Circulation detection using the electrocardiogram and the thoracic impedance acquired by defibrillation pads

Machine learning model to predict evolution of pulseless electrical activity during in-hospital cardiac arrest

Background

During pulseless electrical activity (PEA) the cardiac mechanical and electrical functions are dissociated, a phenomenon occurring in 25-42% of in-hospital cardiac arrest (IHCA) cases. Accurate evaluation of the likelihood of a PEA patient transitioning to return of spontaneous circulation (ROSC) may be vital for the successful resuscitation.

The aim

We sought to develop a model to automatically discriminate between PEA rhythms with favorable and unfavorable evolution to ROSC.

Methods

A dataset of 190 patients, 120 with ROSC, were acquired with defibrillators from different vendors in three hospitals. The ECG and the transthoracic impedance (TTI) signal were processed to compute 16 waveform features. Logistic regression models where designed integrating both automated features and characteristics annotated in the QRS to identify PEAs with better prognosis leading to ROSC. Cross validation techniques were applied, both patient-specific and stratified, to evaluate the performance of the algorithm.

Results

The best model consisted in a three feature algorithm that exhibited median (interquartile range) Area Under the Curve/Balanced accuracy/Sensitivity/Specificity of 80.3(9.9)/75.6(8.0)/ 77.4(15.2)/72.3(16.4) %, respectively.

Conclusions

Information hidden in the waveforms of the ECG and TTI signals, along with QRS complex features, can predict the progression of PEA. Automated methods as the one proposed in this study, could contribute to assist in the targeted treatment of PEA in IHCA.

Cardiac output estimation using ballistocardiography: a feasibility study in healthy subjects

There is no reliable automated non-invasive solution for monitoring circulation and guiding treatment in prehospital emergency medicine. Cardiac output (CO) monitoring might provide a solution, but CO monitors are not feasible/practical in the prehospital setting. Non-invasive ballistocardiography (BCG) measures heart contractility and tracks CO changes. This study analyzed the feasibility of estimating CO using morphological features extracted from BCG signals. In 20 healthy subjects ECG, carotid/abdominal BCG, and invasive arterial blood pressure based CO were recorded. BCG signals were adaptively processed to isolate the circulatory component from carotid (CCc) and abdominal (CCa) BCG. Then, 66 features were computed on a beat-to-beat basis to characterize amplitude/duration/area/length of the fluctuation in CCc and CCa. Subjects' data were split into development set (75%) to select the best feature subset with which to build a machine learning model to estimate CO and validation set (25%) to evaluate model's performance. The model showed a mean absolute error, percentage error and 95% limits of agreement of 0.83 L/min, 30.2% and - 2.18-1.89 L/min respectively in the validation set. BCG showed potential to reliably estimate/track CO. This method is a promising first step towards an automated, non-invasive and reliable CO estimator that may be tested in prehospital emergencies.

Heart rate and QRS duration as biomarkers predict the immediate outcome from pulseless electrical activity

INTRODUCTION

Pulseless electrical activity (PEA) is commonly observed in in-hospital cardiac arrest (IHCA). Universally available ECG characteristics such as QRS duration (QRSd) and heart rate (HR) may develop differently in patients who obtain ROSC or not. The aim of this study was to assess prospectively how QRSd and HR as biomarkers predict the immediate outcome of patients with PEA.

METHOD

We investigated 327 episodes of IHCA in 298 patients at two US and one Norwegian hospital. We assessed the ECG in 559 segments of PEA nested within episodes, measuring QRSd and HR during pauses of compressions, and noted the clinical state that immediately followed PEA. We investigated the development of HR, QRSd, and transitions to ROSC or no-ROSC (VF/VT, asystole or death) in a joint longitudinal and competing risks statistical model.

RESULTS

Higher HR, and a rising HR, reflect a higher transition intensity ("hazard") to ROSC (p < 0.001), but HR was not associated with the transition intensity to no-ROSC. A lower QRSd and a shrinking QRSd reflect an increased transition intensity to ROSC (p = 0.023) and a reduced transition intensity to no-ROSC (p = 0.002).

