Although medicine has developed significantly and continues to develop, it is still not possible to prevent some things. At the top of these things is sudden cardiac arrest. Studies show that one out of every five people who lost their lives today dies due to sudden cardiac arrest.
Many people are unaware of whether they are at risk of sudden cardiac arrest. Here, scientists have developed a new algorithm that will allow people to learn whether they are at risk of sudden cardiac arrest and to take precautions accordingly. The algorithm developed by scientists from John Hopkins University makes use of deep learning technology.
Can predict whether there is a risk in 10 years and when exactly the heart will stop:
‘Survival Study of Cardiac Arrhythmia Risk (Cardiac Arrhythmia Survival Study) – SSCAR) uses border networks to create a personalized assessment of survival for each patient with heart disease. This algorithm, which is the first in the world, calculates the probability of sudden cardiac arrest in 10 years with risk measurements and presents the most expected time with ‘high accuracy’.
The algorithm used images in the University hospital where the damage distribution of real damaged hearts can be seen to train the algorithm. The images presented to the algorithm with high contrast paved the way for the algorithm to see details that cannot be seen with the naked eye. The algorithm realizes its assumptions by comparing the images it contains with the images presented to it.
The algorithm’s estimations were able to produce results that were more accurate than the claims of the doctors in each test performed. In addition, tests performed with different cardiac histories and different imaging data of patient clusters independent of 60 health centers in the USA also gave high accuracy results. The new algorithm has become one of the most valuable steps in the role of artificial intelligence in health.