AI to predict serious health conditions — at speed

A breakthrough in artificial intelligence holds the promise of predicting a person’s risk of developing serious health conditions later in life — at the press of a button.

Abdominal aortic calcification (AAC) is a calcification that can build up within the walls of the abdominal aorta; it predicts the risk of developing cardiovascular disease events such as heart attacks and stroke. It also predicts someone’s risk of falls, fractures and late-life dementia.

AAC can be detected by the common bone density machine scans used to detect osteoporosis; however, highly trained expert readers are needed to analyse the images in a process that can take 5–15 minutes per image.

Now, a multidisciplinary team of researchers have developed software that can analyse scans much, much faster: roughly 60,000 images in a single day.

Researcher and Heart Foundation Future Leader Fellow Associate Professor Joshua Lewis, from Edith Cowan University’s (ECU) School of Medical and Health Sciences, 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 in the future for early cardiovascular disease detection and disease monitoring during routine clinical practice,” he said.

The software was the result of an international collaboration between ECU, the University of WA, University of Minnesota, Southampton and University of Manitoba, Marcus Institute for Aging Research, and Hebrew SeniorLife Harvard Medical School.

While not the first algorithm developed to assess AAC from these images, the researchers said the study was the largest of its kind, was based on the most commonly used bone density machine models and is the first to be tested in a real-world setting using images taken as part of routine bone density testing.

It saw more than 5000 images analysed by experts and the team’s software.

After comparing the results, the expert and software arrived at the same conclusion for the extent of AAC (low, moderate or high) 80% of the time — an impressive figure given this was the first version of the software.

3% of people deemed to have high AAC levels were incorrectly diagnosed as having low levels by the software. Lewis said this was notable, as these were the individuals with the greatest extent of disease and highest risk of fatal and nonfatal cardiovascular events and all-cause mortality.

“Whilst there is still to work to do to improve the software’s accuracy compared to human readings, these results are from our version 1.0 algorithm, and we already have improved the results substantially with our more recent versions,” he added.

“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,” Lewis concluded.

The Heart Foundation contributed funding for the project, thanks to Lewis’s 2019 Future Leadership Fellowship providing support for research over a three-year period.

The findings have been published in eBioMedicine.

Image credit: iStock.com/z1b