A Machine Learning Model for the Prognosis of Pulseless Electrical Activity during Out-of-Hospital Cardiac Arrest.

Jon Urteaga,Unai Irusta,Elisabete Aramendi,Ahamed Idris,Andoni Elola

doi:10.3390/e23070847

Abstract

Pulseless electrical activity (PEA) is characterized by the disassociation of the mechanical and electrical activity of the heart and appears as the initial rhythm in 20–30% of out-of-hospital cardiac arrest (OHCA) cases. Predicting whether a patient in PEA will convert to return of spontaneous circulation (ROSC) is important because different therapeutic strategies are needed depending on the type of PEA. The aim of this study was to develop a machine learning model to differentiate PEA with unfavorable (unPEA) and favorable (faPEA) evolution to ROSC. An OHCA dataset of 1921 PEA signal segments from defibrillator files was used, 703 faPEA segments from 107 patients with ROSC and 1218 unPEA segments from 153 patients with no ROSC. The solution consisted of a signal-processing stage of the ECG and the thoracic impedance (TI) and the extraction of the TI circulation component (ICC), which is associated with ventricular wall movement. Then, a set of 17 features was obtained from the ECG and ICC signals, and a random forest classifier was used to differentiate faPEA from unPEA. All models were trained and tested using patientwise and stratified 10-fold cross-validation partitions. The best model showed a median (interquartile range) area under the curve (AUC) of and a balance accuracy of , improving the previously available solutions at more than four points in the AUC and three points in balanced accuracy. It was demonstrated that the evolution of PEA can be predicted using the ECG and TI signals, opening the possibility of targeted PEA treatment in OHCA.

Highlights

Out-of-hospital cardiac arrest (OHCA) is a major public health problem, with an estimated incidence between 350,000 and 700,000 cases per year in Europe and survival rates below 10% [1,2]
This study introduced a new model to discriminate faPEA from unPEA based on comprehensive automatic feature extraction from the ECG and thoracic impedance (TI) signals using various signal analysis domains
The results showed that a combination of ECG and TI features substantially improved the accuracy of the models, which could be used to assist emergency medical system (EMS) personnel in evaluating the hemodynamic state of the patient and deciding the optimum resuscitation treatment

Summary

Introduction

Out-of-hospital cardiac arrest (OHCA) is a major public health problem, with an estimated incidence between 350,000 and 700,000 cases per year in Europe and survival rates below 10% [1,2]. When the presenting heart rhythm is ventricular fibrillation (VF), an electrical defibrillation shock within the first five minutes from OHCA onset raises survival rates by 50–70% [2,3]. The best course of treatment for OHCA depends on the heart rhythm of the patient, which can be determined using an electrocardiogram (ECG) [4]. A frequently presenting rhythm is pulseless electrical activity (PEA), with recorded incidences of 20–30% out of hospital [7,8,9] and up to 40–60% in hospital [10,11], as well as much lower survival rates [7,12,13,14,15]. Directions for understanding the mechanism and stratification of PEA have been addressed by clinical consortia and efforts to predict, prevent, and manage PEA encouraged [7,13,15,16]

Objectives

Methods

Results

Discussion

Conclusion