A novel embedded system design for the detection and classification of cardiac disorders

Abstract

Phonocardiogram (PCG) signals hold significant prognostic and diagnostic information about cardiac health. Numerous PCG or heart sound based automated detection algorithms were previously proposed to assist the disease diagnosis process. Most of the previous studies only focused on algorithmic development. This study presents an intelligent, portable, and low‐cost embedded system for the classification of cardiac disorders associated with heart murmurs. Different stages corresponding to the developed embedded system implementation are summarized as follows: The first stage consists of the acquisition of PCG signals of both normal and patients from various hospitals with a customized and low‐cost stethoscope. The second stage describes the preprocessing, localization of S1 and S2 heart sounds, and the extraction of systole and diastole from a heart signal with an empirical mode decomposition integrated with the self‐developed algorithm. In the third stage, discriminant features are extracted to represent various cardiac classes of PCG signals in a compact manner. In the final stage of the algorithm, the k‐nearest neighbors classifier is trained and tested to distinguish between normal and four cardiac disorders. The proposed algorithm achieved 94% mean accuracy through comprehensive experimentation. The cardiac disorders classification algorithm is implemented on a RP‐based embedded system. Software application with an interactive graphical interface is also designed to assist users. The developed intelligent system is portable, low‐cost, and it enables regular patient‐monitoring. The proposed system has the potential to be employed at remote locations where the availability of doctors remains challenging.

WITHDRAWN: A robust method for heart sounds classification based on empirical mode decomposition adaptive reconstruction.

“…Author details 1 Department of Light Sources and Illuminating Engineering, Fudan University, Shanghai, 200433, China. 2 Department of Health Management Center, Zhongshan Hospital, Fudan University, 180 Fenglin Rd, Shanghai, 200032, China.…”

“…The process of acquiring heart sound signal is easy to be interfered by external environment. Heart sound reduction has been accomplished through many Methods, such as low pass filter [2][3][4], adaptive filters [5], and moving average filter [6]. In recent years, the research on wavelet theory has developed rapidly, and wavelet denoising method has also been applied in heart sound denoising [7][8].…”

Machine learning‐based classification of multiple heart disorders from PCG signals

“…KNN assigns labels to test features based on their distance to specific neighbourhood features in the training set, in the same way as KNN performs the classification of new query points. The KNN algorithm is a non‐parametric, lazy classification method with sample‐based learning (Riaz et al, 2021). It calculates the distance function between each sample in the training dataset and each query point and then selects the minimum number of nearest neighbours for each class.…”

Exploiting Data-Efficient Image Transformer-Based Transfer Learning for Valvular Heart Diseases Detection

“…Database Features Classification technique Domain Accuracy (%) [5] The [6] PhysioNet/CinC Statistical, Frequency XGBoost ML 92.90 [7] PhysioNet/CinC Time, MFCCs and Statistical Neural network (NN) ML 93.33 [11] PhysioNet/CinC MFCC Decision tree ML 86.40 [12] PhysioNet/CinC MFCCs NN ML 92.00 [13] PhysioNet/CinC LPC, Entropy, MFCCs, DWT and PSD NN ML 91.50 [14] Private MFCC DNN DL 91.12 [15] PhysioNet/CinC MFCCs DNN DL 93.00 [16] The HSM database TQWT, EMD and Shannon energy RBF neural networks ML 98.48 [17] PhysioNet/CinC MFSCs SVM ML 92.00 [18] PhysioNet/CinC Gram polynomial and Fourier transform NN ML 94.00 [19] PASCAL DWT Hidden Markov Models ML 92.74 [20] PhysioNet/CinC Wavelet CNN DL 81.20 [21] PhysioNet/CinC Modified frequency slice wavelet transform CNN DL 94.00 [22] PhysioNet/CinC Frequency spectrum, Energy and Entropy SVM ML 88.00 [23] Private EMD and MFCCs SVM ML 91.00 [24] MIT heart sounds Frequency SVM ML 98.00 [25] PhysioNet/CinC Time, MFCC, DWT and Wavelet SVM ML 82.40 [26] The HSM database FMFE + MFCC SVM ML 99.00 [27] PhysioNet/CinC Spectral SVM ML 98.00 [28] The HSM database Time-frequency MCC ML 98.33 [29] PhysioNet/CinC Cochleagram MLP ML 95.00 [30] The HSM database Time-frequency magnitude and phase RF ML 95.12 [31] Private MFCC KNN ML 98.00 [32] Private EMD KNN ML 94.00 [33] PASCAL MFCCs KNN ML 97.00 [34] Private MFCCs KNN ML 92.60 [37] PhysioNet/CinC MFCCs LSTM DL 98.61 [38] PhysioNet/CinC Time, Frequency and Time-frequency DNN DL 92.60 [39] PhysioNet/CinC MFCC+ MFSC 2D-CNN DL 81.50 [40] PhysioNet/CinC Mean, Standard deviation and Power spectrum CNN DL 86.02 [41] PhysioNet/CinC Spectrogram, Mel-spectrogram and MFCCs CNN DL 86.05 [42] The HSM database Normalized signals CNN...…”