The congestive heart failure (CHF) is a progressive chronic condition that affects the pumping power of the heart muscles. Now, thanks to the development of a neural network, congestive heart failure can be identified with 100% accuracy through the analysis of a single heartbeat without an electrocardiogram (ECG).
Just a beat
Published in the Biomedical Signal Processing and Control Journal by researchers at the University of Surrey, the results of this study suggest a drastic improvement of existing CHF detection methods, which generally focus on heart rate variability that, While it is effective, it consumes a lot of time and is prone to errors.
It is not what happens with this new approach, which makes zero errors, based on highly effective hierarchical neural networks to recognize patterns and structures in the data.
Specifically, the new model uses a combination of advanced signal processing and machine learning tools in raw ECG signals.
The model is also one of the first that can identify the morphological characteristics of the ECG specifically associated with the severity of the condition.
With approximately 26 million people worldwide affected by a form of heart failure, this research presents an important advance in the current methodology, allowing patients an early and more efficient diagnosis and thus relieving economic pressures on existing resources.
