Representing resuscitation data—Considerations on efficient analysis of quality of cardiopulmonary resuscitation

Extracting physiologic and clinical data from defibrillators for research purposes to improve treatment for patients in cardiac arrest

Background

A defibrillator should be connected to all patients receiving cardiopulmonary resuscitation (CPR) to allow early defibrillation. The defibrillator will collect signal data such as the electrocardiogram (ECG), thoracic impedance and end-tidal CO2, which allows for research on how patients demonstrate different responses to CPR. The aim of this review is to give an overview of methodological challenges and opportunities in using defibrillator data for research.

Methods

The successful collection of defibrillator files has several challenges. There is no scientific standard on how to store such data, which have resulted in several proprietary industrial solutions. The data needs to be exported to a software environment where signal filtering and classifications of ECG rhythms can be performed. This may be automated using different algorithms and artificial intelligence (AI). The patient can be classified being in ventricular fibrillation or -tachycardia, asystole, pulseless electrical activity or having obtained return of spontaneous circulation. How this dynamic response is time-dependent and related to covariates can be handled in several ways. These include Aalen's linear model, Weibull regression and joint models.

Conclusions

The vast amount of signal data from defibrillator represents promising opportunities for the use of AI and statistical analysis to assess patient response to CPR. This may provide an epidemiologic basis to improve resuscitation guidelines and give more individualized care. We suggest that an international working party is initiated to facilitate a discussion on how open formats for defibrillator data can be accomplished, that obligates industrial partners to further develop their current technological solutions.

Rhythm characteristics and patterns of change during cardiopulmonary resuscitation for in-hospital paediatric cardiac arrest

During paediatric cardiopulmonary resuscitation (CPR), patients may transition between pulseless electrical activity (PEA), asystole, ventricular fibrillation/tachycardia (VF/VT), and return of spontaneous circulation (ROSC). The aim of this study was to quantify the dynamic characteristics of this process.

METHODS

ECG recordings were collected in patients who received CPR at the Children's Hospital of Philadelphia (CHOP) between 2006 and 2013. Transitions between PEA (including bradycardia with poor perfusion), VF/VT, asystole, and ROSC were quantified by applying a multi-state statistical model with competing risks, and by smoothing the Nelson-Aalen estimator of cumulative hazard.

RESULTS

Seventy-four episodes of cardiac arrest were included. Median age of patients was 15 years [IQR 11-17], 50% were female and 62% had a respiratory aetiology of arrest. Presenting cardiac arrest rhythms were PEA (60%), VF/VT (24%) and asystole (16%). A temporary surge of PEA was observed between 10 and 15 min due to a doubling of the transition rate from ROSC to PEA (i.e. 're-arrests'). The prevalence of sustained ROSC reached an asymptotic value of 30% at 20 min. Simulation suggests that doubling the transition rate from PEA to ROSC and halving the relapse rate might increase the prevalence of sustained ROSC to 50%.

CONCLUSION

Children and adolescents who received CPR were prone to re-arrest between 10 and 15 min after start of CPR efforts. If the rate of PEA to ROSC transition could be increased and the rate of re-arrests reduced, the overall survival rate may improve.

ECG-Based Classification of Resuscitation Cardiac Rhythms for Retrospective Data Analysis

OBJECTIVE

There is a need to monitor the heart rhythm in resuscitation to improve treatment quality. Resuscitation rhythms are categorized into: ventricular tachycardia (VT), ventricular fibrillation (VF), pulseless electrical activity (PEA), asystole (AS), and pulse-generating rhythm (PR). Manual annotation of rhythms is time-consuming and infeasible for large datasets. Our objective was to develop ECG-based algorithms for the retrospective and automatic classification of resuscitation cardiac rhythms.

METHODS

The dataset consisted of 1631 3-s ECG segments with clinical rhythm annotations, obtained from 298 out-of-hospital cardiac arrest patients. In total, 47 wavelet- and time-domain-based features were computed from the ECG. Features were selected using a wrapper-based feature selection architecture. Classifiers based on Bayesian decision theory, k-nearest neighbor, k-local hyperplane distance nearest neighbor, artificial neural network (ANN), and ensemble of decision trees were studied.

