On the Design of an Efficient Cardiac Health Monitoring System Through Combined Analysis of ECG and SCG Signals

Abstract

Cardiovascular disease (CVD) is a major public concern and socioeconomic problem across the globe. The popular high-end cardiac health monitoring systems such as magnetic resonance imaging (MRI), computerized tomography scan (CT scan), and echocardiography (Echo) are highly expensive and do not support long-term continuous monitoring of patients without disrupting their activities of daily living (ADL). In this paper, the continuous and non-invasive cardiac health monitoring using unobtrusive sensors is explored aiming to provide a feasible and low-cost alternative to foresee possible cardiac anomalies in an early stage. It is learned that cardiac health monitoring based on sole usage of electrocardiogram (ECG) signals may not provide powerful insights as ECG provides shallow information on various cardiac activities in the form of electrical impulses only. Hence, a novel low-cost, non-invasive seismocardiogram (SCG) signal along with ECG signals are jointly investigated for the robust cardiac health monitoring. For this purpose, the in-laboratory data collection model is designed for simultaneous acquisition of ECG and SCG signals followed by mechanisms for the automatic delineation of relevant feature points in acquired ECG and SCG signals. In addition, separate feature points based novel approach is adopted to distinguish between normal and abnormal morphology in each ECG and SCG cardiac cycle. Finally, a combined analysis of ECG and SCG is carried out by designing a Naïve Bayes conditional probability model. Experiments on Institutional Review Board (IRB) approved licensed ECG/SCG signals acquired from real subjects containing 12,000 cardiac cycles show that the proposed feature point delineation mechanisms and abnormal morphology detection methods consistently perform well and give promising results. In addition, experimental results show that the combined analysis of ECG and SCG signals provide more reliable cardiac health monitoring compared to the standalone use of ECG and SCG.

Physical Wellbeing Monitoring Employing Non-Invasive Low-Cost and Low-Energy Sensor Socks

“…Authors like Sahoo et al [ 14 ] have presented a continuous and non-invasive cardiac health monitoring system using unobtrusive sensors which aims to provide a feasible and low-cost alternative to foresee possible cardiac anomalies in an early stage. They used a novel low-cost, non-invasive seismocardiogram (SCG) signal along with ECG signals which are jointly investigated for a robust cardiac health monitoring.…”

Recent Advances in Seismocardiography

“…Most research groups applied conventional band-pass filters to remove baseline wandering, body movements, and breathing artefacts from SCG signals [26,36,38,41,45,46,55,[58][59][60][61][62][63]67,71,75,76,[78][79][80]82,93]. A few studies utilized or proposed more advanced noise removal techniques [64,76,88,[94][95][96].…”

“…More studies are needed that compare different filtering methods in clinical and ambulatory settings. [26,36,38,41,45,46,55,[58][59][60][61][62][63]67,71,75,76,[78][79][80]82,93] Adaptive filtering Motion artefact removal [88,95] Averaging theory Motion artefact removal [101] Comb filtering Removing respiration noise from radar signal [50] Empirical mode decomposition Baseline wandering, breathing and body movement artefact removal [76,94,95] Independent component analysis Motion artefact removal [102] Median filtering [96] Morphological filtering [95] Polynomial smoothing Motion artefact removal [103] Savitzky-Golay filtering Motion artefact removal [83,103] Wavelet denoising Segmentation of HSs and SCG [64,95,96] Wiener filtering [94] 2.…”

Detection and Analysis of Heartbeats in Seismocardiogram Signals

“…Besides systolic time intervals annotation, the morphology of SCG signals also carries relevant information. The authors in [25] design hand-crafted features acquired from ECG and SCG traces to detect anomalous heart activity. From a different perspective, raw and spectral features were successfully extracted from SCG traces by means of Convolutional Neural Networks (CNN), leading to personalized heart biometrics [26].…”