Toward prediction of physiological state signals in sleep apnea

Abstract

A recurrent connectionist model is described to predict dynamic respiratory state in the apneic sleeping patient. The time-domain model of nonlinear time-lagged interactions between heart rate, respiration, and oxygen saturation was developed to implicitly embed the dynamics of the respiration and cardiovascular control systems. Multiple future time scales were enforced on the network during training to explore the limits of the prediction horizon and produce a global representation of dynamic state trajectory. Predicted apneic respiration state results are presented in terms of invariant geometric statistics (largest Lyapunov exponent lambda L and correlation dimension Dc). The lambda L prediction error was 13%, while Dc error was within 9% of the true time series value. The magnitude of these errors may fall within experimental noise levels. This methodology may eventually be useful in dynamic control of continuous positive airway pressure (CPAP) therapy devices, and may lead to increased patient compliance with this therapy.