Deep Layer Kernel Sparse Representation Network for the Detection of Heart Valve Ailments from the Time-Frequency Representation of PCG Recordings

Abstract

The heart valve ailments (HVAs) are due to the defects in the valves of the heart and if untreated may cause heart failure, clots, and even sudden cardiac death. Automated early detection of HVAs is necessary in the hospitals for proper diagnosis of pathological cases, to provide timely treatment, and to reduce the mortality rate. The heart valve abnormalities will alter the heart sound and murmurs which can be faithfully captured by phonocardiogram (PCG) recordings. In this paper, a time-frequency based deep layer kernel sparse representation network (DLKSRN) is proposed for the detection of various HVAs using PCG signals. Spline kernel-based Chirplet transform (SCT) is used to evaluate the time-frequency representation of PCG recording, and the features like L1-norm (LN), sample entropy (SEN), and permutation entropy (PEN) are extracted from the different frequency components of the time-frequency representation of PCG recording. The DLKSRN formulated using the hidden layers of extreme learning machine- (ELM-) autoencoders and kernel sparse representation (KSR) is used for the classification of PCG recordings as normal, and pathology cases such as mitral valve prolapse (MVP), mitral regurgitation (MR), aortic stenosis (AS), and mitral stenosis (MS). The proposed approach has been evaluated using PCG recordings from both public and private databases, and the results demonstrated that an average sensitivity of 100%, 97.51%, 99.00%, 98.72%, and 99.13% are obtained for normal, MVP, MR, AS, and MS cases using the hold-out cross-validation (CV) method. The proposed approach is applicable for the Internet of Things- (IoT-) driven smart healthcare system for the accurate detection of HVAs.

Deep Learning for Heart Sound Analysis: A Literature Review

“…Yaseen et al employed Mel-frequency Cepstral Coefficients (MFCCs) combined with Discrete Wavelet Transform features as inputs to Deep Neural Network (DNN) classifiers, achieving an accuracy of 92.1% [80]. Ghosh et al extracted features from the time-frequency matrix of the heart sound recordings and input them into a Deep Layer Kernel Sparse Representation Network classifier, resulting in a 99.24% accuracy [57]. Abbas et al developed a novel attention-based transformer architecture that combines DL and vision transformer.…”

“…At last, 71 original articles were included. These studies can be broadly categorized into several groups: methods (15 papers, including heart sound segmentation [6, 7, 8, 9, 10, 11, 12, 13], noise cancellation [14, 15, 16], algorithm development [17, 18, 19], and database development [20]), cardiac murmurs detection (36 papers [21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56]), valvular heart disease (6 papers [57, 58, 59, 60, 61, 62]), congenital heart disease (4 papers [63, 64, 65, 66]), heart failure (4 papers [67, 68, 69, 70]), coronary artery disease (2 papers [71, 72]), rheumatic heart disease (2 papers [73, 74]), and extracardiac applications (2 papers [75, 76]).…”

Assessment of Dual-Tree Complex Wavelet Transform to Improve SNR in Collaboration with Neuro-Fuzzy System for Heart-Sound Identification

“…It's a combination of the application of short-time Fourier transform (STFT) with wavelet transform found by Mann et al [54]. In the few reported works, CT was employed to heart-sound recordings provided by the Github database (Not Phys-ioNet 2016) [55]. The pristine quality of the Github database was the most significant factor in increasing the classification accuracy regardless of the machine learning used [56,57].…”

Audiological Diagnosis of Valvular and Congenital Heart Diseases in the Era of Artificial Intelligence

“…Features are characteristics of the human brain that can be used to automatically identify and distinguish between objects, and they are similar in concept to variables in regression analysis. The features that can be recognized by machines are often in the form of numbers or symbols, while human experts extract physiological or pathological information from heart sounds through features such as the heart rate, heart rhythm, murmur timing and shape, heart sound frequency and the presence of additional heart sounds [ 19 ].…”