Knowing when someone is likely to suffer a heart attack would allow for lifesaving interventions. And thanks to a new artificial intelligence (AI) led approach pioneered by Johns Hopkins University researchers, this type of critical information – which would completely transform clinical decision making, could soon be at the fingertips of the medical profession.
The technology, described recently in Nature Cardiovascular Research, analyses images of the heart, along with background information on patients, to accurately predict if a sudden and fatal cardiac arrhythmia is likely within a 10-year period.
“Sudden cardiac death caused by arrhythmia accounts for as many as 20% of all deaths worldwide and we know little about why it’s happening or how to tell who’s at risk,” said senior author Natalia Trayanova, the Murray B. Sachs professor of Biomedical Engineering and Medicine. “There are patients who may be at low risk of sudden cardiac death getting defibrillators that they might not need and then there are high-risk patients that aren’t getting the treatment they need and could die in the prime of their life. What our algorithm can do is determine who is at risk for cardiac death and when it will occur, allowing doctors to decide exactly what needs to be done.”
Personalised survival assessment
The team at John Hopkins broke new ground in using neural networks to produce personalised survival assessments for sufferers of heart disease.
Taking cardiac images from hundreds of patients, each showing different levels of scarring, the researchers trained an algorithm to see patterns the naked eye can’t see. While a second neural network was fed a decade of standard patient data. It all resulted in predictions far more accurate than doctors could make, which was proven in tests on patients in 60 health centres across America.
“The images carry critical information that doctors haven’t been able to access,” said first author Dan Popescu, a former Johns Hopkins doctoral student. “This scarring can be distributed in different ways and it says something about a patient’s chance for survival. There is information hidden in it.”
The team is now developing additional algorithms to support early interventions for other cardiac diseases, with Trayanova adding that the technology can be developed for any conditions assessed using visual diagnosis.