CONCLUSION

HR and QRSd convey information of the immediateoutcome during resuscitation from PEA. These universally available and promising biomarkers may guide the emergency team in tailoring individual treatment.

Tidal volume measurements via transthoracic impedance waveform characteristics: The effect of age, body mass index and gender. A single centre interventional study

BACKGROUND AND AIM

Measuring tidal volumes (TV) during bag-valve ventilation is challenging in the clinical setting. The ventilation waveform amplitude of the transthoracic impedance (TTI-amplitude) correlates well with TV for an individual, but poorer between patients. We hypothesized that TV to TTI-amplitude relations could be improved when adjusted for morphometric variables like body mass index (BMI), gender or age, and that TTI-amplitude cut-offs for ventilations with adequate TV (>400ml) could be established.

MATERIALS AND METHODS

Twenty-one consenting adults (9 female, and 9 overall overweight) during positive pressure ventilation in anaesthesia before scheduled surgery were included. Seventeen ventilator modes were used (⩾ five breaths per mode) to adjust different TVs (150-800 ml), ventilation frequencies (10-30 min^-1) and insufflation times (0.5-3.5 s). TTI from the defibrillation pads was filtered to obtain ventilation TTI-amplitudes. Linear regression models were fitted between target and explanatory variables, and compared (coefficient of determination, R²).

RESULTS

The TV to TTI-amplitude slope was 1.39 Ω/l (R²=0.52), with significant differences (p<0.05) between male/female (1.04 Ω/l vs 1.84 Ω/l) and normal/overweight subjects (1.65 Ω/l vs 1.04 Ω/l). The median (interquartile range) TTI-amplitude cut-off for adequate TV was 0.51 Ω(0.14-1.20) with significant differences between males and females (0.58 Ω/0.39 Ω), and normal and overweight subjects (0.52 Ω/0.46 Ω). The TV to TTI-amplitude model improved (R²=0.66) when BMI, age and gender were included.

CONCLUSIONS

TTI-amplitude to TV relations were established and cut-offs for ventilations with adequate TV determined. Patient morphometric variables related to gender, age and BMI explain part of the variability in the measurements.

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.

Shock decision algorithm for use during load distributing band cardiopulmonary resuscitation

AIM

Chest compressions delivered by a load distributing band (LDB) induce artefacts in the electrocardiogram. These artefacts alter shock decisions in defibrillators. The aim of this study was to demonstrate the first reliable shock decision algorithm during LDB compressions.

METHODS

The study dataset comprised 5813 electrocardiogram segments from 896 cardiac arrest patients during LDB compressions. Electrocardiogram segments were annotated by consensus as shockable (1154, 303 patients) or nonshockable (4659, 841 patients). Segments during asystole were used to characterize the LDB artefact and to compare its characteristics to those of manual artefacts from other datasets. LDB artefacts were removed using adaptive filters. A machine learning algorithm was designed for the shock decision after filtering, and its performance was compared to that of a commercial defibrillator's algorithm.

RESULTS

Median (90% confidence interval) compression frequencies were lower and more stable for the LDB than for the manual artefact, 80 min^-1 (79.9-82.9) vs. 104.4 min^-1 (48.5-114.0). The amplitude and waveform regularity (Pearson's correlation coefficient) were larger for the LDB artefact, with 5.5 mV (0.8-23.4) vs. 0.5 mV (0.1-2.2) (p < 0.001) and 0.99 (0.78-1.0) vs. 0.88 (0.55-0.98) (p < 0.001). The shock decision accuracy was significantly higher for the machine learning algorithm than for the defibrillator algorithm, with sensitivity/specificity pairs of 92.1/96.8% (machine learning) vs. 91.4/87.1% (defibrillator) (p < 0.001).

CONCLUSION

Compared to other cardiopulmonary resuscitation artefacts, removing the LDB artefact was challenging due to larger amplitudes and lower compression frequencies. The machine learning algorithm achieved clinically reliable shock decisions during LDB compressions.

