Dual-Input Neural Network Integrating Feature Extraction and Deep Learning for Coronary Artery Disease Detection Using Electrocardiogram and Phonocardiogram

Abstract

Electrocardiogram (ECG) and phonocardiogram (PCG) signals reflect the electrical and mechanical activities of the heart, respectively. Although studies have documented that some abnormalities in ECG and PCG signals are associated with coronary artery disease (CAD), only few researches have combined the two signals for automatic CAD detection. This paper aims to differentiate between CAD and non-CAD groups using simultaneously collected ECG and PCG signals. To entirely exploit the underlying information in these signals, a novel dual-input neural network that integrates the feature extraction and deep learning methods is developed. First, the ECG and PCG features are extracted from multiple domains, and the information gain ratio is used to select important features. On the other hand, the ECG signal and the decomposed PCG signal (at four scales) are concatenated as a five-channel signal. Then, the selected features and the five-channel signal are fed into the proposed network composed of a fully connected model and a deep learning model. The results show that the classification performance of either feature extraction or deep learning is insufficient when using only ECG or PCG signal, and combining the two signals improves the performance. Further, when using the proposed network, the best result is obtained with accuracy, sensitivity, specificity, and G-mean of 95.62%, 98.48%, 89.17%, and 93.69%, respectively. Comparisons with existing studies demonstrate that the proposed network can effectively capture the combined information of ECG and PCG signals for the recognition of CAD.

Artificial intelligence in disease diagnostics: A critical review and classification on the current state of research guiding future direction

“…Future research needs to corroborate these findings in a diverse patient population [116]. This can be achieved by using heterogeneous and larger datasets (i.e., with N > 1,000 samples) [55,89,96,[101][102][103][104][105][106][107][108][109] with a range of formats such as X-ray images or ultrasounds [56,110] which are currently almost neglected. Furthermore, larger datasets should commonly be splitted using crossvalidation to approximate external validity thus generate better outcomes [68].…”

Artificial intelligence in hospitals: providing a status quo of ethical considerations in academia to guide future research

“…AI also assists medical experts within disease diagnostics such as ectopic pregnancies (De Ramón Fernández et al 2019 ), neonatal sepsis (López-Martínez et al 2019 ), or coronary artery disease (Li et al 2019a ). Medical data are thereby processed, evaluated, and classified using AI algorithms to estimate probabilities and enable clinicians to detect diseases earlier, thus allowing them to treat patients more effectively.…”

“…Current applications have been developed for particular tasks (e.g., Frick et al 2019a ), such as taking advantage of medical data to generate predictions or derive recommendations (Krittanawong et al 2017 ; Ku et al 2019 ). For example, AI monitors patients’ health conditions to support healing and regeneration (Pereira et al 2013 ) and assists physicians in diagnosing diseases (Mirbabaie et al 2021b ) and planning suitable treatments (e.g., De Ramón Fernández et al 2019 ; Li et al 2019a , b ; López-Martínez et al 2019 ). However, some AI approaches possess certain technical restrictions which can lead to diagnostic results not being transferable to other circumstances or not being comprehensible to humans, i.e.…”

Phonocardiogram Signal Processing for Automatic Diagnosis of Congenital Heart Disorders through Fusion of Temporal and Cepstral Features

“…An efficient method for the detection of abnormal PCG signals was proposed [ 32 ] using MFCCs and SVM with a classification accuracy of 92.6%. Classification of CAD and non-CAD subjects from PCG and ECG [ 33 ] using a dual input neural network (DINN) achieved specificity, accuracy, and G-mean of 89.17%, 95.62%, and 93.69%, respectively. A combination of machine learning and a deep learning model [ 34 ] for identification of congestive heart failure (CHF) from audio PCG obtained an accuracy of 93.2%.…”