An equipment framework for heart sounds monitor in noisy environments: Regular paper

Compared to other heart monitoring approaches, such as electrocardiography (EGG), Color Doppler and Magnetic Resonance Imaging Diagnosis, heart sounds detection is much safer and cheaper, which can be accomplished in ambulatory patients, thus has a broader applicability. Changes and murmurs of heart sounds often provide the earliest information of abnormal heart status, which makes heart sound monitor important for the diagnosis of cardiovascular disease. This paper aims to design an equipment framework for monitoring heart sounds in noisy environments, which can achieve signal acquisition, transmission and automatic analysis. For the signal acquisition part, a novel equipment prototype is designed by separately using the two channels of digital sounds, one to record mixed signals of heart sounds and environmental noises, while the other to record only environmental noises as a reference. These signals are then transferred to a server for further analysis through a wireless sensor network in the signal transmission part. In the signal analysis part, the environmental noise is filtered and the purified heart sound is analyzed. Experiments with real data demonstrate that our approach can correctly classify all the tested heart sounds even those with heart diseases not included in the training data.