Automatic Detection of Seismocardiogram Sensor Misplacement for Robust Pre-Ejection Period Estimation in Unsupervised Settings

Abstract

Seismocardiography (SCG), the measurement of the local chest vibrations due to the movements of blood and the heart, is a non-invasive technique for assessing myocardial contractility via the pre-ejection period (PEP). Recently, SCG-based extraction of PEP has been shown to be an effective means of classifying decompensated from compensated heart failure patients, and thus can be potentially used for monitoring such patients at home. Accurate extraction of PEP from SCG signals hinges on lab-based population data (i.e., regression curves) linking particular time-domain features of the SCG signal to corresponding features from reference standard bulky instruments such as impedance cardiography (ICG). Such regression curves, in the case of SCG, have always been estimated based on the “ideal” positioning of the SCG sensor on the chest. However, in settings such as the home where users may position the SCG measurement hardware on the chest without supervision, it is likely that the sensor will not always be placed exactly on this “ideal” location on the sternum, but rather on other positions on the chest as well. In this study, we show for the first time that the regression curve for estimating PEP from SCG signals differs significantly as the position of the sensor changes. We further devise a method to automatically detect when the sensor is placed in any position other than the desired one in order to avoid inaccurate systolic time interval estimation. Our classification algorithm for this purpose resulted in 0.83 precision and 0.82 recall when classifying whether the sensor is placed in the desired position or not. The classifier was tested with heartbeats taken both at rest, and also during exercise recovery to ensure that waveform changes due to positioning could be accurately discriminated from those due to physiological effects.

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.…”

“…Simple time domain [47,61,81,82,107] Statistical time domain [41,56,65,106] Simple frequency domain [41,56] Statistical frequency domain [40,41,47,78] 2.4. Machine Learning…”

“…Other studies [40,65] sought to classify SCG signals according to the lung volume phases as opposed to inspiration/expiration. Classification methods were also utilized to help identify fiducial points on the SCG signals [61], artefact presence in the SCG [98], and identification of the sensor location [41,82].…”

Detection and Analysis of Heartbeats in Seismocardiogram Signals

“…Seismocardiograms are typically obtained from MEMS accelerometers, firmly attached to the subject's chest, close to the sternum, by means of dedicated fixtures [11]. Some works explore different sensor placements over the chest wall, as reported in [12]; in [13], the impact of sensor placement on the estimation of Pre-Ejection Period (PEP, a relevant metric used in heart dynamics monitoring) is assessed. Reliable markers for cardiac activity were also found in gyroscope traces [14], a technique named GyroCardioGraphy (GCG).…”