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

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.

Impedance-Based Ventilation Detection and Signal Quality Control During Out-of-Hospital Cardiopulmonary Resuscitation

Feedback on ventilation could help improve cardiopulmonary resuscitation quality and survival from out-of-hospital cardiac arrest (OHCA). However, current technology that monitors ventilation during OHCA is very limited. Thoracic impedance (TI) is sensitive to air volume changes in the lungs, allowing ventilations to be identified, but is affected by artifacts due to chest compressions and electrode motion. This study introduces a novel algorithm to identify ventilations in TI during continuous chest compressions in OHCA. Data from 367 OHCA patients were included, and 2551 one-minute TI segments were extracted. Concurrent capnography data were used to annotate 20724 ground truth ventilations for training and evaluation. A three-step procedure was applied to each TI segment: First, bidirectional static and adaptive filters were applied to remove compression artifacts. Then, fluctuations potentially due to ventilations were located and characterized. Finally, a recurrent neural network was used to discriminate ventilations from other spurious fluctuations. A quality control stage was also developed to anticipate segments where ventilation detection could be compromised. The algorithm was trained and tested using 5-fold cross-validation, and outperformed previous solutions in the literature on the study dataset. The median (interquartile range, IQR) per-segment and per-patient F 1-scores were 89.1 (70.8-99.6) and 84.1 (69.0-93.9), respectively. The quality control stage identified most low performance segments. For the 50% of segments with highest quality scores, the median per-segment and per-patient F 1-scores were 100.0 (90.9-100.0) and 94.3 (86.5-97.8). The proposed algorithm could allow reliable, quality-conditioned feedback on ventilation in the challenging scenario of continuous manual CPR in OHCA.

Quality of Cardiopulmonary Resuscitation and 5-Year Survival Following in-Hospital Cardiac Arrest

PURPOSE

To improve cardiac arrest survival, international resuscitation guidelines emphasize measuring the quality of cardiopulmonary resuscitation (CPR). We aimed to investigate CPR quality during in-hospital cardiac arrest (IHCA) and study long-term survival outcomes.

PATIENTS AND METHODS

This was a cohort study of IHCA from December 2011 until November 2014. Data were collected from the hospital switch board, patient records, and from defibrillators. Impedance data from defibrillators were analyzed manually at the level of single compressions. Long-term survival at 1-, 3-, and 5 years is reported.

RESULTS

The study included 189 IHCAs; median (interquartile range (IQR)) time to first rhythm analysis was 116 (70-201) seconds and median (IQR) time to first defibrillation was 133 (82-264) seconds. Median (IQR) chest compression rate was 126 (119-131) per minute and chest compression fraction (CCF) was 78% (69-86). Thirty-day survival was 25%, while 1-year-, 3-year-, and 5-year survival were 21%, 14%, and 13%, respectively. There was no significant association between any survival outcomes and CCF, whereas chest compression rate was associated with survival to 30 days and 3 years. Overall, 5-year survival was associated with younger age (median 68 vs 74 years, p=0.003), less comorbidity (Charlson comorbidity index median 3 vs 5, p<0.001), and witnessed cardiac arrest (96% vs 77%, p=0.03).

CONCLUSION

We established a systematic collection of IHCA CPR quality data to measure and improve CPR quality and long-term survival outcomes. Median time to first rhythm check/defibrillation was <3 minutes, but median chest compression rate was too fast and median CCF slightly below 80%. More than half of 30-day survivors were still alive at 5 years.

Novel application of thoracic impedance to characterize ventilations during cardiopulmonary resuscitation in the pragmatic airway resuscitation trial

BACKGROUND

Significant challenges exist in measuring ventilation quality during out-of-hospital cardiopulmonary arrest (OHCA) outcomes. Since ventilation is associated with outcomes in cardiac arrest, tools that objectively describe ventilation dynamics are needed. We sought to characterize thoracic impedance (TI) oscillations associated with ventilation waveforms in the Pragmatic Airway Resuscitation Trial (PART).

METHODS

We analyzed CPR process files collected from adult OHCA enrolled in PART. We limited the analysis to cases with simultaneous capnography ventilation recordings at the Dallas-Fort Worth site. We identified ventilation waveforms in the thoracic impedance signal by applying automated signal processing with adaptive filtering techniques to remove overlying artifacts from chest compressions. We correlated detected ventilations with the end-tidal capnography signals. We determined the amplitudes (Ai, Ae) and durations (Di, De) of both insufflation and exhalation phases. We compared differences between laryngeal tube (LT) and endotracheal intubation (ETI) airway management during mechanical or manual chest compressions using Mann-Whitney U-test.

RESULTS

We included 303 CPR process cases in the analysis; 209 manual (77 ETI, 132 LT), 94 mechanical (41 ETI, 53 LT). Ventilation Ai and Ae were higher for ETI than LT in both manual (ETI: Ai 0.71 Ω, Ae 0.70 Ω vs LT: Ai 0.46 Ω, Ae 0.45 Ω; p < 0.01 respectively) and mechanical chest compressions (ETI: Ai 1.22 Ω, Ae 1.14 Ω VS LT: Ai 0.74 Ω, Ae 0.68 Ω; p < 0.01 respectively). Ventilations per minute, duration of TI amplitude insufflation and exhalation did not differ among groups.

