Current trends and perspectives for automated screening of cardiac murmurs

Abstract

Although in high income countries rheumatic heart disease is now rare, it remains a major burden in low and middle income countries. In these world areas, physicians and expert sonographers are rare, and screening campaigns are usually performed by nomadic caregivers who can only recognise patients in an advanced phase of heart failure with high economic and social costs. Therefore, great interest exists regarding the possibility of developing a simple, low-cost procedure for screening valvular heart disease. With the development of computer science, the cardiac sound signal can be analysed in an automatic way. More precisely, a panel of features characterising the acoustic signal are extracted and sent to a decision-making software able to provide the final diagnosis. Although no system is currently available in the market, the rapid evolution of these technologies recently led to the activation of clinical trials. The aim of this note is to review the state of advancement of this technology (trends in feature selection and automatic diagnostic strategies), data available regarding performance of the technology in the clinical setting and finally what obstacles still need to be overcome before automated systems can be clinically/commercially viable.

Cardiovascular risk assessment in low-resource settings

“…Ultraportable, hand-held, pocket-sized imaging devices capable of producing two-dimensional and color images are now available [128] , but in LMICs, physicians and expert sonographers are scarce. The possibility that low-cost electronic stethoscope able to reach a provisional diagnosis of cardiac valve disease might be developed to screen heart murmurs in children [129] is a sector of high potential interest [130] . These devices might be accessible to unskilled personnel for screening purposes.…”

Cloud-Connected Patch-Worn Auscultation Device for Chest Sound Monitoring

“…Still, intelligent auscultation technology is not widely used to assist in clinical diagnosis [16], and better tools for research and application of computer-aided heart sound analysis are needed to grow this field [12]. In addition to this need, simple and automated screening methods for valvular heart disease would prove invaluable in low-and middle-income countries, where screening campaigns are usually limited to recognizing patients with advanced phases of heart failure [17].…”

Real-Time Smart-Digital Stethoscope System for Heart Diseases Monitoring

“…The history of the evolution of using PCG for diagnosis is stated in [20], whereas the signal processing steps involved are discussed in [21]. Recent trends in machine learning techniques (automatic classification) and the feature selection for it is stated in [22] and [23]. Similar to the problems in machine learning techniques, different techniques of automatic segmentation, extraction of relevant features, feature reduction, and state-of-the art algorithms for classification have been discussed in several hundred articles in the literature.…”