Multimodal Algorithms for the Classification of Circulation States During Out-of-Hospital Cardiac Arrest

GOAL

Identifying the circulation state during out-of-hospital cardiac arrest (OHCA) is essential to determine what life-saving therapies to apply. Currently algorithms discriminate circulation (pulsed rhythms, PR) from no circulation (pulseless electrical activity, PEA), but PEA can be classified into true (TPEA) and pseudo (PPEA) depending on cardiac contractility. This study introduces multi-class algorithms to automatically determine circulation states during OHCA using the signals available in defibrillators.

METHODS

A cohort of 60 OHCA cases were used to extract a dataset of 2506 5-s segments, labeled as PR (1463), PPEA (364) and TPEA (679) using the invasive blood pressure, experimentally recorded through a radial/femoral cannulation. A multimodal algorithm using features obtained from the electrocardiogram, the thoracic impedance and the capnogram was designed. A random forest model was trained to discriminate three (TPEA/PPEA/PR) and two (PEA/PR) circulation states. The models were evaluated using repeated patient-wise 5-fold cross-validation, with the unweighted mean of sensitivities (UMS) and F ₁-score as performance metrics.

RESULTS

The best model for 3-class had a median (interquartile range, IQR) UMS and F ₁ of 69.0% (68.0-70.1) and 61.7% (61.0-62.5), respectively. The best two class classifier had median (IQR) UMS and F ₁ of 83.9% (82.9-84.5) and 76.2% (75.0-76.9), outperforming all previous proposals in over 3-points in UMS.

CONCLUSIONS

The first multiclass OHCA circulation state classifier was demonstrated. The method improved previous algorithms for binary pulse/no-pulse decisions.

SIGNIFICANCE

Automatic multiclass circulation state classification during OHCA could contribute to improve cardiac arrest therapy and improve survival rates.

Assessment of the evolution of end-tidal carbon dioxide within chest compression pauses to detect restoration of spontaneous circulation

Background

Measurement of end-tidal CO₂ (ETCO₂) can help to monitor circulation during cardiopulmonary resuscitation (CPR). However, early detection of restoration of spontaneous circulation (ROSC) during CPR using waveform capnography remains a challenge. The aim of the study was to investigate if the assessment of ETCO₂ variation during chest compression pauses could allow for ROSC detection. We hypothesized that a decay in ETCO₂ during a compression pause indicates no ROSC while a constant or increasing ETCO2 indicates ROSC.

Methods

We conducted a retrospective analysis of adult out-of-hospital cardiac arrest (OHCA) episodes treated by the advanced life support (ALS). Continuous chest compressions and ventilations were provided manually. Segments of capnography signal during pauses in chest compressions were selected, including at least three ventilations and with durations less than 20 s. Segments were classified as ROSC or non-ROSC according to case chart annotation and examination of the ECG and transthoracic impedance signals. The percentage variation of ETCO₂ between consecutive ventilations was computed and its average value, ΔET_avg, was used as a single feature to discriminate between ROSC and non-ROSC segments.

Results

A total of 384 segments (130 ROSC, 254 non-ROSC) from 205 OHCA patients (30.7% female, median age 66) were analyzed. Median (IQR) duration was 16.3 (12.9,18.1) s. ΔET_avg was 0.0 (-0.7, 0.9)% for ROSC segments and -11.0 (-14.1, -8.0)% for non-ROSC segments (p < 0.0001). Best performance for ROSC detection yielded a sensitivity of 95.4% (95% CI: 90.1%, 98.1%) and a specificity of 94.9% (91.4%, 97.1%) for all ventilations in the segment. For the first 2 ventilations, duration was 7.7 (6.0, 10.2) s, and sensitivity and specificity were 90.0% (83.5%, 94.2%) and 89.4 (84.9%, 92.6%), respectively. Our method allowed for ROSC detection during the first compression pause in 95.4% of the patients.