CONCLUSION

Compared with LT, ETI thoracic impedance ventilation insufflation and exhalation amplitude were higher while duration did not differ. TI may provide a novel approach to characterizing ventilation during OHCA.

Methodology and framework for the analysis of cardiopulmonary resuscitation quality in large and heterogeneous cardiac arrest datasets

BACKGROUND

Out-of-hospital cardiac arrest (OHCA) data debriefing and clinical research often require the retrospective analysis of large datasets containing defibrillator files from different vendors and clinical annotations by the emergency medical services.

AIM

To introduce and evaluate a methodology to automatically extract cardiopulmonary resuscitation (CPR) quality data in a uniform and systematic way from OHCA datasets from multiple heterogeneous sources.

METHODS

A dataset of 2236 OHCA cases from multiple defibrillator models and manufacturers was analyzed. Chest compressions were automatically identified using the thoracic impedance and compression depth signals. Device event time-stamps and clinical annotations were used to set the start and end of the analysis interval, and to identify periods with spontaneous circulation. A manual audit of the automatic annotations was conducted and used as gold standard. Chest compression fraction (CCF), rate (CCR) and interruption ratio were computed as CPR quality variables. The unsigned error between the automated procedure and the gold standard was calculated.

RESULTS

Full-episode median errors below 2% in CCF, 1 min^-1 in CCR, and 1.5% in interruption ratio, were measured for all signals and devices. The proportion of cases with large errors (>10% in CCF and interruption ratio, and >10 min^-1 in CCR) was below 10%. Errors were lower for shorter sub-intervals of interest, like the airway insertion interval.

CONCLUSIONS

An automated methodology was validated to accurately compute CPR metrics in large and heterogeneous OHCA datasets. Automated processing of defibrillator files and the associated clinical annotations enables the aggregation and analysis of CPR data from multiple sources.

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

Airway strategy and chest compression quality in the Pragmatic Airway Resuscitation Trial

BACKGROUND

Chest compression (CC) quality is associated with improved out-of-hospital cardiopulmonary arrest (OHCA) outcomes. Airway management efforts may adversely influence CC quality. We sought to compare the effects of initial laryngeal tube (LT) and initial endotracheal intubation (ETI) airway management strategies upon chest compression fraction (CCF), rate and interruptions in the Pragmatic Airway Resuscitation Trial (PART).

METHODS

We analyzed CPR process files collected from adult OHCA enrolled in PART. We used automated signal processing techniques and a graphical user interface to calculate CC quality measures and defined interruptions as pauses in chest compressions longer than 3 s. We determined CC fraction, rate and interruptions (number and total duration) for the entire resuscitation and compared differences between LT and ETI using t-tests. We repeated the analysis stratified by time before, during and after airway insertion as well as by successive 3-min time segments. We also compared CC quality between single vs. multiple airway insertion attempts, as well as between bag-valve-mask (BVM-only) vs. ETI or LT.

RESULTS

Of 3004 patients enrolled in PART, CPR process data were available for 1996 (1001 LT, 995 ETI). Mean CPR analysis duration were: LT 22.6 ± 10.8 min vs. ETI 25.3 ± 11.3 min (p < 0.001). Mean CC fraction (LT 88% vs. ETI 87%, p = 0.05) and rate (LT 114 vs. ETI 114 compressions per minute (cpm), p = 0.59) were similar between LT and ETI. Median number of CC interruptions were: LT 11 vs. ETI 12 (p = 0.001). Total CC interruption duration was lower for LT than ETI (LT 160 vs. ETI 181 s, p = 0.002); this difference was larger before airway insertion (LT 56 vs. ETI 78 s, p < 0.001). There were no differences in CC quality when stratified by 3-min time epochs.

CONCLUSION

In the PART trial, compared with ETI, LT was associated with shorter total CC interruption duration but not other CC quality measures. CC quality may be associated with OHCA airway management.

Automatic identification of compressions and ventilations during CPR based on the fuzzy c-means clustering and deep belief network

Background

A transthoracic impedance (TTI) signal is an important indicator of the quality of chest compressions (CCs) during cardiopulmonary resuscitation (CPR). We proposed an automatic detection algorithm including the wavelet decomposition, fuzzy c-means (FCM) clustering, and deep belief network (DBN) to identify the compression and ventilation waveforms for evaluating the quality of CPR.

Methods

TTI signals were collected from a cardiac arrest model that electrically induced cardiac arrest in pigs. All signals were denoised using the wavelet and morphology method. The potential compression and ventilation waveforms were marked using an algorithm with a multi-resolution window. The compressions and ventilations in these waveforms were identified and classified using the FCM clustering and DBN methods.

