
One of the perils of ageing is being uncertain about one’s future health. When should you retire? Should you plan a world trip or a tree change not knowing if you are likely to live to enjoy it?
Now researchers have discovered a way to predict our risk of developing serious health conditions later in life by examining bone scans for signs of calcification of the abdominal artery.
Abdominal aortic calcification (AAC) is a calcium deposit that which can build up within the walls of the abdominal aorta.
ECU Associate Professor Joshua Lewis explains the abdominal aorta is the main artery responsible for distributing oxygenated blood from the heart to the rest of the body.
“If it becomes calcified it is less flexible and blood flow becomes uneven which may damage other organs including the kidneys, brain and lower limbs.”
ACC can be used to predict your risk of developing cardiovascular disease events such as heart attacks and stroke as well as your risk of falls, fractures and late-life dementia.
The technology to measure this calcification is already available in bone density machine scans used to detect osteoporosis. However, interpreting the images is time consuming and requires highly trained expert readers, making it impractical for routine use in preventive medicine.
Scientists examined the AAC scores of nearly 1000 women from the late 1990s, and then followed their health status for more than 15 years.
They found one in two older women had medium to high levels of AAC, and these women were twice as likely to be hospitalised or die from a late-life dementia – independent of other cardiovascular factors or genetic factors.
The scans provide valuable predictions of several future health risks, including risk of dementia earlier in life, which could prove vital in slowing development of the condition.
Scientists from ECU School of Medical and Health Sciences in collaboration with scientists from the University of WA, Universities of Minnesota, Southampton and Manitoba, Marcus Institute for Aging Research, Hebrew SeniorLife and Harvard Medical School have developed artificial intelligence software which can analyse scans much faster – up to 60,000 images per day.
Professor Lewis said this significant boost in efficiency will be crucial for the widespread use of AAC in research and helping people avoid developing health problems later in life.
“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 for early cardiovascular disease detection and monitoring during routine clinical practice,” he said.
The team scored 5000 images obtained during routine bone density tests by both human experts and Artificial Intelligence algorithms.
After comparing the results, the experts and software arrived at the same conclusion for the extent of AAC (low, moderate or high) 80 per cent of the time.
“It is about the same agreement as between two human experts,” said Professor Lewis. “The latest version of the software is three per cent better and machine learning ensures the software improves the more it is used.”
Only three per cent of people deemed to have high AAC levels were incorrectly diagnosed to have low levels by the software.
“This is notable as these people with high AAC scores are the individuals with the greatest extent of disease and highest risk of fatal and nonfatal cardiovascular events and all-cause mortality,” Professor Lewis said.
“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.
“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 research was published in eBioMedicine in July 2023.