RESULTS

The best results were obtained for ANN classifier with Bayesian regularization backpropagation training algorithm with 14 features, which forms the proposed algorithm. The overall accuracy for the proposed algorithm was 78.5%. The sensitivities (and positive-predictive-values) for AS, PEA, PR, VF, and VT were 88.7% (91.0%), 68.9% (70.4%), 65.9% (69.0%), 86.2% (83.8%), and 78.8% (72.9%), respectively.

CONCLUSIONS

The results demonstrate that it is possible to classify resuscitation cardiac rhythms automatically, but the accuracy for the organized rhythms (PEA and PR) is low.

SIGNIFICANCE

We have made an important step toward making classification of resuscitation rhythms more efficient in the sense of minimal feedback from human experts.

Beyond ventricular fibrillation analysis: comprehensive waveform analysis for all cardiac rhythms occurring during resuscitation

AIM

To propose a method which analyses the electrocardiogram (ECG) waveform of any cardiac rhythm occurring during resuscitation and computes the probability of that rhythm converting into another with better prognosis (Pdes).

METHODS

Rhythm transitions occurring spontaneously or due to defibrillation were analyzed. For each possible rhythm, ventricular fibrillation/ventricular tachycardia (VF/VT), pulseless electrical activity (PEA), pulse-generating rhythm (PR) and asystole (AS), the desired and undesired transitions were defined. ECG segments corresponding to the last 3s of rhythms prior to transition were used to extract waveform features. For each rhythm type, waveform features were combined into a logistic regression model to develop a rhythm specific classifier of desired transitions. This model was the monitoring function for the Pdes. The capacity of each rhythm specific classifier to discriminate between desired and undesired transitions was evaluated in terms of area under the curve (AUC). Pdes was integrated into a state sequence representation, which structures the information of cardiac arrest episodes, to analyze the effect of therapy on patient. As a case study, the effect of optimal/suboptimal cardiopulmonary resuscitation (CPR) on Pdes was analyzed. The mean Pdes was computed for the pre- and post-CPR intervals which presented the same underlying rhythm. The relationship between the optimal/suboptimal CPR and increase/decrease of Pdes was analyzed.

RESULTS

The AUC was 0.80, 0.79, 0.73 and 0.61 for VF/VT, PEA, PR and AS respectively. The Pdes quantified the probability of every rhythm of the episode developing to a better state, and the evolution of Pdes was coherent with the provided therapy. The case study indicated, for most rhythms, that positive trends in the dynamic behaviour could be associated with optimal CPR, whereas the opposite seemed true for negative trends.

CONCLUSION

A method for continuous ECG waveform analysis covering all cardiac rhythms during resuscitation has been proposed. This methodology can be further developed to be used in retrospective studies of CPR techniques, and, in the future, for potentially monitoring in real time the probability of survival of patients being resuscitated.

Automatic detection of chest compressions for the assessment of CPR-quality parameters

AIM

Accurate chest compression detection is key to evaluate cardiopulmonary resuscitation (CPR) quality. Two automatic compression detectors were developed, for the compression depth (CD), and for the thoracic impedance (TI). The objective was to evaluate their accuracy for compression detection and for CPR quality assessment.

METHODS

Compressions were manually annotated using the force and ECG in 38 out-of-hospital resuscitation episodes, comprising 869 min and 67,402 compressions. Compressions were detected using a negative peak detector for the CD. For the TI, an adaptive peak detector based on the amplitude and duration of TI fluctuations was used. Chest compression rate (CC-rate) and chest compression fraction (CCF) were calculated for the episodes and for every minute within each episode. CC-rate for rescuer feedback was calculated every 8 consecutive compressions.

RESULTS

The sensitivity and positive predictive value were 98.4% and 99.8% using CD, and 94.2% and 97.4% using TI. The mean CCF and CC-rate obtained from both detectors showed no significant differences with those obtained from the annotations (P>0.6). The Bland-Altman analysis showed acceptable 95% limits of agreement between the annotations and the detectors for the per-minute CCF, per-minute CC-rate, and CC-rate for feedback. For the detector based on TI, only 3.7% of CC-rate feedbacks had an error larger than 5%.

