EXTENDED STATE KALMAN FILTERING BASED FETAL ECG, MATERNAL ECG EXTRACTION & ESTIMATE THE MATERNAL BLOOD PRESSURE USING SINGLE CHANNEL RECORDINGS?

The fetal ECG (fECG) provides a mean to monitor non-invasively the fetal heart activity. In this paper, an extended nonlinear Bayesian filtering framework for extracting electrocardiograms (ECGs) from a single channel as encountered in the fetal and maternal ECG extraction from abdominal sensor is presented. The recorded signals are modeled as the summation of several ECGs. Each of them is described by a nonlinear dynamic model, previously presented for the generation of a highly realistic synthetic ECG. A modified version of this model is used in several Bayesian filters, including the extended kalman filter, Extended Kalman smoother, and Unscented Kalman filter. Consequently, each ECG has a corresponding term in this model and can thus be efficiently discriminated even if the waves overlap in time. This framework is also validated on the extractions of fetal ECG and maternal ECG from actual abdominal recordings, as well as of actual twin magneto cardiograms. In this paper, maternal blood pressure is estimated based on kalman filtering using single channel recordings.