Multichannel esophageal signals to monitor respiratory rate in preterm infants

BACKGROUND: Apnea of prematurity cannot be reliably measured with current monitoring techniques. Instead, indirect parameters such as oxygen desaturation or bradycardia are captured. We propose a Kalman filter-based detection of respiration activity and hence apnea using multichannel esophageal signals in neonatal intensive care unit patients. METHODS: We performed a single-center observational study with moderately preterm infants. Commercially available nasogastric feeding tubes containing multiple electrodes were used to capture signals with customized software. Multichannel esophageal raw signals were manually annotated, processed using extended Kalman filter, and compared with standard monitoring data including chest impedance to measure respiration activity. RESULTS: Out of a total of 405.4 h captured signals in 13 infants, 100 episodes of drop in oxygen saturation or heart rate were examined. Median (interquartile range) difference in respiratory rate was 0.04 (−2.45 to 1.48)/min between esophageal measurements annotated manually and with Kalman filter and −3.51 (−7.05 to −1.33)/min when compared to standard monitoring, suggesting an underestimation of respiratory rate when using the latter. CONCLUSIONS: Kalman filter-based estimation of respiratory activity using multichannel esophageal signals is safe and feasible and results in respiratory rate closer to visual annotation than that derived from chest impedance of standard monitoring.