Results

Using the FCM clustering method, the positive predictive values (PPVs) for compressions and ventilations were 99.7% and 95.7%, respectively. The sensitivities of recognition were 99.8% for compressions and 95.1% for ventilations. The DBN approach exhibited similar PPV and sensitivity results to the FCM clustering method. The time cost was satisfactory using either of these techniques.

Conclusions

Our findings suggest that FCM clustering and DBN can be utilized to effectively and accurately evaluate CPR quality, and provide information for improving the success rate of CPR. Our real-time algorithms using FCM clustering and DBN eliminated most distortions and noises effectively, and correctly identified the compression and ventilation waveforms with a low time cost.

Rhythm Analysis during Cardiopulmonary Resuscitation Using Convolutional Neural Networks

Chest compressions during cardiopulmonary resuscitation (CPR) induce artifacts in the ECG that may provoque inaccurate rhythm classification by the algorithm of the defibrillator. The objective of this study was to design an algorithm to produce reliable shock/no-shock decisions during CPR using convolutional neural networks (CNN). A total of 3319 ECG segments of 9 s extracted during chest compressions were used, whereof 586 were shockable and 2733 nonshockable. Chest compression artifacts were removed using a Recursive Least Squares (RLS) filter, and the filtered ECG was fed to a CNN classifier with three convolutional blocks and two fully connected layers for the shock/no-shock classification. A 5-fold cross validation architecture was adopted to train/test the algorithm, and the proccess was repeated 100 times to statistically characterize the performance. The proposed architecture was compared to the most accurate algorithms that include handcrafted ECG features and a random forest classifier (baseline model). The median (90% confidence interval) sensitivity, specificity, accuracy and balanced accuracy of the method were 95.8% (94.6-96.8), 96.1% (95.8-96.5), 96.1% (95.7-96.4) and 96.0% (95.5-96.5), respectively. The proposed algorithm outperformed the baseline model by 0.6-points in accuracy. This new approach shows the potential of deep learning methods to provide reliable diagnosis of the cardiac rhythm without interrupting chest compression therapy.

A Method to Detect Presence of Chest Compressions During Resuscitation Using Transthoracic Impedance

OBJECTIVE

Interruptions in chest compressions during treatment of out-of-hospital cardiac arrest are associated with lower likelihood of successful resuscitation. Real-time automated detection of chest compressions may improve CPR administration during resuscitation, and could facilitate application of next-generation ECG algorithms that employ different parameters depending on compression state. In contrast to accelerometer sensors, transthoracic impedance (TTI) is commonly acquired by defibrillators. We sought to develop and evaluate the performance of a TTI-based algorithm to automatically detect chest compressions.

METHODS

Five-second TTI segments were collected from patients with out-of-hospital cardiac arrest treated by one of four defibrillator models. Segments with and without chest compressions were collected prior to each of the first four defibrillation shocks (when available) from each case. Patients were divided randomly into 40% training and 60% validation groups. From the training segments, we identified spectral and time-domain features of the TTI associated with compressions. We used logistic regression to predict compression state from these features. Performance was measured by sensitivity and specificity in the validation set. The relationship between performance and TTI segment length was also evaluated.

RESULTS

The algorithm was trained using 1859 segments from 460 training patients. Validation sensitivity and specificity were >98% using 2727 segments from 691 validation patients. Validation performance was significantly reduced using segments shorter than 3.2 s.

CONCLUSIONS

A novel method can reliably detect the presence of chest compressions using TTI. These results suggest potential to provide real-time feedback in order to improve CPR performance or facilitate next-generation ECG rhythm algorithms during resuscitation.

Automatic Detection of Ventilations During Mechanical Cardiopulmonary Resuscitation

Feedback on chest compressions and ventilations during cardiopulmonary resuscitation (CPR) is important to improve survival from out-of-hospital cardiac arrest (OHCA). The thoracic impedance signal acquired by monitor-defibrillators during treatment can be used to provide feedback on ventilations, but chest compression components prevent accurate detection of ventilations. This study introduces the first method for accurate ventilation detection using the impedance while chest compressions are concurrently delivered by a mechanical CPR device. A total of 423 OHCA patients treated with mechanical CPR were included, 761 analysis intervals were selected which in total comprised 5 884 minutes and contained 34 864 ventilations. Ground truth ventilations were determined using the expired CO ₂ channel. The method uses adaptive signal processing to obtain the impedance ventilation waveform. Then, 14 features were calculated from the ventilation waveform and fed to a random forest (RF) classifier to discriminate false positive detections from actual ventilations. The RF feature importance was used to determine the best feature subset for the classifier. The method was trained and tested using stratified 10-fold cross validation (CV) partitions. The training/test process was repeated 20 times to statistically characterize the results. The best ventilation detector had a median (interdecile range, IDR) F ₁-score of 96.32 (96.26-96.37). When used to provide feedback in 1-min intervals, the median (IDR) error and relative error in ventilation rate were 0.002 (-0.334-0.572) min^-1 and 0.05 (-3.71-9.08)%, respectively. An accurate ventilation detector during mechanical CPR was demonstrated. The algorithm could be introduced in current equipment for feedback on ventilation rate and quality, and it could contribute to improve OHCA survival rates.

