- Cardiac arrest occurs when the heart stops beating due to irregular heart rhythm.
- When a patient can have a cardiac attack that can be predicted through the new artificial intelligence system.
- This AI system is created on the basis of standard clinical data of a patient of several years.
- But this AI system cannot fully replace the conventional doctor examination.
With the new form of artificial intelligence, the probability of cardiac arrest chances of a person can be predicted more accurately than a doctor, which was invented by the research team of Johns Hopkins University in Maryland.
“Sudden cardiac death caused by arrhythmia accounts for as many as 20 percent of all deaths worldwide, and we know little about why it’s happening or how to tell who’s at risk,” said Natalia A. Trayanova, a senior author of the study and a professor of biomedical engineering and medicine at Johns Hopkins, in a press release.
“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,” she explained. “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.”
How it works
The fellow researchers use a neural network to build a personalized survival assessment system for each patient having heart disease. These risk measurement systems provide the chances of higher accuracy of death due to cardiac arrest over 10 years.
This deep learning technology is called Survival Study of Cardiac Arrhythmia Risk or SSCAR. The cardiac scarring caused by heart disease which results in lethal arrhythmia also can be studied under this system.
Currently, they are using contrast-enhanced cardiac images that can visualize scar distribution from hundreds of cardiac patients at John Hopkins hospital with cardiac scarring technology to create an algorithm to detect the patterns of cardiac arrest which are not visible to the naked eye. At present, those images are only used for studying certain aspects of cardiac scarring like volume and mass. But in the future, there shall be much important information that can be found.
“The images carry critical information that doctors haven’t been able to access,” said by 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 research team is now working to develop a second neural network to gather the standard clinical data of the patient from the last 10 years of various factors such as patients’ age, weight, race, and prescribed drug usage.
They also added that to check the accuracy of AI prediction about the cardiac disease of an individual patient, they validate the report in 60 different health centers across the United States. This was also carried out with different cardiac histories with different imaging data.
“This has the potential to significantly shape clinical decision-making regarding arrhythmia risk and represents an essential step towards bringing patient trajectory prognostication into the age of artificial intelligence,” said Trayanova, co-director of the Alliance for Cardiovascular Diagnostic and Treatment Innovation. “It epitomizes the trend of merging artificial intelligence, engineering, and medicine as the future of healthcare.”
In the future, they have a plan for building up further new algorithms for detecting other cardiac diseases also. According to Trayanova, the deep-learning concept could also be developed for other fields of medicine that rely on visual diagnosis