Inter-patient congestive heart failure automatic recognition using attention-based multi-scale convolutional neural network

Accurate classification of congestive heart failure (CHF) is essential to reduce the mortality of cardiovascular disease. Many existing researches suffer from unsatisfactory performance in inter-patient scheme closer to clinical application. To address this issue, this paper presents a novel attention-based multi-scale convolutional neural network (AMCNN) to automatically detect CHF. An effective multi-scale convolution structure is designed to enhance feature extraction capability. By combining channel attention mechanism, the output feature maps of multi-scale CNN are reweighted to explore the most decisive information. To validate the proposed method, we conducted experiments under both intra- and inter- patient schemes using long term ECGs from 73 subjects. The overall accuracies yield 99.97% and 99.71% respectively, outperforming traditional CNN 98.97% accuracy and the state-of-the-art methods. Moreover, our method performs well on unbalanced data with noise at speed of 0.000127 s for recognizing per segment, which has potential values to provide reliable diagnostic advice for cardiologists.