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

Entropy ◽  
2021 ◽  
Vol 23 (7) ◽  
pp. 847
Author(s):  
Jon Urteaga ◽  
Elisabete Aramendi ◽  
Andoni Elola ◽  
Unai Irusta ◽  
Ahamed Idris
Keyword(s):  
Machine Learning ◽  
Cardiac Arrest ◽  
Electrical Activity ◽  
Area Under The Curve ◽  
Pulseless Electrical Activity ◽  
Learning Model ◽  
Spontaneous Circulation ◽  
Machine Learning Model ◽  
Balance Accuracy ◽  
Hospital Cardiac Arrest

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 5s 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 85.7(9.8)% and a balance accuracy of 78.8(9.8)%, 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.

scholarly journals Towards the Prediction of Rearrest during Out-of-Hospital Cardiac Arrest

Entropy ◽  
2020 ◽  
Vol 22 (7) ◽  
pp. 758
Author(s):  
Andoni Elola ◽  
Elisabete Aramendi ◽  
Enrique Rueda ◽  
Unai Irusta ◽  
Henry Wang ◽  
...  
Keyword(s):  
Machine Learning ◽  
Cardiac Arrest ◽  
Patient Outcomes ◽  
Learning Model ◽  
Spontaneous Circulation ◽  
Operating Characteristics ◽  
Machine Learning Model ◽  
Validation Procedure ◽  
Electrocardiogram Ecg ◽  
Hospital Cardiac Arrest

A secondary arrest is frequent in patients that recover spontaneous circulation after an out-of-hospital cardiac arrest (OHCA). Rearrest events are associated to worse patient outcomes, but little is known on the heart dynamics that lead to rearrest. The prediction of rearrest could help improve OHCA patient outcomes. The aim of this study was to develop a machine learning model to predict rearrest. A random forest classifier based on 21 heart rate variability (HRV) and electrocardiogram (ECG) features was designed. An analysis interval of 2 min after recovery of spontaneous circulation was used to compute the features. The model was trained and tested using a repeated cross-validation procedure, on a cohort of 162 OHCA patients (55 with rearrest). The median (interquartile range) sensitivity (rearrest) and specificity (no-rearrest) of the model were 67.3% (9.1%) and 67.3% (10.3%), respectively, with median areas under the receiver operating characteristics and the precision–recall curves of 0.69 and 0.53, respectively. This is the first machine learning model to predict rearrest, and would provide clinically valuable information to the clinician in an automated way.

Abstract 13102: Outcomes of Primary and Secondary Pulseless Electrical Activity During In-Hospital Cardiac Arrest

Circulation ◽  
2021 ◽  
Vol 144 (Suppl_2) ◽  
Author(s):  
Eirik Unneland ◽  
Anders Norvik ◽  
Shaun McGovern ◽  
David Buckler ◽  
Unai Irusta ◽  
...  
Keyword(s):  
Cardiac Arrest ◽  
Electrical Activity ◽  
Additive Model ◽  
Pulseless Electrical Activity ◽  
Spontaneous Circulation ◽  
Clinical State ◽  
Time To Event ◽  
Time To Event Data ◽  
Average Patient ◽  
Hospital Cardiac Arrest

Background: Pulseless Electrical Activity (PEA) is common during in-hospital cardiac arrest. We investigated the development of four types of PEA: PEA as presenting clinical state (primary) and PEA secondary to transient return of spontaneous circulation (ROSC), ventricular fibrillation/tachycardia (VF/VT), or asystole (ASY). Methods: We analyzed 660 episodes of cardiac arrest at one Norwegian and three U.S. hospitals. ECG, chest compressions and ventilations were recorded by defibrillators during CPR. Clinical states were annotated using a graphical application. We quantified the transition intensities from PEA to ROSC (i.e. the immediate probability of a transition), and the observed half-lives for the four types of PEA (i.e. how quickly PEA develops into another clinical state), using Aalen’s additive model for time-to-event data. Results: The transition intensities to ROSC from primary PEA (n=386) and secondary PEA after ASY (n=226) were about 0.08 per minute, peaking at 6 and 9 min, respectively (figure, left). Thus, an average patient in these types of PEA has about 8% chance to achieve ROSC in one minute. Much higher transition intensities to ROSC of about 0.20 per min were observed for secondary PEA after transient ROSC (n=209) or VF/VT (n=225), peaking at 10 and 5 min, respectively. Half-live times for the four types of PEA (figure, right) were 8.5 min, 6.8 min, 4.6 min and 1.6 min, for primary PEA, and secondary PEA after ASY, transient ROSC and VF/VT, respectively. Discussion: The observed clinical development of PEA in terms of intensity, peak intensity and half-lives during resuscitation differs substantially between the four types of PEA. The chance of obtaining ROSC is considerably lower in primary PEA or PEA after ASY, compared to PEA following transient ROSC or after VF/VT. This may increase understanding of the nature of PEA and the process leading to ROSC; and allow for simple prognostic assessments during a resuscitation attempt.