CONCLUSION

Automatic compression detectors based on the CD and TI signals are very accurate. In most cases, episode review could safely rely on these detectors without resorting to manual review. Automatic feedback on rate can be accurately done using the impedance channel.

Towards the automated analysis and database development of defibrillator data from cardiac arrest

BACKGROUND

During resuscitation of cardiac arrest victims a variety of information in electronic format is recorded as part of the documentation of the patient care contact and in order to be provided for case review for quality improvement. Such review requires considerable effort and resources. There is also the problem of interobserver effects.

OBJECTIVE

We show that it is possible to efficiently analyze resuscitation episodes automatically using a minimal set of the available information.

METHODS AND RESULTS

A minimal set of variables is defined which describe therapeutic events (compression sequences and defibrillations) and corresponding patient response events (annotated rhythm transitions). From this a state sequence representation of the resuscitation episode is constructed and an algorithm is developed for reasoning with this representation and extract review variables automatically. As a case study, the method is applied to the data abstraction process used in the King County EMS. The automatically generated variables are compared to the original ones with accuracies ≥ 90% for 18 variables and ≥ 85% for the remaining four variables.

CONCLUSIONS

It is possible to use the information present in the CPR process data recorded by the AED along with rhythm and chest compression annotations to automate the episode review.

Clinical state transitions during advanced life support (ALS) in in-hospital cardiac arrest

BACKGROUND

When providing advanced life support (ALS) in cardiac arrest, the patient may alternate between four clinical states: ventricular fibrillation/tachycardia (VF/VT), pulseless electrical activity (PEA), asystole, and return of spontaneous circulation (ROSC). At the end of the resuscitation efforts, either death has been declared or sustained ROSC has been obtained. The aim of this study was to describe and analyze the clinical state transitions during ALS among patients experiencing in-hospital cardiac arrest.

METHODS AND RESULTS

The defibrillator files from 311 in-hospital cardiac arrests at the University of Chicago Hospital (IL, USA) and St. Olav University Hospital (Trondheim, Norway) were analyzed (clinicaltrials.gov: NCT00920244). The transitions between clinical states were annotated along the time axis and visualized as plots of the state prevalence according to time. The cumulative intensity of the state transitions was estimated by the Nelson-Aalen estimator for each type of state transition, and for the intensities of overall state transitions. Between 70% and 90% of patients who eventually obtained sustained ROSC had progressed to ROSC by approximately 15-20 min of ALS, depending on the initial rhythm. Patients behaving unstably after this time period, i.e., alternating between ROSC, VF/VT and PEA, had a high risk of ultimately being declared dead.

CONCLUSIONS

We provide an overall picture of the intensities and patterns of clinical state transitions during in-hospital ALS. The majority of patients who obtained sustained ROSC obtained this state and stabilized within the first 15-20 min of ALS. Those who continued to behave unstably after this time point had a high risk of ultimately being declared dead.

Data management in automated external defibrillators: a call for a standardised solution

BACKGROUND

The ECG data stored in automated external defibrillators (AEDs) may be valuable for establishing a final diagnosis and deciding further diagnostics and treatment. Different data management systems are used and this may create significant problems for data storage and access for physicians treating victims in whom an AED has been used.

METHODS

In this descriptive study, we collected information (number, manufacturer and model) on 17 December 2010 from a web page used for the voluntary registration of AEDs in Denmark. The manufacturers were contacted and asked to provide information about data downloading.

RESULTS

There were 12 different manufactures and 20 different AED models. Five models were registered in a quantity <5. We report data from the remaining 15 models (3603 AEDs). Several models stored only one case or 15 min of ECG data. All models had a data transfer option, but most had outdated 'hardware': Seven had infrared transfer; one had a cable with a serial port. Four had a removable memory device, but only one was a USB. The software was available as freeware only in a few cases. Otherwise, a CD ROM was needed, some even with a licence. The software for the second most common AED could not be installed.

CONCLUSION

The development of data management solutions is not a high priority. We encourage the manufacturers to collaborate with researchers to develop a simple data transfer solution in order to improve patient care and facilitate research.