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.

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.

Optimizing support vector machines and autoregressive integrated moving average methods for heart rate variability data correction.

Heart rate variability (HRV) is the variation in time between successive heartbeats and can be used as an indirect measure of autonomic nervous system (ANS) activity. During physical exercise, movement of the measuring device can cause artifacts in the HRV data, severely affecting the analysis of the HRV data. Current methods used for data artifact correction perform insufficiently when HRV is measured during exercise. In this paper we propose the use of autoregressive integrated moving average (ARIMA) and support vector regression (SVR) for HRV data artifact correction. Since both methods are only trained on previous data points, they can be applied not only for correction (i.e., gap filling), but also prediction (i.e., forecasting future values). Our paper describes:•why HRV is difficult to predict and why ARIMA and SVR might be valuable options.•finding the best hyperparameters for using ARIMA and SVR to correct HRV data, including which criterion to use for choosing the best model.•which correction method should be used given the data at hand.

Non-shockable rhythms: A parametric model for the immediate probability of return of spontaneous circulation.

BACKGROUND: Cardiac arrest can present with asystole, Pulseless Electrical Activity (PEA), or Ventricular Fibrillation/Tachycardia (VF/VT). We investigated the transition intensity of Return of spontaneous circulation (ROSC) from PEA and asystole during in-hospital resuscitation. MATERIALS AND METHODS: We included 770 episodes of cardiac arrest. PEA was defined as ECG with >12 QRS complexes per min, asystole by an isoelectric signal >5 seconds. The observed times of PEA to ROSC transitions were fitted to five different parametric time-to-event models. At values ≤0.1, transition intensities roughly represent next-minute probabilities allowing for direct interpretation. Different entities of PEA and asystole, dependent on whether it was the primary or a secondary rhythm, were included as covariates. RESULTS: The transition intensities to ROSC from primary PEA and PEA after asystole were unimodal with peaks of 0.12 at 3 min and 0.09 at 6 min, respectively. Transition intensities to ROSC from PEA after VF/VT, or following transient ROSC, exhibited high initial values of 0.32 and 0.26 at 3 minutes, respectively, but decreased. The transition intensity to ROSC from initial asystole and asystole after PEA were both about 0.01 and 0.02; while asystole after VF/VT had an intensity to ROSC of 0.15 initially which decreased. The transition intensity from asystole after temporary ROSC was constant at 0.08. CONCLUSION: The immediate probability of ROSC develops differently in PEA and asystole depending on the preceding rhythm and the duration of the resuscitation attempt. This knowledge may aid simple bedside prognostication and electronic resuscitation algorithms for monitors/defibrillators.

Continuous assessment of ventricular fibrillation prognostic status during CPR: Implications for resuscitation.

BACKGROUND: Ventricular fibrillation (VF) waveform measures reflect myocardial physiologic status. Continuous assessment of VF prognosis using such measures could guide resuscitation, but has not been possible due to CPR artifact in the ECG. A recently-validated VF measure (termed VitalityScore), which estimates the probability (0-100%) of return-of-rhythm (ROR) after shock, can assess VF during CPR, suggesting potential for continuous application during resuscitation. OBJECTIVE: We evaluated VF using VitalityScore to characterize VF prognostic status continuously during resuscitation. METHODS: We characterized VF using VitalityScore during 60 seconds of CPR and 10 seconds of subsequent pre-shock CPR interruption in patients with out-of-hospital VF arrest. VitalityScore utility was quantified using area under the receiver operating characteristic curve (AUC). VitalityScore trends over time were estimated using mixed-effects models, and associations between trends and ROR were evaluated using logistic models. A sensitivity analysis characterized VF during protracted (100-second) periods of CPR. RESULTS: We evaluated 724 VF episodes among 434 patients. After an initial decline from 0-8 seconds following VF onset, VitalityScore increased slightly during CPR from 8-60 seconds (slope: 0.18%/min). During the first 10 seconds of subsequent pre-shock CPR interruption, VitalityScore declined (slope: -14%/min). VitalityScore predicted ROR throughout CPR with AUCs 0.73-0.75. Individual VitalityScore trends during 8-60 seconds of CPR were marginally associated with subsequent ROR (adjusted odds ratio for interquartile slope change (OR) = 1.10, p = 0.21), and became significant with protracted (100 seconds) CPR duration (OR = 1.28, p = 0.006). CONCLUSION: VF prognostic status can be continuously evaluated during resuscitation, a development that could translate to patient-specific resuscitation strategies.

