Automated Detection of Pulse Using Continuous Invasive Arterial Blood Pressure in Patients During Cardiopulmonary Resuscitation

Continuous invasive arterial blood pressure (ABP) and its characteristic waveform features are widely used to monitor cardiovascular health. The invasive ABP signal has been proven useful to guide therapy during cardiopulmonary resuscitation (CPR) of patients in cardiac arrest. Automated algorithms to compute ABP parameters were not designed to work during CPR, so their performance in this scenario is unknown. The aim of this study was to develop automated algorithms to detect pulse and measure physiological ABP variables during CPR. A dataset of 122 segments of invasive ABP were extracted during chest compression pauses from 26 patients with regular ECG during and a total duration of 262 min. The ABP was denoised using a stationary wavelet decomposition and pulse peaks were detected in the first difference of the ABP by applying adaptive thresholding. The following parameters were computed. systolic blood pressure (SBP), diastolic blood pressure (DBP), pulse pressure (PP) and heart rate (HR). The algorithm presented a median (IQR) Se/PPV/F1 of 97.6(17.5)=99.3(10.0)=97.2(10.1)% for diastolic peak detection, 4-points above the F1 obtained with Physionet's wabp algorithm. The absolute and relative errors were 0.62(1.40)mmHg and 1.22(1.62)%, 0.74(1.43)mmHg and 1.81(2.76)%, 1.13(1.67)mmHg and 4.68(4.86)%, 0.50(1.42)min and 0.58(1.31)% for SBP, DBP, PP and HR, respectively.