Dynamic Bayesian Model for Detecting Obstructive Respiratory Events by Using an Experimental Model

Abstract

In this study, we propose a model-based tool for the detection of obstructive apnea episodes by using ECG features from a single lead channel. Several sequences of recurrent apnea were provoked in separate 15-min periods in anesthetized rats during an experimental model of obstructive sleep apnea (OSA). Morphology-based ECG markers and the beat-to-beat interval (RR) were assessed in each sequence. These markers were used to train dynamic Bayesian networks (DBN) with different orders and feature combinations to find a good tradeoff between network complexity and apnea-detection performance. By using a filtering approach, the resulting DBNs were used to infer the apnea probability signal for subsequent episodes in the same rat. These signals were then processed using by 15-s epochs to determine whether epochs were classified as apneic or nonapneic. Our results showed that fifth-order models provided suitable RMSE values, since higher order models become significantly more complex and present worse generalization. A global threshold of 0.2 gave the best overall performance for all combinations tested, with Acc = 81.3%, Se = 69.8% and Sp = 81.5%, using only two parameters including the RR and Ds (R-wave downslope) markers. We concluded that multivariate models using DBNs represent a powerful tool for detecting obstructive apnea episodes in short segments, which may also serve to estimate the number of total events in a given time period.