Texture-based probability mapping for automatic scar assessment in late gadolinium-enhanced cardiovascular magnetic resonance images.

PURPOSE: To evaluate a novel texture-based probability mapping (TPM) method for scar size estimation in LGE-CMRI. METHODS: This retrospective proof-of-concept study included chronic myocardial scars from 52 patients. The TPM was compared with three signal intensity-based methods: manual segmentation, full-width-half-maximum (FWHM), and 5-standard deviation (5-SD). TPM is generated using machine learning techniques, expressing the probability of scarring in pixels. The probability is derived by comparing the texture of the 3 × 3 pixel matrix surrounding each pixel with reference dictionaries from patients with established myocardial scars. The Sørensen-Dice coefficient was used to find the optimal TPM range. A non-parametric test was used to test the correlation between infarct size and remodeling parameters. Bland-Altman plots were performed to assess agreement among the methods. RESULTS: The study included 52 patients (76.9% male; median age 64.5 years (54, 72.5)). A TPM range of 0.328-1.0 was found to be the optimal probability interval to predict scar size compared to manual segmentation, median dice (25th and 75th percentiles)): 0.69(0.42-0.81). There was no significant difference in the scar size between TPM and 5-SD. However, both 5-SD and TPM yielded larger scar sizes compared with FWHM (p < 0.001 and p = 0.002). There were strong correlations between scar size measured by TPM, and left ventricular ejection fraction (LVEF, r = -0.76, p < 0.001), left ventricular end-diastolic volume index (r = 0.73, p < 0.001), and left ventricular end-systolic volume index (r = 0.75, p < 0.001). CONCLUSION: The TPM method is comparable with current SI-based methods, both for the scar size assessment and the relationship with left ventricular remodeling when applied on LGE-CMRI.

Fetal heart rate development during labour.

BACKGROUND: Fresh stillbirths (FSB) and very early neonatal deaths (VEND) are important global challenges with 2.6 million deaths annually. The vast majority of these deaths occur in low- and low-middle income countries. Assessment of the fetal well-being during pregnancy, labour, and birth is normally conducted by monitoring the fetal heart rate (FHR). The heart rate of newborns is reported to increase shortly after birth, but a corresponding trend in how FHR changes just before birth for normal and adverse outcomes has not been studied. In this work, we utilise FHR measurements collected from 3711 labours from a low and low-middle income country to study how the FHR changes towards the end of the labour. The FHR development is also studied in groups defined by the neonatal well-being 24 h after birth. METHODS: A signal pre-processing method was applied to identify and remove time periods in the FHR signal where the signal is less trustworthy. We suggest an analysis framework to study the FHR development using the median FHR of all measured heart rates within a 10-min window. The FHR trend is found for labours with a normal outcome, neonates still admitted for observation and perinatal mortality, i.e. FSB and VEND. Finally, we study how the spread of the FHR changes over time during labour. RESULTS: When studying all labours, there is a drop in median FHR from 134 beats per minute (bpm) to 119 bpm the last 150 min before birth. The change in FHR was significant ([Formula: see text]) using Wilcoxon signed-rank test. A drop in median FHR as well as an increased spread in FHR is observed for all defined outcome groups in the same interval. CONCLUSION: A significant drop in FHR the last 150 min before birth is seen for all neonates with a normal outcome or still admitted to the NCU at 24 h after birth. The observed earlier and larger drop in the perinatal mortality group may indicate that they struggle to endure the physical strain of labour, and that an earlier intervention could potentially save lives. Due to the low amount of data in the perinatal mortality group, a larger dataset is required to validate the drop for this group.

