A New Approach of Transparent and Explainable Artificial Intelligence Technique for Patient-Specific ECG Beat Classification

Abstract

ECG signals are carried important clinical information in the form of intervals and amplitude or morphology. Therefore, it is very important to identify these fiducial points effectively. The major limitations of the existing semi and fully-automatic ECG beat classification systems are extensive data requirements and low performance. This paper proposes a modified one-dimensional (1D) U-net architecture to find the exact locations of the important waves in the ECG signal. The proposed network utilised 1D convolutions instead of two-dimensional (2D), which is different from the traditional U-net. The encoder and decoder are the main components of the proposed 1D-U-net, where the encoder is designed to extract high-level features of the input data. The encoder contains two down-sampling stages, and the output of each stage in the encoder is sent to the corresponding decoder layer for further convolutional operations. The output of the decoder section concatenates with the respective encoder, which enables the network to perceive low-level and high-level features. The onset and offset of P, QRS, and T-waves in the ECG signal are identified using the proposed technique. The proposed method is validated on two publicly available databases, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">i.e.</i> , LUDB and MIT-BIH. The experimental results demonstrate that the performance of the proposed method is superior to the state-of-the-art techniques.