ECG-derived respiration estimation from single-lead ECG using gaussian process and phase space reconstruction methods

Respiratory activity influences electrocardiographic measurements (ECG) in various ways. Therefore, extraction of respiratory information from ECG, namely ECG-derived respiratory (EDR), can be used as a promising noninvasive method to monitor respiration activity. In this paper, an automatic EDR extraction system using single-lead ECG is proposed. Respiration effects on ECG are categorized into two different models: additive and multiplicative based models. After selection of a proper model for each subject using a proposed criterion, gaussian process (GP) and phase space reconstruction area (PSRArea) are introduced as new methods of EDR extraction for additive and multiplicative models, respectively. We applied our algorithms on Fantasia database from Physionet, and the performance of our algorithms is assessed by comparing the EDR signals to the reference respiratory signal, using the normalized cross-correlation coefficient. The proposed method is also compared with other EDR techniques in the literature. The extracted EDRs using GP and PSRArea methods, considering their selected appropriate models, show mean correlations of 0.706 and 0.727 with reference respiration which is significantly better than most of the state-of-the-art methods. It can be seen that after selecting the model of each subject and using either PSRArea or GP (combined method), the correlation result, 0.717, is improved. Statistical significant differences (p < 0.05) are found in the correlation coefficients of our algorithms and most of the state-of-the-art methods, showing that our combined methods outperforms them and is comparable to the well-known EDR technique, principal component analysis (PCA) based EDR extraction. A model selection criterion and two EDR extraction methods, GP and PSRArea, have been proposed. The combined method using GP and PSRArea following model selection for each subject yields EDR estimation system which results better than most of the state-of-the-art single-lead EDR extraction in terms of correlation coefficient and can be used as a promising algorithm to obtain ECG-derived respiratory signals.