Abstract 150: Impact of Epinephrine on ECG Changes During Resuscitation From Out-of-Hospital Cardiac Arrest With Initial Pulseless Electrical Activity

Circulation ◽  
2018 ◽  
Vol 138 (Suppl_2) ◽  
Author(s):  
Gunnar W Skjeflo ◽  
Eirik Skogvoll ◽  
Jan Pål Loennechen ◽  
Theresa M Olasveengen ◽  
Lars Wik ◽  
...  
Keyword(s):  
Heart Rate ◽  
Cardiac Arrest ◽  
Electrical Activity ◽  
Multivariate Regression ◽  
Life Support ◽  
Controlled Trial ◽  
Pulseless Electrical Activity ◽  
Qrs Complex ◽  
Epinephrine Administration ◽  
Hospital Cardiac Arrest

Introduction: Presence of electrocardiographic rhythm, documented by the electrocardiogram (ECG), in the absence of palpable pulses defines pulseless electrical activity (PEA). Our aims were to examine the development of ECG characteristics during advanced life support (ALS) from Out-of-Hospital-Cardiac-Arrest (OHCA) with initial PEA, and to explore the effects of epinephrine on these characteristics. Methods: Patients with OHCA and initial PEA in a randomized controlled trial of ALS with or without intravenous access and medications were included. QRS widths and heart-rates were measured in recorded ECG signals during pauses in compressions. Statistical analysis was carried out by multivariate regression (MANOVA). Results: Defibrillator recordings from 170 episodes of cardiac arrest were analyzed, 4840 combined measurements of QRS complex width and heart rate were made. By the multivariate regression model both whether epinephrine was administered and whether return of spontaneous circulation (ROSC) was obtained were significantly associated with changes in QRS width and heart rate. For both control and epinephrine groups, ROSC was preceded by decreasing QRS width and increasing rate, but in the epinephrine group an increase in rate without a decrease in QRS width was associated with poor outcome (fig). Conclusion: The QRS complex characteristics are affected by epinephrine administration during ALS, but still yields valuable prognostic information.

scholarly journals MEWS++: Enhancing the Prediction of Clinical Deterioration in Admitted Patients through a Machine Learning Model

2020 ◽  
Vol 9 (2) ◽  
pp. 343 ◽  
Author(s):  
Arash Kia ◽  
Prem Timsina ◽  
Himanshu N. Joshi ◽  
Eyal Klang ◽  
Rohit R. Gupta ◽  
...  
Keyword(s):  
Machine Learning ◽  
At Risk ◽  
Area Under The Curve ◽  
Learning Model ◽  
Clinical Deterioration ◽  
Early Warning Score ◽  
Support Vector ◽  
Adult Age ◽  
Machine Learning Model ◽  
Patients At Risk

Early detection of patients at risk for clinical deterioration is crucial for timely intervention. Traditional detection systems rely on a limited set of variables and are unable to predict the time of decline. We describe a machine learning model called MEWS++ that enables the identification of patients at risk of escalation of care or death six hours prior to the event. A retrospective single-center cohort study was conducted from July 2011 to July 2017 of adult (age > 18) inpatients excluding psychiatric, parturient, and hospice patients. Three machine learning models were trained and tested: random forest (RF), linear support vector machine, and logistic regression. We compared the models’ performance to the traditional Modified Early Warning Score (MEWS) using sensitivity, specificity, and Area Under the Curve for Receiver Operating Characteristic (AUC-ROC) and Precision-Recall curves (AUC-PR). The primary outcome was escalation of care from a floor bed to an intensive care or step-down unit, or death, within 6 h. A total of 96,645 patients with 157,984 hospital encounters and 244,343 bed movements were included. Overall rate of escalation or death was 3.4%. The RF model had the best performance with sensitivity 81.6%, specificity 75.5%, AUC-ROC of 0.85, and AUC-PR of 0.37. Compared to traditional MEWS, sensitivity increased 37%, specificity increased 11%, and AUC-ROC increased 14%. This study found that using machine learning and readily available clinical data, clinical deterioration or death can be predicted 6 h prior to the event. The model we developed can warn of patient deterioration hours before the event, thus helping make timely clinical decisions.

Sign in / Sign up

Export Citation Format

Share Document