Impedance Based Automatic Detection of Ventilations During Mechanical Cardiopulmonary Resuscitation

Monitoring ventilation rate is key to improve the quality of cardiopulmonary resuscitation (CPR) and increase the probability of survival in the event of an out-of-hospital cardiac arrest (OHCA). Ventilations produce discernible fluctuations in the thoracic impedance signal recorded by defibrillators. Impedance-based detection of ventilations during CPR is challenging due to chest compression artifacts. This study presents a method for an accurate detection of ventilations when chest compressions are delivered using a piston-driven mechanical device. Data from 223 OHCA patients were analyzed and 399 analysis segments totaling 3101 minutes of mechanical CPR were extracted. A total of 18327 ventilations were annotated using concurrent capnogram recordings. An adaptive least mean squares filter was used to remove compression artifacts. Potential ventilations were detected using a greedy peak detector, and the ventilation waveform was characterized using 8 waveform features. These features were used in a logistic regression classifier to discriminate true ventilations from false positives produced by the greedy peak detector. The classifier was trained and tested using patient wise 10-fold cross validation (CV), and 100 random CV partitions were created to statistically characterize the performance metrics. The peak detector presented a sensitivity (Se) of 99.30%, but a positive predictive value (PPV) of 54.43%. The best classifier configuration used 6 features and improved the mean (sd) Se and PPV of the detector to 93.20% (0.06) and 94.43% (0.04), respectively. When used to measure per minute ventilation rates for feedback to the rescuer, the mean (sd) absolute error in ventilation rate was 0.61 (1.64) min^-1. The first impedance-based method to accurately detect ventilations and give feedback on ventilation rate during mechanical CPR has been demonstrated.

Transthoracic Impedance Measured with Defibrillator Pads-New Interpretations of Signal Change Induced by Ventilations

Compressions during the insufflation phase of ventilations may cause severe pulmonary injury during cardiopulmonary resuscitation (CPR). Transthoracic impedance (TTI) could be used to evaluate how chest compressions are aligned with ventilations if the insufflation phase could be identified in the TTI waveform without chest compression artifacts. Therefore, the aim of this study was to determine whether and how the insufflation phase could be precisely identified during TTI. We synchronously measured TTI and airway pressure (Paw) in 21 consenting anaesthetised patients, TTI through the defibrillator pads and Paw by connecting the monitor-defibrillator’s pressure-line to the endotracheal tube filter. Volume control mode with seventeen different settings were used (5–10 ventilations/setting): Six volumes (150–800 mL) with 12 min⁻¹ frequency, four frequencies (10, 12, 22 and 30 min⁻¹) with 400 mL volume, and seven inspiratory times (0.5–3.5 s) with 400 mL/10 min⁻¹ volume/frequency. Median time differences (quartile range) between timing of expiration onset in the Paw-line (Paw_EO) and the TTI peak and TTI maximum downslope were measured. TTI peak and Paw_EO time difference was 579 (432–723) ms for 12 min⁻¹, independent of volume, with a negative relation to frequency, and it increased linearly with inspiratory time (slope 0.47, R2 = 0.72). Paw_EO and TTI maximum downslope time difference was between −69 and 84 ms for any ventilation setting (time aligned). It was independent (R2 < 0.01) of volume, frequency and inspiratory time, with global median values of −47 (−153–65) ms, −40 (−168–68) ms and 20 (−93–128) ms, for varying volume, frequency and inspiratory time, respectively. The TTI peak is not aligned with the start of exhalation, but the TTI maximum downslope is. This knowledge could help with identifying the ideal ventilation pattern during CPR.

Capnography: A support tool for the detection of return of spontaneous circulation in out-of-hospital cardiac arrest

BACKGROUND

Automated detection of return of spontaneous circulation (ROSC) is still an unsolved problem during cardiac arrest. Current guidelines recommend the use of capnography, but most automatic methods are based on the analysis of the ECG and thoracic impedance (TI) signals. This study analysed the added value of EtCO₂ for discriminating pulsed (PR) and pulseless (PEA) rhythms and its potential to detect ROSC.

MATERIALS AND METHODS

A total of 426 out-of-hospital cardiac arrest cases, 117 with ROSC and 309 without ROSC, were analysed. First, EtCO₂ values were compared for ROSC and no ROSC cases. Second, 5098 artefact free 3-s long segments were automatically extracted and labelled as PR (3639) or PEA (1459) using the instant of ROSC annotated by the clinician on scene as gold standard. Machine learning classifiers were designed using features obtained from the ECG, TI and the EtCO₂ value. Third, the cases were retrospectively analysed using the classifier to discriminate cases with and without ROSC.

