WA health breakthrough could use AI for early heart disease and cancer detection

Kate EmeryThe West Australian
Camera IconWA breakthrough could use AI for early disease detection Credit: Adobe Express

A WA health breakthrough could make it easier to predict cancer or cardiovascular disease from a simple scan that costs as much as a cup of coffee and exposes patients to the same amount of radiation as flying from Perth to London.

Edith Cowan University researchers have developed an artificial intelligence system that uses bone density scans — commonly known as DEXA scans — and ultrasounds to help medical experts pick up early signs of serious diseases.

If successfully commercialised, the ECU-developed algorithm could pave the way for early detection and treatment of heart disease, cancer and diabetes-related blindness.

ECU researcher Afsah Saleem said many chronic illnesses such as cardiovascular disease, which is responsible for one in four deaths, and diabetic retinopathy, a leading cause of blindness, were difficult to detect in the early stages “because they lack obvious symptoms”.

“Current diagnostic methods frequently rely on manual assessments of medical scans, which is a time-consuming, expensive, and subjective process,” she said. “Being a machine learning scientist and working in medical imaging, our aim is to prevent or delay permanent health losses from chronic diseases.

Read more...

“Using this algorithm, we achieved 85 per cent accuracy and 79 per cent sensitivity in identifying abdominal aortic calcification, an early indicator of cardiovascular disease. We also obtained 87 per cent accuracy and 84 per cent sensitivity in diagnosing diabetic retinopathy, and 91 per cent accuracy in identifying different stages of breast cancer.”

ECU senior lecturer Zulgarnain Gilani said the algorithm made it possible for disease signs to be picked up in a simple DEXA scan “which costs you roughly a cup of coffee and the radiation is as small as you would be exposed to flying London to Perth”.

“The innovative aspect of the developed algorithm lies in its ability to capture and learn the distinctive characteristics of both healthy and unhealthy individuals,” he said. “Subsequently, the algorithm effectively differentiates these traits to identify individuals afflicted with disease with remarkable precision.”

Long-term, he said, the idea would be that a GP could simply send a patient for DEXA scan and a patient would receive a score for, for example, aortic calcification — an early indication of the risk of heart disease. Currently, the “gold standard” for getting an aortic calcification score is to send patients for a CT scan, which is both significantly more expensive than a DEXA scan and exposes patients to higher levels of radiation.

Dr Gilani and Dr Saleem are leading the AI aspect of the research, in collaboration with other researchers both at ECU and overseas in Canada, the US, the UK and Korea. It is backed by the Heart Foundation, Raine Medical Research Foundation and the WA Health Department.

Get the latest news from thewest.com.au in your inbox.

Sign up for our emails