New AI Tool Detects Hidden Heart Attack Risk at the Click of a Button
New AI Tool Detects Hidden Heart Attack Risk at the Click of a Button
————————————-
Researchers from Edith Cowan University (ECU), in collaboration with the University of Manitoba, have developed an AI tool that rapidly detects hidden cardiovascular and fall risks in older adults using routine bone density scans, SciTech Daily reported.
The machine learning algorithm identifies abdominal aortic calcification (AAC), a key indicator of cardiovascular risk, from vertebral fracture assessment images typically used in osteoporosis management.
The AI significantly speeds up the assessment process, analyzing thousands of images and generating AAC scores in under a minute, compared to five to six minutes per image by specialists. ECU research fellow Dr. Cassandra Smith found that 58% of older individuals screened had moderate to high AAC levels, with many unaware of their elevated risk for heart attack and stroke.
Additionally, ECU senior research fellow Dr. Marc Sim revealed a strong link between higher AAC scores and increased risk of falls and fractures, surpassing traditional risk factors. The tool offers clinicians valuable insights into vascular health, an often overlooked factor in fall and fracture risk assessments, improving early diagnosis and prevention strategies.