RESULTS

EtCO₂ values increased significantly from 41 mmHg 3-min before ROSC to 57 mmHg 1-min after ROSC, and EtCO₂ was significantly larger for PR than for PEA, 46 mmHg/20 mmHg (p < 0.05). Adding EtCO₂ to the machine learning models increased their area under the curve (AUC) by over 2 percentage points. The combination of ECG, TI and EtCO₂ had an AUC for the detection of pulse of 0.92. Finally, the retrospective analysis showed a sensitivity and specificity of 96.6% and 94.5% for the detection of ROSC and no-ROSC cases, respectively.

CONCLUSION

Adding EtCO₂ improves the performance of automatic algorithms for pulse detection based on ECG and TI. These algorithms can be used to identify pulse on site, and to retrospectively identify cases with ROSC.

Deep Neural Networks for ECG-Based Pulse Detection during Out-of-Hospital Cardiac Arrest

The automatic detection of pulse during out-of-hospital cardiac arrest (OHCA) is necessary for the early recognition of the arrest and the detection of return of spontaneous circulation (end of the arrest). The only signal available in every single defibrillator and valid for the detection of pulse is the electrocardiogram (ECG). In this study we propose two deep neural network (DNN) architectures to detect pulse using short ECG segments (5 s), i.e., to classify the rhythm into pulseless electrical activity (PEA) or pulse-generating rhythm (PR). A total of 3914 5-s ECG segments, 2372 PR and 1542 PEA, were extracted from 279 OHCA episodes. Data were partitioned patient-wise into training (80%) and test (20%) sets. The first DNN architecture was a fully convolutional neural network, and the second architecture added a recurrent layer to learn temporal dependencies. Both DNN architectures were tuned using Bayesian optimization, and the results for the test set were compared to state-of-the art PR/PEA discrimination algorithms based on machine learning and hand crafted features. The PR/PEA classifiers were evaluated in terms of sensitivity (Se) for PR, specificity (Sp) for PEA, and the balanced accuracy (BAC), the average of Se and Sp. The Se/Sp/BAC of the DNN architectures were 94.1%/92.9%/93.5% for the first one, and 95.5%/91.6%/93.5% for the second one. Both architectures improved the performance of state of the art methods by more than 1.5 points in BAC.

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.

Detection of spontaneous pulse using the acceleration signals acquired from CPR feedback sensor in a porcine model of cardiac arrest

Background

Reliable detection of return of spontaneous circulation with minimal interruptions of chest compressions is part of high-quality cardiopulmonary resuscitation (CPR) and routinely done by checking pulsation of carotid arteries. However, manual palpation was time-consuming and unreliable even if performed by expert clinicians. Therefore, automated accurate pulse detection with minimal interruptions of chest compression is highly desirable during cardiac arrest especially in out-of-hospital settings.

Objective

To investigate whether the acceleration (ACC) signals acquired from accelerometer-based CPR feedback sensor can be used to distinguish perfusing rhythm (PR) from pulseless electrical activity (PEA) in a porcine model of cardiac arrest.

Methods

Cardiac arrest was induced in 49 male adult pigs. ECG, arterial blood pressure (ABP) and ACC waveforms were simultaneously recorded during CPR. 3-second segments containing compression-free signals during chest compression pauses were extracted and only those segments with organized rhythm were used for analysis. PR was defined as systolic arterial pressure >60 mmHg and pulse pressure >10 mmHg, while PEA was defined as an organized rhythm that does not meet the above criteria for PR. Peak correlation coefficient (CCp) of the cross-correlation function between pre-processed ECG and ACC, was used to discriminate PR and PEA.

Results

63 PR and 153 PEA were identified from the total of 1025 extracted segments. CCp was significantly higher for PR as compared to PEA (0.440±0.176 vs. 0.067±0.042, p<0.01) and highly correlated with ABP (r = 0.848, p<0.001). The area under the receiver operating characteristic curve, sensitivity, specificity and accuracy were 0.965, 93.6%, 97.5% and 96.7% for the ACC-based automatic spontaneous pulse detection.

Conclusions

In this animal model, the ACC signals acquired from an accelerometer-based CPR feedback sensor can be used to detect the presence of spontaneous pulse with high accuracy.

An automatic system for the comprehensive retrospective analysis of cardiac rhythms in resuscitation episodes

AIM

An automatic resuscitation rhythm annotator (ARA) would facilitate and enhance retrospective analysis of resuscitation data, contributing to a better understanding of the interplay between therapy and patient response. The objective of this study was to define, implement, and demonstrate an ARA architecture for complete resuscitation episodes, including chest compression pauses (CC-pauses) and chest compression intervals (CC-intervals).

METHODS

We analyzed 126.5h of ECG and accelerometer-based chest-compression depth data from 281 out-of-hospital cardiac arrest (OHCA) patients. Data were annotated by expert reviewers into asystole (AS), pulseless electrical activity (PEA), pulse-generating rhythm (PR), ventricular fibrillation (VF), and ventricular tachycardia (VT). Clinical pulse annotations were based on patient-charts and impedance measurements. An ARA was developed for CC-pauses, and was used in combination with a chest compression artefact removal filter during CC-intervals. The performance of the ARA was assessed in terms of the unweighted mean of sensitivities (UMS).

