Heart Valve Diseases Detection Based on Feature-Fusion and Hierarchical LSTM Network

Early detection and diagnosis of heart valve diseases (HVDs) can prevent cardiac arrest. This work proposes a novel feature fusion method for detecting HVDs using a phonocardiogram (PCG) signal. In the proposed method, first, the raw PCG signal is preprocessed. Then, two feature fusion models are proposed based on mel-frequency cepstral coefficients (MFCCs) and linear prediction cepstral coefficients (LPCCs). One model is the series feature fusion (SFF) model. Another is the parallel feature fusion (PFF) model. We propose a hierarchical long-short-term memory (HLSTM) network with a self-attention (SA) mechanism for both models. HLSTM encodes the sequential information of the fused features in different abstractions. Then, the SA module aggregates these encoded vectors based on their clinical relevance to detect HVDs. The efficacy of the proposed method is evaluated using two publicly available databases offered by Physionet challenge (CinC) 2016 and the GitHub repository. The CinC 2016 database is used for binary classification. The results show an overall accuracy (OA) of 98.76% and 98.29% for binary classification using SFF-HLSTM and PFF-HLSTM models. The heart sound murmur (HSM) database in the GitHub repository is used for multiclass classification. The results show an OA of 99.10% and 98.71% for multiclass classification using the SFF-HLSTM and PFF-HLSTM models, respectively. The promising results show that the proposed method is compelling enough for the preliminary automated diagnosis of HVDs in cardiac care units (CCUs).