Classification of nonstationary cardiac signals based on their spectral and probabilistic properties

This research presents a quantification method for the estimation of normalised correlation-spectral cardiac signal parameters that applies a probabilistic model of the cardiac signal as a random and a priori nonstationary process. The high sensitivity and informative significance of the proposed parameters of nonstationarity are confirmed by statistical cardiac signal classification (significance testing) and multi-alternative discrimination by types of cardiac state. The possibility is shown for the building of the absolute metric scales of the cardiac states.