RESULTS

The UMS of the ARA were 75.0% during CC-pauses and 52.5% during CC-intervals, 55-points and 32.5-points over a random guess (20% for five categories). Filtering increased the UMS during CC-intervals by 5.2-points. Sensitivities for AS, PEA, PR, VF, and VT were 66.8%, 55.8%, 86.5%, 82.1% and 83.8% during CC-pauses; and 51.1%, 34.1%, 58.7%, 86.4%, and 32.1% during CC-intervals.

CONCLUSIONS

A general ARA architecture was defined and demonstrated on a comprehensive OHCA dataset. Results showed that semi-automatic resuscitation rhythm annotation, which may involve further revision/correction by clinicians for quality assurance, is feasible. The performance (UMS) dropped significantly during CC-intervals and sensitivity was lowest for PEA.

Quality of bystander cardiopulmonary resuscitation during real-life out-of-hospital cardiac arrest

BACKGROUND

Cardiopulmonary resuscitation (CPR) can increase survival in out-of-hospital cardiac arrest (OHCA). However, little is known about bystander CPR quality in real-life OHCA.

AIM

To describe bystander CPR quality based on automated external defibrillator (AED) CPR process data during OHCA and compare it with the European Resuscitation Council 2010 and 2015 Guidelines.

METHODS

We included OHCA cases from the Capital Region, Denmark, (2012-2016) where a Zoll AED was used before ambulance arrival. For cases with at least one minute of continuous data, the initial 10min of CPR data were analysed for compression rate, depth, fraction and compressions delivered for each minute of CPR. Data are presented as median [25th;75th percentile].

RESULTS

We included 136 cases. Bystander median compression rate was 101min^-1 [94;113], compression depth was 4.8cm [3.9;5.8] and compressions per minute were 62 [48;73]. Of all cases, the median compression rate was 100-120min^-1 in 42%, compression depth was 5-6cm in 26%, compression fraction≥60% in 51% and compressions delivered per minute exceeded 60 in 54%. In a minute-to-minute analysis, we found no evidence of deterioration in CPR quality over time. The median peri-shock pause was 27s [23;31] and the pre-shock pause was 19s [17;22].

CONCLUSIONS

The median CPR performed by bystanders using AEDs with audio-feedback in OHCA was within guideline recommendations without deterioration over time. Compression depth had poorer quality compared with other parameters. To improve bystander CPR quality, focus should be on proper compression depth and minimizing pauses.

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.

Effect of the Cardio First Angel™ device on CPR indices: a randomized controlled clinical trial

Background

A number of cardiopulmonary resuscitation (CPR) adjunct devices have been developed to improve the consistency and quality of manual chest compressions. We investigated whether a CPR feedback device would improve CPR quality and consistency, as well as patient survival.

Methods

We conducted a randomized controlled study of patients undergoing CPR for cardiac arrest in the mixed medical-surgical intensive care units of four academic teaching hospitals. Patients were randomized to receive either standard manual CPR or CPR using the Cardio First Angel™ CPR feedback device. Recorded variables included guideline adherence, CPR quality, return of spontaneous circulation (ROSC) rates, and CPR-associated morbidity.

Results

A total of 229 subjects were randomized; 149 were excluded; and 80 were included. Patient demographics were similar. Adherence to published CPR guidelines and CPR quality was significantly improved in the intervention group (p < 0.0001), as were ROSC rates (72 % vs. 35 %; p = 0.001). A significant decrease was observed in rib fractures (57 % vs. 85 %; p = 0.02), but not sternum fractures (5 % vs. 17 %; p = 0.15).

Conclusions

Use of the Cardio First Angel™ CPR feedback device improved adherence to published CPR guidelines and CPR quality, and it was associated with increased rates of ROSC. A decrease in rib but not sternum fractures was observed with device use. Further independent prospective validation is warranted to determine if these results are reproducible in other acute care settings.

Trial registration

ClinicalTrials.gov identifier: NCT02394977. Registered on 5 Mar 2015.

Feedback on the Rate and Depth of Chest Compressions during Cardiopulmonary Resuscitation Using Only Accelerometers

Background

Quality of cardiopulmonary resuscitation (CPR) is key to increase survival from cardiac arrest. Providing chest compressions with adequate rate and depth is difficult even for well-trained rescuers. The use of real-time feedback devices is intended to contribute to enhance chest compression quality. These devices are typically based on the double integration of the acceleration to obtain the chest displacement during compressions. The integration process is inherently unstable and leads to important errors unless boundary conditions are applied for each compression cycle. Commercial solutions use additional reference signals to establish these conditions, requiring additional sensors. Our aim was to study the accuracy of three methods based solely on the acceleration signal to provide feedback on the compression rate and depth.

