With the help of Artificial Intelligence (AI), researchers have developed a neural network approach that can accurately identify congestive heart failure with 100 percent accuracy through analysis of just one raw electrocardiogram (ECG) heartbeat.
Heart failure (CHF) is a chronic progressive condition that affects the pumping power of the heart muscle. High prevalence, significant mortality and sustained health care costs, require urgent skilled discovery procedures associated with clinical practitioners and health systems.
Researchers have worked to address these critical concerns by using sensory neural networks (CNN) – hierarchical neural networks that are highly effective at identifying patterns and structures in data.
“We trained and tested the CNN model on a massively available ECG dataset, featuring CHF as well as healthy, non-arrhythmic heart subjects. Our model provided 100 percent accuracy: only one heartbeat We investigate whether there is a person or not. There is heart failure, “said the study researcher Sebastiano Massaro, a Surrey scientist in the UK The school has an Associate Professor.
“Our model has been known to be able to identify the morphological features of the ECG even earlier,” said Massaro.
Published in the journal Biomedical Signal Processing and Control, the research has greatly improved existing CHF detection methods, which typically focus on heart rate variability, which while being effective, are time-consuming and prone to errors.
In contrast, their new model uses a combination of advanced signal processing and machine learning tools on raw ECG signals, achieving 100 percent accuracy.
“Approximately 26 million people worldwide are affected by one form of heart failure, our research presents a major advancement on current functioning,” said study leader Leandro Peccia of the University of Warwick.