The robustness of Random Forest and Support Vector Machine Algorithms to a Faulty Heart Sound Segmentation.

Cardiac auscultation is the key exam to screen cardiac diseases both in developed and developing countries. A heart sound auscultation procedure can detect the presence of murmurs and point to a diagnosis, thus it is an important first-line assessment and also cost-effective tool. The design automatic recommendation systems based on heart sound auscultation can play an important role in boosting the accuracy and the pervasiveness of screening tools. One such as step, consists in detecting the fundamental heart sound states, a process known as segmentation. A faulty segmentation or a wrong estimation of the heart rate might result in an incapability of heart sound classifiers to detect abnormal waves, such as murmurs. In the process of understanding the impact of a faulty segmentation, several common heart sound segmentation errors are studied in detail, namely those where the heart rate is badly estimated and those where S1/S2 and Systolic/Diastolic states are swapped in comparison with the ground truth state sequence. From the tested algorithms, support vector machine (SVMs) and random forest (RFs) shown to be more sensitive to a wrong estimation of the heart rate (an expected drop of 6% and 8% on the overall performance, respectively) than to a swap in the state sequence of events (an expected drop of 1.9% and 4.6%, respectively).

Do we really need a segmentation step in heart sound classification algorithms?

Cardiac auscultation is the key screening procedure to detect and identify cardiovascular diseases (CVDs). One of many steps to automatically detect CVDs using auscultation, concerns the detection and delimitation of the heart sound boundaries, a process known as segmentation. Whether to include or not a segmentation step in the signal classification pipeline is nowadays a topic of discussion. Up to our knowledge, the outcome of a segmentation algorithm has been used almost exclusively to align the different signal segments according to the heartbeat. In this paper, the need for a heartbeat alignment step is tested and evaluated over different machine learning algorithms, including deep learning solutions. From the different classifiers tested, Gate Recurrent Unit (GRU) Network and Convolutional Neural Network (CNN) algorithms are shown to be the most robust. Namely, these algorithms can detect the presence of heart murmurs even without a heartbeat alignment step. Furthermore, Support Vector Machine (SVM) and Random Forest (RF) algorithms require an explicit segmentation step to effectively detect heart sounds and murmurs, the overall performance is expected drop approximately 5% on both cases.

Classifying Heart Sounds Using Images of Motifs, MFCC and Temporal Features.

Cardiovascular disease is the leading cause of death in the world, and its early detection is a key to improving long-term health outcomes. The auscultation of the heart is still an important method in the medical process because it is very simple and cheap. To detect possible heart anomalies at an early stage, an automatic method enabling cardiac health low-cost screening for the general population would be highly valuable. By analyzing the phonocardiogram signals, it is possible to perform cardiac diagnosis and find possible anomalies at an early-term. Therefore, the development of intelligent and automated analysis tools of the phonocardiogram is very relevant. In this work, we use simultaneously collected electrocardiograms and phonocardiograms from the Physionet Challenge database with the main objective of determining whether a phonocardiogram corresponds to a "normal" or "abnormal" physiological state. Our main contribution is the methodological combination of time domain features and frequency domain features of phonocardiogram signals to improve cardiac disease automatic classification. This novel approach is developed using both features. First, the phonocardiogram signals are segmented with an algorithm based on a logistic regression hidden semi-Markov model, which uses electrocardiogram signals as a reference. Then, two groups of features from the time and frequency domain are extracted from the phonocardiogram segments. One group is based on motifs and the other on Mel-frequency cepstral coefficients. After that, we combine these features into a two-dimensional time-frequency heat map representation. Lastly, a binary classifier is applied to both groups of features to learn a model that discriminates between normal and abnormal phonocardiogram signals. In the experiments, three classification algorithms are used: Support Vector Machines, Convolutional Neural Network, and Random Forest. The best results are achieved when both time and Mel-frequency cepstral coefficients features are considered using a Support Vector Machines with a radial kernel.