Materials and Methods

We simulated a CPR scenario with several volunteers grouped in couples providing chest compressions on a resuscitation manikin. Different target rates (80, 100, 120, and 140 compressions per minute) and a target depth of at least 50 mm were indicated. The manikin was equipped with a displacement sensor. The accelerometer was placed between the rescuer’s hands and the manikin’s chest. We designed three alternatives to direct integration based on different principles (linear filtering, analysis of velocity, and spectral analysis of acceleration). We evaluated their accuracy by comparing the estimated depth and rate with the values obtained from the reference displacement sensor.

Results

The median (IQR) percent error was 5.9% (2.8–10.3), 6.3% (2.9–11.3), and 2.5% (1.2–4.4) for depth and 1.7% (0.0–2.3), 0.0% (0.0–2.0), and 0.9% (0.4–1.6) for rate, respectively. Depth accuracy depended on the target rate (p < 0.001) and on the rescuer couple (p < 0.001) within each method.

Conclusions

Accurate feedback on chest compression depth and rate during CPR is possible using exclusively the chest acceleration signal. The algorithm based on spectral analysis showed the best performance. Despite these encouraging results, further research should be conducted to asses the performance of these algorithms with clinical data.

An investigation of thrust, depth and the impedance cardiogram as measures of cardiopulmonary resuscitation efficacy in a porcine model of cardiac arrest

OBJECTIVE

Optimising the depth and rate of applied chest compressions following out of hospital cardiac arrest is crucial in maintaining end organ perfusion and improving survival. The impedance cardiogram (ICG) measured via defibrillator pads produces a characteristic waveform during chest compressions with the potential to provide feedback on cardiopulmonary resuscitation (CPR) and enhance performance. The objective of this pre-clinical study was to investigate the relationship between mechanical and physiological markers of CPR efficacy in a porcine model and examine the strength of correlation between the ICG amplitude, compression depth and end-tidal CO2 (ETCO2).

METHODS

Two experiments were performed using 24 swine (12 per experiment). For experiment 1, ventricular fibrillation (VF) was induced and mechanical CPR commenced at varying thrusts (0-60 kg) for 2 min intervals. Chest compression depth was recorded using a Philips QCPR device with additional recording of invasive physiological parameters: systolic blood pressure, ETCO2, cardiac output and carotid flow. For experiment 2, VF was induced and mechanical CPR commenced at varying depths (0-5 cm) for 2 min intervals. The ICG was recorded via defibrillator pads attached to the animal's sternum and connected to a Heartsine 500 P defibrillator. ICG amplitude, chest compression depth, systolic blood pressure and ETCO2 were recorded during each cycle. In both experiments the within-animal correlation between the measured parameters was assessed using a mixed effect model.

RESULTS

In experiment 1 moderate within-animal correlations were observed between physiological parameters and compression depth (r=0.69-0.77) and thrust (r=0.66-0.82). A moderate correlation was observed between compression depth and thrust (r=0.75). In experiment 2 a strong within-animal correlation and moderate overall correlations were observed between ICG amplitude and compression depth (r=0.89, r=0.79) and ETCO2 (r=0.85, r=0.64).

CONCLUSION

In this porcine model of induced cardiac arrest moderate within animal correlations were observed between mechanical and physiological markers of chest compression efficacy demonstrating the challenge in utilising a single mechanical metric to quantify chest compression efficacy. ICG amplitude demonstrated strong within animal correlations with compression depth and ETCO2 suggesting its potential utility to provide CPR feedback in the out of hospital setting to improve performance.

Classification of cardiopulmonary resuscitation chest compression patterns: manual versus automated approaches

OBJECTIVES

New chest compression detection technology allows for the recording and graphical depiction of clinical cardiopulmonary resuscitation (CPR) chest compressions. The authors sought to determine the inter-rater reliability of chest compression pattern classifications by human raters. Agreement with automated chest compression classification was also evaluated by computer analysis.

METHODS

This was an analysis of chest compression patterns from cardiac arrest patients enrolled in the ongoing Resuscitation Outcomes Consortium (ROC) Continuous Chest Compressions Trial. Thirty CPR process files from patients in the trial were selected. Using written guidelines, research coordinators from each of eight participating ROC sites classified each chest compression pattern as 30:2 chest compressions, continuous chest compressions (CCC), or indeterminate. A computer algorithm for automated chest compression classification was also developed for each case. Inter-rater agreement between manual classifications was tested using Fleiss's kappa. The criterion standard was defined as the classification assigned by the majority of manual raters. Agreement between the automated classification and the criterion standard manual classifications was also tested.

RESULTS

The majority of the eight raters classified 12 chest compression patterns as 30:2, 12 as CCC, and six as indeterminate. Inter-rater agreement between manual classifications of chest compression patterns was κ = 0.62 (95% confidence interval [CI] = 0.49 to 0.74). The automated computer algorithm classified chest compression patterns as 30:2 (n = 15), CCC (n = 12), and indeterminate (n = 3). Agreement between automated and criterion standard manual classifications was κ = 0.84 (95% CI = 0.59 to 0.95).

