Artificial intelligence can identify patients most likely to die from any medical disease. By examining the ECG reports AI can predict the future illness and can also predict the death.
To make this possible researchers from Geisinger Health system in pennsylvania analyzed 1.77 million ECG results. These results are of almost 400000 patients.
This data is used to train the machine learning models that will directly analyses the RAW ECG signals or relied on aggregated.
This neural network model is found accurate for predicting one-year advance risk of death.the neural network was able to accurately predict risk of death even in patients deemed by a physician to have a normal ECG.
It can accurately detect the risk in reports that were considered normal by Cardiologist.The model is very powerful.
“This is the most important finding of this study. This could completely alter the way we interpret ECGs in the future,” said Brandon Fornwalt, chair of the Department of Imaging Science and Innovation at Geisinger in Danville, Pennsylvania.
Study also revelas that this model can also analyze the ECG to predict arrhythmia.
An arrhythmia is a problem with the rate or rhythm of your heartbeat. It means that your heart beats too quickly, too slowly, or with an irregular pattern. When the heart beats faster than normal, it is called tachycardia.
“Incorporating these models into routine ECG analysis would be simple. However, developing appropriate care plans for patients based on computer predictions would be a bigger challenge,” said lead author Sushravya Raghunath.
Both studies are among the first to use AI to predict future events from an ECG rather than to detect current health problems.
Technologies like this are giving boost to medical facilities.Hope we will see this technique implementing as soon as possible.
Source : Gadgets360
Read more : Samsung W20 5G