Automatic Classification of Normal–Abnormal Heart Sounds Using Convolution Neural Network and Long-Short Term Memory

Abstract

The phonocardiogram (PCG) is an important analysis method for the diagnosis of cardiovascular disease, which is usually performed by experienced medical experts. Due to the high ratio of patients to doctors, there is a pressing need for a real-time automated phonocardiogram classification system for the diagnosis of cardiovascular disease. This paper proposes a deep neural-network structure based on a one-dimensional convolutional neural network (1D-CNN) and a long short-term memory network (LSTM), which can directly classify unsegmented PCG to identify abnormal signal. The PCG data were filtered and put into the model for analysis. A total of 3099 pieces of heart-sound recordings were used, while another 100 patients’ heart-sound data collected by our group and diagnosed by doctors were used to test and verify the model. Results show that the CNN-LSTM model provided a good overall balanced accuracy of 0.86 ± 0.01 with a sensitivity of 0.87 ± 0.02, and specificity of 0.89 ± 0.02. The F1-score was 0.91 ± 0.01, and the receiver-operating characteristic (ROC) plot produced an area under the curve (AUC) value of 0.92 ± 0.01. The sensitivity, specificity and accuracy of the 100 patients’ data were 0.83 ± 0.02, 0.80 ± 0.02 and 0.85 ± 0.03, respectively. The proposed model does not require feature engineering and heart-sound segmentation, which possesses reliable performance in classification of abnormal PCG; and is fast and suitable for real-time diagnosis application.

Development of a Collaborative Robotic Platform for Autonomous Auscultation

“…This may represent a barrier for the healthcare professional. In addition, computer systems already exist to automatically classify heart and breath sound abnormalities with a very small error rate [38,39], paving the way to assisted diagnosis. Hence, the health professional can be released for more differentiated tasks.…”

Precision Diagnosis: An Automated Method for Detecting Congenital Heart Diseases in Children From Phonocardiogram Signals Employing Deep Neural Network

“…The suggested Xception model exhibited promise for rapid and accurate diagnosis of valvular heart disease, and it outperformed the competition. Discrete wavelet transformations (DWTs) and Mel-frequency cepstral coefficients (MFCCs) are extracted in the investigation of cardiac sound signal classification in [9]. The study utilizes SVMs, deep neural networks, and k-nearest neighbors (kNN) for reliable classification.…”

“…The author in [8] utilized both CinC and Pascal datasets to extract MFCC features and implemented a CNN algorithm, resulting in an accuracy of 95.24%. In a study utilizing the CinC dataset, the author in [9] utilized MFCC and Wavelet Entropy features, applied the RF algorithm, and obtained an accuracy of 92%. Author in [10] retrieved features such as RMSE, Skewness, and Kurtosis from a dataset of 1000 samples from CinC.…”

Adopting Artificial Intelligence Algorithms for Remote Fetal Heart Rate Monitoring and Classification using Wearable Fetal Phonocardiography

“…This subsection presents the comparative performance of the proposed AI-FHR to existing methods such as PFM-FPG [36], PCG CNN-LSTM [39], and Mobile FPCG [37] in terms of validation metrics such as accuracy, Sensitivity, F1-Score, Positive predictive values, and complexity. Below is a detailed analysis of each metric between the proposed work and the existing works.…”