Conclusion

Average percent variation of ETCO₂ during pauses in chest compressions allowed for ROSC discrimination. This metric could help confirm ROSC during compression pauses in ALS settings.

Study on the Improvement of Electrical Facility System of Automated External Defibrillators by Real-Time Measurement of Thoracic Impedance

Sudden Cardiac Arrest (SCA) is a serious emergency disease that has increased steadily every year. To this end, an Automated External Defibrillator (AED) is placed in a public place so that even non-professional medical personnel can respond to SCA. However, the thoracic impedance of patients changes due to CardioPulmonary Resuscitation (CPR) and artificial respiration during first aid treatment. In addition, changes in chest statues due to gender, age, and accidents cause changes in thoracic impedance in real time. The change in thoracic impedance caused by this has a negative effect on the intended electrical energy of the automatic heart shocker to the emergency patient. To prove this, we divided it into adult and pediatric modes and experimented with the energy error of the AED according to the same impedance change. When the first peak current was up to 56.4 (A) and at least 8.4 (A) in the adult mode, the first peak current was up to 32.2 (A) and at least 4.8 (A), respectively, when the impedance changed, the error of the current figure occurred. In this paper, the inverse relationship between thoracic impedance and electric shock energy according to the state of the cardiac arrest patient is demonstrated through the results of the experiment, and the need for an electric facility system that can revise for changes in thoracic impedance of the cardiac arrest patient by reflecting them on electric shock energy in real time is presented.

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.

ECG-based Random Forest Classifier for Cardiac Arrest Rhythms

Rhythm annotation of out-of-hospital cardiac episodes (OHCA) is key for a better understanding of the interplay between resuscitation therapy and OHCA patient outcome. OHCA rhythms are classified in five categories, asystole (AS), pulseless electrical activity (PEA), pulsed rhythms (PR), ventricular fibrillation (VF) and ventricular tachycardia (VT). Manual OHCA annotation by expert clinicians is onerous and time consuming, so there is a need for accurate and automatic OHCA rhythm annotation methods. For this study 852 OHCA episodes of patients treated with Automated External Defibrillators (AED) by the Emergency Medical Services of the Basque Country were analyzed. Six expert clinicians reviewed the electrocardiogram (ECG) of 4214 AED rhythm analyses and annotated the rhythm. Their consensus decision was used as ground truth. There were a total of 2418 AS, 294 PR, 1008 PEA, 472 VF and 22 VT. The ECG analysis intervals were extracted and used to develop an automatic rhythm annotator. Data was partitioned patient-wise into training (70%) and test (30%). Performance was evaluated in terms of per class sensitivity (Se) and F-score (F1). The unweighted mean of sensitivity (UMS) and F-score were used as global performance metrics. The classification method is composed of a feature extraction and denoising stage based on the stationary wavelet transform of the ECG, and on a random forest classifier. The best model presented a per rhythm Se/F1 of 95.8/95.7, 43.3/52.2, 85.3/81.3, 94.2/96.1, 81.9/72.2 for AS, PR, PEA, VF and VT, respectively. The UMS for the test set was 80.2%, 2-points above that of previous solutions. This method could be used to retrospectively annotate large OHCA datasets and ameliorate the workload of manual OHCA rhythm annotation.

Convolutional Recurrent Neural Networks to Characterize the Circulation Component in the Thoracic Impedance during Out-of-Hospital Cardiac Arrest

Pulse detection during out-of-hospital cardiac arrest remains challenging for both novel and expert rescuers because current methods are inaccurate and time-consuming. There is still a need to develop automatic methods for pulse detection, where the most challenging scenario is the discrimination between pulsed rhythms (PR, pulse) and pulseless electrical activity (PEA, no pulse). Thoracic impedance (TI) acquired through defibrillation pads has been proven useful for detecting pulse as it shows small fluctuations with every heart beat. In this study we analyse the use of deep learning techniques to detect pulse using only the TI signal. The proposed neural network, composed by convolutional and recurrent layers, outperformed state of the art methods, and achieved a balanced accuracy of 90% for segments as short as 3 s.

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.