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.

Factors affecting the course of resuscitation from cardiac arrest with pulseless electrical activity in children and adolescents.

BACKGROUND: Although in-hospital pediatric cardiac arrests and cardiopulmonary resuscitation occur >15,000/year in the US, few studies have assessed which factors affect the course of resuscitation in these patients. We investigated transitions from Pulseless Electrical Activity (PEA) to Ventricular Fibrillation/pulseless Ventricular Tachycardia (VF/pVT), Return of Spontaneous Circulation (ROSC) and recurrences from ROSC to PEA in children and adolescents with in-hospital cardiac arrest. METHODS: Episodes of cardiac arrest at the Children's Hospital of Philadelphia were prospectively registered. Defibrillators that recorded chest compression depth/rate and ventilation rate were applied. CPR variables, patient characteristics and etiology, and dynamic factors (e.g. the proportion of time spent in PEA or ROSC) were entered as time-varying covariates for the transition intensities under study. RESULTS: In 67 episodes of CPR in 59 patients (median age 15 years) with cardiac arrest, there were 52 transitions from PEA to ROSC, 22 transitions from PEA to VF/pVT, and 23 recurrences of PEA from ROSC. Except for a nearly significant effect of mean compression depth beyond a threshold of 5.7 cm, only dynamic factors that evolved during CPR favored a transition from PEA to ROSC. The latter included a lower proportion of PEA over the last 5 min and a higher proportion of ROSC over the last 5 min. Factors associated with PEA to VF/pVT development were age, weight, the proportion spent in VF/pVT or PEA the last 5 min, and the general transition intensity, while PEA recurrence from ROSC only depended on the general transition intensity. CONCLUSION: The clinical course during pediatric cardiac arrest was mainly influenced by dynamic factors associated with time in PEA and ROSC. Transitions from PEA to ROSC seemed to be favored by deeper compressions.

Automatic identification of stimulation activities during newborn resuscitation using ECG and accelerometer signals.

BACKGROUND AND OBJECTIVE: Early neonatal death is a worldwide challenge with 1 million newborn deaths every year. The primary cause of these deaths are complications during labour and birth asphyxia. The majority of these newborns could have been saved with adequate resuscitation at birth. Newborn resuscitation guidelines recommend immediate drying, stimulation, suctioning if indicated, and ventilation of non-breathing newborns. A system that will automatically detect and extract time periods where different resuscitation activities are performed, would be highly beneficial to evaluate what resuscitation activities that are improving the state of the newborn, and if current guidelines are good and if they are followed. The potential effects of especially stimulation are not very well documented as it has been difficult to investigate through observations. In this paper the main objective is to identify stimulation activities, regardless if the state of the newborn is changed or not, and produce timelines of the resuscitation episode with the identified stimulations. METHODS: Data is collected by utilizing a new heart rate device, NeoBeat, with dry-electrode ECG and accelerometer sensors placed on the abdomen of the newborn. We propose a method, NBstim, based on time domain and frequency domain features from the accelerometer signals and ECG signals from NeoBeat, to detect time periods of stimulation. NBstim use causal features from a gliding window of the signals, thus it can potentially be used in future realtime systems. A high performing feature subset is found using feature selection. System performance is computed using a leave-one-out cross-validation and compared with manual annotations. RESULTS: The system achieves an overall accuracy of 90.3% when identifying regions with stimulation activities. CONCLUSION: The performance indicates that the proposed NBstim, used with signals from the NeoBeat can be used to determine when stimulation is performed. The provided activity timelines, in combination with the status of the newborn, for example the heart rate, at different time points, can be studied further to investigate both the time spent and the effect of different newborn resuscitation parameters.

Activity Recognition From Newborn Resuscitation Videos.

