving fall risk assessment.
“The higher the calcification in your arteries, the higher the risk of falls and fracture,” Dr. Sim said.
What’s next
The researchers plan to further refine the algorithm and explore its application in broader populations to enhance early detection of cardiovascular and fracture risks, potentially leading to more proactive and personalized healthcare strategies.