Real-Time Seismocardiogram Feature Extraction Using Adaptive Gaussian Mixture Models.

Abstract

Accurate and timely cardiovascular health evaluations can be provided by wearable systems that estimate key hemodynamic indices in real-time. A number of these hemodynamic parameters can be estimated non-invasively using the seismocardiogram (SCG), a cardiomechanical signal whose features can be linked to cardiac events such as aortic valve opening (AO) and aortic valve closing (AC). However, tracking a single SCG feature is often unreliable due to physiological state changes, motion artifacts, and external vibrations. In this work, an adaptable Gaussian Mixture Model (GMM) framework is proposed to concurrently track multiple AO or AC features in quasi-real-time from the measured SCG signal. For all extrema in a SCG beat, the GMM calculates the likelihood that an extremum is an AO/AC correlated feature. The Dijkstra algorithm is then used to isolate tracked heartbeat related extrema. Finally, a Kalman filter updates the GMM parameters, while filtering the features. Tracking accuracy is tested on a porcine hypovolemia dataset with various noise levels added. In addition, blood volume decompensation status estimation accuracy is evaluated using the tracked features on a previously developed model. Experimental results showed a 4.5 ms tracking latency per beat and an average AO and AC root mean square error (RMSE) of 1.47ms and 7.67ms respectively at 10dB noise and 6.18ms and 15.3ms at -10dB noise. When analyzing the tracking accuracy of all AO or AC correlated features, combined AO and AC RMSE remained in similar ranges at 2.70ms and 11.91ms respectively at 10dB noise and 7.50 and 16.35ms at - 10dB. The low latency and RMSE of all tracked features make the proposed algorithm suitable for real-time processing. Such systems would enable accurate and timely extraction of important hemodynamic indices for a multitude of cardiovascular monitoring applications, including trauma care in field settings.