A project at The University of Western Australia aims to develop artificial intelligence technology to improve the diagnosis of heart disease.
Coronary artery disease results from the build-up of plaque – fats, cholesterol and other substances – in and on the walls of arteries that supply the heart and results in narrowing and obstruction of blood flow. Plaques may rupture, causing a blood clot which can lead to a sudden blockage of the artery.
Heart disease affects more than 1.2 million Australians and coronary artery disease is the leading cause of death in Australia. However, more than 50 per cent of patients who die of a heart attack may not have prior warning symptoms and the majority have less than 50 per cent artery narrowing.
Left undiagnosed, patients remain at risk, without getting the correct treatment thus escalating health care costs. With ageing populations and the demand for medical services rising globally, delays in responding can leave patients at risk.
Researchers at the University of Western Australia are developing a system for more accurate diagnosis and faster reporting of the heart computed tomography (CT) scan images and thus improving the quality and consistency of patient care.
The UWA team of experts in cardiac imaging and artificial intelligence has been awarded nearly $900,000 through a Medical Research Future Fund Frontiers grant, to develop a tool to predict the risk of coronary heart disease from heart CT scans.
Traditional methods using CT imaging of the heart are cumbersome and time-consuming and need highly trained experts to achieve high accuracy.
Led by Professor Girish Dwivedi, the UWA Wesfarmers chair in cardiology, the team, including Professor Mohammed Bennamoun, Professor Farid Boussaid, Dr Frank Sanfilippo and Dr Abdul Ihdayhid, will create an artificial intelligence-based risk assessment tool that will better detect plaque on heart CT scans.
The tool is designed to determine if plaque build-up has narrowed the coronary arteries and identify those patients most at risk of adverse cardiovascular events, ultimately reducing the number of heart attacks and deaths.
Artificial intelligence (AI) makes it possible for computers to learn from experience, adjust to new inputs and perform human-like tasks. AI works by combining large amounts of data with fast, repeated processing and intelligent algorithms, allowing the software to learn automatically from recognition of patterns in the data, without explicitly being programmed for where to look or what to conclude.
Professor Dwivedi said bringing new and disruptive technologies to medical imaging and risk prevention will accelerate new technological advances in health care.
“Our artificial intelligence-based risk prediction system will be able to define groups based on heart CT scans and will identify patients at risk of heart attack and also those who would most benefit from treatment,” he said.
“Preventing, reducing or even delaying the onset of heart attack will drive massive savings in public health costs.”
UWA has partnered with Artrya, a Perth based medical technology company. Artrya is an applied artificial intelligence healthcare company that works alongside clinicians to improve the diagnosis of coronary heart disease and develop a holistic overview of a patient at risk. They develop deep learning algorithms enabling the prediction and prevention of acute coronary event.
“Partnering with Artrya shows that academics and industry can jointly innovate and create solutions using advanced technology such as artificial intelligence to improve the health of Australians,” said Professor Dwivedi.