Monitoring chest compressions using finger photoplethysmography in out-of-hospital cardiac arrest

Abstract

Quality cardiopulmonary resuscitation (CPR) is crucial to increase the probability of survival during out-of-hospital cardiac arrest (OHCA). Continuous chest compressions (CCs) provided with appropriate rate are recommended by the guidelines. Currently, defibrillators and monitors may integrate additional hardware to monitor CCs and give feedback to the rescuer to align CC rate with recommended values. Photoplethysmogram (PPG) obtained with pulse oximeters measures the oxygen saturation in the blood using non invasive and inexpensive technology. This study proposes a method based on the finger PPG to detect the presence of CCs and compute the CC rate. A total of 153 segments from 66 OHCA patients, with 470 min and 48496 CCs, were analyzed. The algorithm classifies 5 s windows as either CC or CC-pause using a logistic regression classifier with Lasso regularization based on time, spectral, correlation, statistical and entropy features. The rate was computed for windows with CCs using the autocorrelation function. Results were compared to the ground truth obtained from the compression depth signal derived from an sternal accelerometer. The method was evaluated using 10 fold cross-validation, and the median (IQR) for 5 feature model were 90.7 (6.3) % sensitivity, 98.3 (1.3) % positive predictive value, 94.6 (3.1) % F 1 and 94.4 (4.8) % area under the curve. The median (IQR) of the absolute error in CC rate was 1.7 (2.7) min −1 , with 2.6 (9.1) % of the windows with errors above 10 %. This is the first approach that analyzes the feasibility of the PPG to monitor CPR, and an accurate automated solution based on a multifeature classification model was demonstrated.