Respiratory rate estimation from multi-channel signals using auto-regulated adaptive extended Kalman filter

Background: Respiration rate (RR) is a major cause for false alarms in intensive care units (ICU) and is primarily impaired by the artifact prone signals from skin-attached electrodes. Catheter-integrated esophageal electrodes are an alternative source for multi-channel physiological signals from multiple organs such as the heart and the diaphragm. Nonlinear estimation and sensor fusion are promising techniques for extracting the respiratory activity from such multi-component signals, however, pathologic breathing patterns with rapid RR changes typically observed in patient populations such as premature infants, pose significant challenges.
Methods: We developed an auto-regulated adaptive extended Kalman filter (AA-EKF), which iteratively adapts the system model and the noise parameters based on the respiratory pattern. AA-EKF was tested on neonatal esophageal observations (NEO), and also on simulated multi-components signals created using waveforms in CapnoBase and ETNA databases.
Results: AA-EKF derived RR (RRAA-EKF) from NEO had lower median (inter-quartile range) error of 0.1 (10.6) breaths per minute (bpm) compared to contemporary neonatal ICU monitors (RRNICU): −3.8 (15.7) bpm (p <0.001). RRAA-EKF error of −0.2 (3.2) bpm was achieved for ETNA wave forms and a bias (95% LOA) of 0.1 (−5.6, 5.9) in breath count. Mean absolute error (MAE) of RRAA-EKF with Capnobase waveforms, as median
(inter-quartile range), at 0.3 (0.2) bpm was comparable to the literature reported values.
Discussion: The auto-regulated approach allows RR estimation on a broad set of clinical data without requiring extensive patient specific adjustments. Causality and fast response times of EKF based algorithms makes the AA-EKF suitable for bedside monitoring in the ICU setting.