Mixed convolutional and long short-term memory network for the detection of lethal ventricular arrhythmia

Early defibrillation by an automated external defibrillator (AED) is key for the survival of out-of-hospital cardiac arrest (OHCA) patients. ECG feature extraction and machine learning have been successfully used to detect ventricular fibrillation (VF) in AED shock decision algorithms. Recently, deep learning architectures based on 1D Convolutional Neural Networks (CNN) have been proposed for this task. This study introduces a deep learning architecture based on 1D-CNN layers and a Long Short-Term Memory (LSTM) network for the detection of VF. Two datasets were used, one from public repositories of Holter recordings captured at the onset of the arrhythmia, and a second from OHCA patients obtained minutes after the onset of the arrest. Data was partitioned patient-wise into training (80%) to design the classifiers, and test (20%) to report the results. The proposed architecture was compared to 1D-CNN only deep learners, and to a classical approach based on VF-detection features and a support vector machine (SVM) classifier. The algorithms were evaluated in terms of balanced accuracy (BAC), the unweighted mean of the sensitivity (Se) and specificity (Sp). The BAC, Se, and Sp of the architecture for 4-s ECG segments was 99.3%, 99.7%, and 98.9% for the public data, and 98.0%, 99.2%, and 96.7% for OHCA data. The proposed architecture outperformed all other classifiers by at least 0.3-points in BAC in the public data, and by 2.2-points in the OHCA data. The architecture met the 95% Sp and 90% Se requirements of the American Heart Association in both datasets for segment lengths as short as 3-s. This is, to the best of our knowledge, the most accurate VF detection algorithm to date, especially on OHCA data, and it would enable an accurate shock no shock diagnosis in a very short time.

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.

Ventricular Fibrillation Waveform Analysis During Chest Compressions to Predict Survival From Cardiac Arrest

BACKGROUND

Quantitative measures of the ventricular fibrillation (VF) ECG waveform can assess myocardial physiology and predict cardiac arrest outcomes, making these measures a candidate to help guide resuscitation. Chest compressions are typically paused for waveform measure calculation because compressions cause ECG artifact. However, such pauses contradict resuscitation guideline recommendations to minimize cardiopulmonary resuscitation interruptions. We evaluated a comprehensive group of VF measures with and without ongoing compressions to determine their performance under both conditions for predicting functionally-intact survival, the study's primary outcome.

METHODS

Five-second VF ECG segments were collected with and without chest compressions before 2755 defibrillation shocks from 1151 out-of-hospital cardiac arrest patients. Twenty-four individual measures and 3 combination measures were implemented. Measures were optimized to predict functionally-intact survival (Cerebral Performance Category score ≤2) using 460 training cases, and their performance evaluated using 691 independent test cases.

RESULTS

Measures predicted functionally-intact survival on test data with an area under the receiver operating characteristic curve ranging from 0.56 to 0.75 (median, 0.73) without chest compressions and from 0.53 to 0.75 (median, 0.69) with compressions ( P<0.001 for difference). Of all measures evaluated, the support vector machine model ranked highest both without chest compressions (area under the receiver operating characteristic curve, 0.75; 95% CI, 0.73-0.78) and with compressions (area under the receiver operating characteristic curve, 0.75; 95% CI, 0.72-0.78; P=0.75 for difference).

CONCLUSIONS

VF waveform measures predict functionally-intact survival when calculated during chest compressions, but prognostic performance is generally reduced compared with compression-free analysis. However, support vector machine models exhibited similar performance with and without compressions while also achieving the highest area under the receiver operating characteristic curve. Such machine learning models may, therefore, offer means to guide resuscitation during uninterrupted cardiopulmonary resuscitation.

ECG-based pulse detection during cardiac arrest using random forest classifier

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.

Metrics save lives: value and hurdles faced

PURPOSE OF REVIEW

Affirmation of the importance of precision in fundamentals of resuscitation practices with improving neurologically intact survival from sudden cardiac arrest, correlated with both measurements of resuscitation metrics generically and recently further refined metric parameters specifically.

