ECG-based pulse detection during cardiac arrest using random forest classifier
- 209 Downloads
Sudden cardiac arrest is one of the leading causes of death in the industrialized world. Pulse detection is essential for the recognition of the arrest and the recognition of return of spontaneous circulation during therapy, and it is therefore crucial for the survival of the patient. This paper introduces the first method based exclusively on the ECG for the automatic detection of pulse during cardiopulmonary resuscitation. Random forest classifier is used to efficiently combine up to nine features from the time, frequency, slope, and regularity analysis of the ECG. Data from 191 cardiac arrest patients was used, and 1177 ECG segments were processed, 796 with pulse and 381 without pulse. A leave-one-patient out cross validation approach was used to train and test the algorithm. The statistical distributions of sensitivity (SE) and specificity (SP) for pulse detection were estimated using 500 patient-wise bootstrap partitions. The mean (std) SE/SP for nine-feature classifier was 88.4 (1.8) %/89.7 (1.4) %, respectively. The designed algorithm only requires 4-s-long ECG segments and could be integrated in any commercial automated external defibrillator. The method permits to detect the presence of pulse accurately, minimizing interruptions in cardiopulmonary resuscitation therapy, and could contribute to improve survival from cardiac arrest.
KeywordsPulse detection Cardiac arrest Random forest Pulseless electrical activity Pulsed rhythm
This work has been partially supported by the Spanish Ministerio de Economía y Competitividad, jointly with the Fondo Europeo de Desarrollo Regional (FEDER), project TEC2015-64678-R, by the University of the Basque Country via the Ayudas a Grupos de Investigación GIU17/031 and the unit UFI11/16, and by the Basque Government through the Emaitek programme and the grant PRE_2017_1_0112.
Compliance with Ethical Standards
The CPR process files used in this study were collected as part of an effort to develop an airway check algorithm using the capnography signal. Since these raw data files have no identifying information, the Institutional Review Board at the Oregon Health & Science University determined that the proposed activity is not human subject research because the proposed activity does not meet the definition of human subject per 45 CFR 46.102(f).
- 3.Babbs CF (2013) We still need a real-time hemodynamic monitor for cpr. ResuscitationGoogle Scholar
- 4.Berg RA, Hemphill R, Abella BS, Aufderheide TP, Cave DM, Hazinski MF, Lerner EB, Rea TD, Sayre MR, Swor RA (2010) Part 5: Adult basic life support 2010 American Heart Association guidelines for cardiopulmonary resuscitation and emergency cardiovascular care. Circulation 122(18 suppl 3):S685–S705CrossRefGoogle Scholar
- 13.Friedman J, Hastie T, Tibshirani R (2001) The elements of statistical learning, vol 1. Springer series in statistics Springer, BerlinGoogle Scholar
- 18.Koster RW, Baubin MA, Bossaert LL, Caballero A, Cassan P, Castrén M, Granja C, Handley AJ, Monsieurs KG, Perkins GD et al (2010) European resuscitation council guidelines for resuscitation 2010 section 2. Adult basic life support and use of automated external defibrillators. Resuscitation 81(10):1277–1292CrossRefGoogle Scholar
- 21.Navarro C, Cromie NA, Turner C, Escalona OJ, Anderson JM (2011) Detection of cardiac arrest using a simplified frequency analysis of the impedance cardiogram recorded from defibrillator pads. In: 2011 annual international conference of the IEEE engineering in medicine and biology society, EMBC, pp 1709–1712. IEEEGoogle Scholar
- 22.Neurauter A, Eftestøl T, Kramer-Johansen J, Abella BS, Sunde K, Wenzel V, Lindner KH, Eilevstjønn J, Myklebust H, Steen PA et al (2007) Prediction of countershock success using single features from multiple ventricular fibrillation frequency bands and feature combinations using neural networks. Resuscitation 73(2):253–263CrossRefGoogle Scholar
- 26.Rad A B, Eftestol T, Engan K, Irusta U, Kvaloy JT, Kramer-Johansen J, Wik L, Katsaggelos AK (2017) Ecg-based classification of resuscitation cardiac rhythms for retrospective data analysis. IEEE Transactions on Biomedical EngineeringGoogle Scholar
- 36.Wijshoff RW, van der Sar T, Peeters WH, Bezemer R, Aelen P, Paulussen IW, Ordelman SC, Venema A, van Berkom PF, Aarts RM et al (2013) Detection of a spontaneous pulse in photoplethysmograms during automated cardiopulmonary resuscitation in a porcine model. Resuscitation 84(11):1625–1632CrossRefGoogle Scholar