Respiratory sinus arrhythmia (RSA) represents a physiological phenomenon of cardiopulmonary interaction. It is known as a measure of efficiency of the circulation system, as well as a biomarker of cardiac vagal and well-being. In this article, RSA is modeled as modulation of heart rate by respiration in an interactive cardiopulmonary system with the most effective system state of resonance. By mathematically modeling of this modulation, we propose a quantitative measurement for RSA referred to as “Cardiopulmonary Resonance Function (CRF) and Cardiopulmonary Resonance Indices (CRI),” which are derived by disentanglement of the RR-intervals series into respiratory-modulation component, R-HRV, and the rest, NR-HRV using spectral G-causality. Evaluation of CRI performance in quantifying RSA has been conducted in the scenarios of paced breathing and in the different sleep stages. The preliminary experimental results have shown superior representation ability of CRF and CRI compared to Heart Rate Variability (HRV) and Cardiopulmonary Coupling index (CPC).

The cyclic alternating pattern is the periodic electroencephalogram activity occurring during non-rapid eye movement sleep. It is a marker of sleep instability and is correlated with several sleep-related pathologies. Considering the connection between the human heart and brain, our study explores the feasibility of using cardiopulmonary features to automatically detect the cyclic alternating pattern of sleep and hence diagnose sleep-related pathologies. By statistically analyzing and comparing the cardiopulmonary characteristics of a healthy group and groups with sleep-related diseases, an automatic recognition scheme of the cyclic alternating pattern is proposed based on the cardiopulmonary resonance indices. Using the Hidden Markov and Random Forest, the scheme combines the variation and stability of measurements of the coupling state of the cardiopulmonary system during sleep. In this research, the F1 score of the sleep-wake classification reaches 92.0%. In terms of the cyclic alternating pattern, the average recognition rate of A-phase reaches 84.7% on the CAP Sleep Database of 108 cases of people. The F1 score of disease diagnosis is 87.8% for insomnia and 90.0% for narcolepsy.