RECENT FINDINGS

Quality of baseline cardiopulmonary resuscitation (CPR) in historic intervention trials may not be 'high quality' as once assumed. Optimal chest compression rates are within the narrow spectrum of 106-108/min for adults. Optimal ventilation rates remain within the 8-10/min range.

SUMMARY

Although traditional CPR teaching of 'hard and fast' chest compressions has promoted a relatively easy to remember directive, the reality is that laypersons and medical professionals alike may unwittingly provide markedly suboptimal chest compression depths and rates. Prior resuscitation studies that focused upon airway adjuncts, defibrillation strategies, and/or pharmaceutical interventions that did not simultaneously gauge the underlying CPR chest compression rates, chest compression fraction of time, and ventilation rates should be cautiously interpreted in light of discovery that assumption of 'high-quality CPR' without measurement of the metrics of such is likely a faulty assumption.

Circulation assessment by automated external defibrillators during cardiopulmonary resuscitation

AIM

To design and evaluate a simple algorithm able to discriminate pulsatile rhythms from pulseless electrical activity during automated external defibrillator (AED) analysis intervals, using the ECG and the transthoracic impedance (TI) acquired from defibrillation pads.

METHODS

ECG and TI signals from out-of-hospital AED recordings were retrospectively analysed. Experts annotated the cardiac rhythm during AED analysis intervals and at the end of each episode. We developed an algorithm to classify 3-s segments of non-shockable and non-asystole rhythms as either pulsatile rhythm or pulseless electrical activity. The algorithm consisted on a decision tree based on two features: the mean power of the TI segment and the mean cross-power between ECG and TI segments.

RESULTS

From the 302 annotated episodes, 167 contained segments eligible for the study. The circulation detector algorithm presented a sensitivity (ability of detecting pulsatile rhythms) of 98.3% (95% CI: 95.1-100) and a specificity (ability to detect pulseless electrical activity) of 98.4% (95% CI: 97.1-99.8) in the validation subset. Absence of pulsatile rhythm was confirmed during the first AED analysis interval in 98.9% of the episodes, and presence of a pulse was confirmed in the first 3 s of all intervals with annotated return of spontaneous circulation.

CONCLUSION

Accurate automated detection of circulation based on TI and ECG is possible during AED analysis intervals. This functionality could potentially contribute to enhance patient's care by laypersons using AEDs.

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.

Predicting ROSC in out-of-hospital cardiac arrest using expiratory carbon dioxide concentration: Is trend-detection instead of absolute threshold values the key?

AIM

Guidelines recommend detecting return of spontaneous circulation (ROSC) by a rising concentration of carbon dioxide in the exhalation air. As CO₂ is influenced by numerous factors, no absolute cut-off values of CO₂ to detect ROSC are agreed on so far. As trends in CO₂ might be less affected by influencing factors, we investigated an approach which is based on detecting CO₂-trends in real-time.

METHODS

We conducted a retrospective case-control study on 169 CO₂ time series from out of hospital cardiac arrests resuscitated by Muenster City Ambulance-Service, Germany. A recently developed statistical method for real-time trend-detection (SCARM) was applied to each time series. For each series, the percentage of time points with detected positive and negative trends was determined.

RESULTS

ROSC time series had larger percentages of positive trends than No-ROSC time series (p=0.003). The median percentage of positive trends was 15% in the ROSC time series (IQR: 5% to 23%) and 7% in the No-ROSC time series (IQR: 3% to 14%). A receiver operating characteristic (ROC) analysis yielded an optimal threshold of 13% to differentiate between ROSC and No-ROSC cases with a specificity of 58.4% and sensitivity of 73.9%; the area under the curve was 63.5%.

CONCLUSION

Patients with ROSC differed from patients without ROSC as to the percentage of detected CO₂ trends, indicating the potential of our real-time trend-detection approach. Since the study was designed as a proof of principle and its calculated specificity and sensitivity are low, more research is required to implement CO₂-trend-detection into clinical use.

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.

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.