AI tool could help predict heart attacks
Professor Natalia Trayanova, Johns Hopkins University, USA, has developed an artificial intelligence and bioengineering tool that could prove to be life-saving for more than four million Australians affected by cardiovascular disease (CVD).
The tool was showcased at the Bionics Institute 2022 Graeme Clark Oration in Melbourne.
Using data-driven machine learning and biophysics-based modelling, Trayanova has created ‘digital heart twins’ — virtual replicas of a person’s heart that can be used to forecast progress of heart disease, estimate the risk of heart attacks and inform treatment decisions.
“My AI technology uses algorithms created from MRIs and PET scans, in combination with deep learning of clinical data, to predict a patient’s risk of sudden cardiac death over a period of 10 years,” Trayanova said.
The application of Trayanova’s technology could be key to reducing the burden on our country’s healthcare system, as CVD costs the Australian economy almost $12 billion annually (2018–2019).
She said, “I envisage a future where re-hospitalisations and repeat procedures are reduced; shifting heart disease treatment options from being based on the state of the patient today, to optimising the state of the patient for the future.”
Bionics Institute CEO Robert Klupacs said the Institute was proud to be principal sponsor of the 2022 Graeme Clark Oration, a science event with a long history of showcasing eminent biomedical scientists.
“Over 1000 Melburnians have registered to join us at the Oration and learn about the future of heart health care from Professor Trayanova — a pioneer in the field of computational cardiology. This is an event not to be missed,” he said.
Alfred Health trials eye-tracking tech to assess brain function
The Alfred hospital has commenced clinical trials with BrainEye to screen for neurological...
Australian regions with high cardiac arrest rates and low CPR: study
Australia has about 26,000 out-of-hospital cardiac arrests annually, with only 12% of patients...
Non-invasive 'virtual' biopsy for skin cancer diagnosis
Researchers have developed a new imaging method that allows clinicians to analyse the skin...
