Artificial Intelligence (AI) (© NicoElNino - stock.adobe.com)
JOONDALUP, Australia — Artificial intelligence (AI) can now predict how healthy you will be later in life — all at the press of a button. Researchers from Edith Cowan University (ECU) in Australia have created AI software capable of rapidly analyzing bone density scans to predict the risk of future health conditions, including cardiovascular diseases and dementia.
Abdominal aortic calcification (AAC) is a buildup within the abdominal aorta’s walls that can indicate an individual’s risk of heart attacks, strokes, falls, fractures, and late-life dementia. Although the detection of AAC is possible through bone density scans – usually utilized to determine osteoporosis – these scans historically required highly trained experts and considerable time to analyze.
However, the new software designed by the collaborative teams from ECU’s School of Science and School of Medical and Health Sciences can analyze roughly 60,000 images in just a day.
“Since these images and automated scores can be rapidly and easily acquired at the time of bone density testing, this may lead to new approaches in the future for early cardiovascular disease detection and disease monitoring during routine clinical practice,” says Joshua Lewis, an associate professor and a Heart Foundation Future Leader Fellow, in a university release.
The study emerged from an international partnership, including institutions such as the University of Western Australia, the University of Minnesota, the University of Manitoba, and Harvard Medical School. While it’s not the first of its kind, this study stands out because of its scale, utilization of popular bone density machine models, and its real-world application. Over 5,000 images were assessed by both human experts and the software. The findings revealed that both methods concurred on the extent of AAC 80 percent of the time, a commendable achievement for the software’s inaugural version.
Lewis emphasized the importance of the software’s accuracy, noting that only three percent of individuals identified by human experts as having high AAC levels were misdiagnosed by the software as having low levels.
“Automated assessment of the presence and extent of AAC with similar accuracies to imaging specialists provides the possibility of large-scale screening for cardiovascular disease and other conditions – even before someone has any symptoms,” says Lewis. “This will allow people at risk to make the necessary lifestyle changes far earlier and put them in a better place to be healthier in their later years.”
The study was published in the journal eBioMedicine.
