Artificial Intelligence Revolutionizes Cardiovascular Risk Prediction – Bone Density Scans Now a Powerful Indicator
Thanks to the power of artificial intelligence (AI), cardiovascular risk prediction is undergoing a revolutionary transformation. A new study reveals that bone density scans, commonly used to detect osteoporosis, can now serve as a powerful indicator of cardiovascular health risks, thanks to AI technology.
Abdominal aortic calcification (AAC), the accumulation of calcium deposits in the walls of the abdominal aorta, has long been associated with an increased risk of heart attacks, strokes, falls, fractures, and late-life dementia. Traditionally, assessing AAC from bone density scans required expert readers and a time-consuming process of 5-15 minutes per image.
However, researchers from Edith Cowan University (ECU) have developed innovative software that can analyze bone density scans much faster, allowing for the assessment of approximately 60,000 images in a single day. This significant boost in efficiency paves the way for widespread use of AAC in research and enables early cardiovascular disease detection and monitoring during routine clinical practice.
The study, conducted by ECU in collaboration with several prestigious institutions including the University of WA, the University of Minnesota, and Harvard Medical School, is the largest of its kind. It utilized the most commonly used bone density machine models and analyzed over 5,000 images both manually by experts and through the newly developed AI software.
In an impressive outcome, the expert analysis and the AI software arrived at the same conclusion regarding the extent of AAC 80 percent of the time. Moreover, the software only misdiagnosed 3 percent of individuals with high AAC levels as having low levels. These misdiagnosed individuals are at the greatest risk of cardiovascular events and all-cause mortality. Although further improvements in accuracy are necessary, these results are based on the initial version of the algorithm, and subsequent versions have already shown substantial enhancements.
Automated assessment of AAC from bone density scans holds great promise for large-scale screening of cardiovascular disease and other conditions – even before symptoms manifest. This early detection can lead to important lifestyle changes and interventions that improve long-term health outcomes.
The Heart Foundation, through Professor Joshua Lewis’ 2019 Future Leadership Fellowship, provided funding for this groundbreaking research. Over a three-year period, the fellowship supported the development of the software and the comprehensive study.
In conclusion, AI is revolutionizing cardiovascular risk prediction by harnessing the potential of bone density scans. The software developed by ECU researchers enables rapid analysis of AAC from these scans, offering the possibility of early detection and monitoring of cardiovascular disease. This breakthrough has the potential to significantly improve health outcomes by empowering individuals to take proactive steps towards a healthier future.
Reference: Machine learning for abdominal aortic calcification assessment from bone density machine-derived lateral spine images by Naeha Sharif, Syed Zulqarnain Gilani, David Suter, Siobhan Reid, Pawel Szulc, Douglas Kimelman, Barret A. Monchka, Mohammad Jafari Jozani, Jonathan M. Hodgson, Marc Sim, Kun Zhu, Nicholas C. Harvey, Douglas P. Kiel, Richard L. Prince, John T. Schousboe, William D. Leslie and Joshua R. Lewis, eBioMedicine.
DOI: 10.1016/j.ebiom.2023.104676