CONCLUSIONS

In this study, good inter-rater agreement in the manual classification of CPR chest compression patterns was observed. Automated classification showed strong agreement with human ratings. These observations support the consistency of manual CPR pattern classification as well as the use of automated approaches to chest compression pattern analysis.

Fully automatic rhythm analysis during chest compression pauses

AIM

Chest compression artefacts impede a reliable rhythm analysis during cardiopulmonary resuscitation (CPR). These artefacts are not present during ventilations in 30:2 CPR. The aim of this study is to prove that a fully automatic method for rhythm analysis during ventilation pauses in 30:2 CPR is reliable an accurate.

METHODS

For this study 1414min of 30:2 CPR from 135 out-of-hospital cardiac arrest cases were analysed. The data contained 1942 pauses in compressions longer than 3.5s. An automatic pause detector identified the pauses using the transthoracic impedance, and a shock advice algorithm (SAA) diagnosed the rhythm during the detected pauses. The SAA analysed 3-s of the ECG during each pause for an accurate shock/no-shock decision.

RESULTS

The sensitivity and PPV of the pause detector were 93.5% and 97.3%, respectively. The sensitivity and specificity of the SAA in the detected pauses were 93.8% (90% low CI, 90.0%) and 95.9% (90% low CI, 94.7%), respectively. Using the method, shocks would have been advanced in 97% of occasions. For patients in nonshockable rhythms, rhythm reassessment pauses would be avoided in 95.2% (95% CI, 91.6-98.8) of occasions, thus increasing the overall chest compression fraction (CCF).

CONCLUSION

An automatic method could be used to safely analyse the rhythm during ventilation pauses. This would contribute to an early detection of refibrillation, and to increase CCF in patients with nonshockable rhythms.

Reliability and accuracy of the thoracic impedance signal for measuring cardiopulmonary resuscitation quality metrics

AIM

To determine the accuracy and reliability of the thoracic impedance (TI) signal to assess cardiopulmonary resuscitation (CPR) quality metrics.

METHODS

A dataset of 63 out-of-hospital cardiac arrest episodes containing the compression depth (CD), capnography and TI signals was used. We developed a chest compression (CC) and ventilation detector based on the TI signal. TI shows fluctuations due to CCs and ventilations. A decision algorithm classified the local maxima as CCs or ventilations. Seven CPR quality metrics were computed: mean CC-rate, fraction of minutes with inadequate CC-rate, chest compression fraction, mean ventilation rate, fraction of minutes with hyperventilation, instantaneous CC-rate and instantaneous ventilation rate. The CD and capnography signals were accepted as the gold standard for CC and ventilation detection respectively. The accuracy of the detector was evaluated in terms of sensitivity and positive predictive value (PPV). Distributions for each metric computed from the TI and from the gold standard were calculated and tested for normality using one sample Kolmogorov-Smirnov test. For normal and not normal distributions, two sample t-test and Mann-Whitney U test respectively were applied to test for equal means and medians respectively. Bland-Altman plots were represented for each metric to analyze the level of agreement between values obtained from the TI and gold standard.

RESULTS

The CC/ventilation detector had a median sensitivity/PPV of 97.2%/97.7% for CCs and 92.2%/81.0% for ventilations respectively. Distributions for all the metrics showed equal means or medians, and agreements >95% between metrics and gold standard was achieved for most of the episodes in the test set, except for the instantaneous ventilation rate.

CONCLUSION

With our data, the TI can be reliably used to measure all the CPR quality metrics proposed in this study, except for the instantaneous ventilation rate.

Photoplethysmography-based algorithm for detection of cardiogenic output during cardiopulmonary resuscitation

Detecting return of spontaneous circulation (ROSC) during cardiopulmonary resuscitation (CPR) is challenging, time consuming, and requires interrupting chest compressions. Based on automated-CPR porcine data, we have developed an algorithm to support ROSC detection, which detects cardiogenic output during chest compressions via a photoplethysmography (PPG) signal. The algorithm can detect palpable and impalpable spontaneous pulses. A compression-free PPG signal which estimates the spontaneous pulse waveform, was obtained by subtracting the compression component, modeled by a harmonic series. The fundamental frequency of this series was the compression rate derived from the transthoracic impedance signal measured between the defibrillation pads. The amplitudes of the harmonic components were obtained via a least mean-square algorithm. The frequency spectrum of the compression-free PPG signal was estimated via an autoregressive model, and the relationship between the spectral peaks was analyzed to identify the pulse rate (PR). Resumed cardiogenic output could also be detected from a decrease in the baseline of the PPG signal, presumably caused by a redistribution of blood volume to the periphery. The algorithm indicated cardiogenic output when a PR or a redistribution of blood volume was detected. The algorithm indicated cardiogenic output with 94% specificity and 69% sensitivity compared to the retrospective ROSC detection of nine clinicians. Results showed that ROSC detection can be supported by combining the compression-free PPG signal with an indicator based on the detected PR and redistribution of blood volume.