OBJECTIVE: Birth asphyxia is one of the leading causes of neonatal deaths. A key for survival is performing immediate and continuous quality newborn resuscitation. A dataset of recorded signals during newborn resuscitation, including videos, has been collected in Haydom, Tanzania, and the aim is to analyze the treatment and its effect on the newborn outcome. An important step is to generate timelines of relevant resuscitation activities, including ventilation, stimulation, suction, etc., during the resuscitation episodes. METHODS: We propose a two-step deep neural network system, ORAA-net, utilizing low-quality video recordings of resuscitation episodes to do activity recognition during newborn resuscitation. The first step is to detect and track relevant objects using Convolutional Neural Networks (CNN) and post-processing, and the second step is to analyze the proposed activity regions from step 1 to do activity recognition using 3D CNNs. RESULTS: The system recognized the activities newborn uncovered, stimulation, ventilation and suction with a mean precision of 77.67%, a mean recall of 77,64%, and a mean accuracy of 92.40%. Moreover, the accuracy of the estimated number of Health Care Providers (HCPs) present during the resuscitation episodes was 68.32%. CONCLUSION: The results indicate that the proposed CNN-based two-step ORAA-net could be used for object detection and activity recognition in noisy low-quality newborn resuscitation videos. SIGNIFICANCE: A thorough analysis of the effect the different resuscitation activities have on the newborn outcome could potentially allow us to optimize treatment guidelines, training, debriefing, and local quality improvement in newborn resuscitation.

Duration of Elevated Heart Rate Is an Important Predictor of Exercise-Induced Troponin Elevation.

Background The precise mechanisms causing cardiac troponin (cTn) increase after exercise remain to be determined. The aim of this study was to investigate the impact of heart rate (HR) on exercise-induced cTn increase by using sports watch data from a large bicycle competition. Methods and Results Participants were recruited from NEEDED (North Sea Race Endurance Exercise Study). All completed a 91-km recreational mountain bike race (North Sea Race). Clinical status, ECG, blood pressure, and blood samples were obtained 24 hours before and 3 and 24 hours after the race. Participants (n=177) were, on average, 44 years old; 31 (18%) were women. Both cTnI and cTnT increased in all individuals, reaching the highest level (of the 3 time points assessed) at 3 hours after the race (P<0.001). In multiple regression models, the duration of exercise with an HR >150 beats per minute was a significant predictor of both cTnI and cTnT, at both 3 and 24 hours after exercise. Neither mean HR nor mean HR in percentage of maximum HR was a significant predictor of the cTn response at 3 and 24 hours after exercise. Conclusions The duration of elevated HR is an important predictor of physiological exercise-induced cTn elevation. Clinical Trial Registration URL: https://www.clinicaltrials.gov/. Unique identifier: NCT02166216.

State transition modeling of complex monitored health data.

This article considers the analysis of complex monitored health data, where often one or several signals are reflecting the current health status that can be represented by a finite number of states, in addition to a set of covariates. In particular, we consider a novel application of a non-parametric state intensity regression method in order to study time-dependent effects of covariates on the state transition intensities. The method can handle baseline, time varying as well as dynamic covariates. Because of the non-parametric nature, the method can handle different data types and challenges under minimal assumptions. If the signal that is reflecting the current health status is of continuous nature, we propose the application of a weighted median and a hysteresis filter as data pre-processing steps in order to facilitate robust analysis. In intensity regression, covariates can be aggregated by a suitable functional form over a time history window. We propose to study the estimated cumulative regression parameters for different choices of the time history window in order to investigate short- and long-term effects of the given covariates. The proposed framework is discussed and applied to resuscitation data of newborns collected in Tanzania.

Object Detection During Newborn Resuscitation Activities.

OBJECTIVE: Birth asphyxia is a major newborn mortality problem in low-resource countries. International guideline provides treatment recommendations; however, the importance and effect of the different treatments are not fully explored. The available data are collected in Tanzania, during newborn resuscitation, for analysis of the resuscitation activities and the response of the newborn. An important step in the analysis is to create activity timelines of the episodes, where activities include ventilation, suction, stimulation, etc. Methods: The available recordings are noisy real-world videos with large variations. We propose a two-step process in order to detect activities possibly overlapping in time. The first step is to detect and track the relevant objects, such as bag-mask resuscitator, heart rate sensors, etc., and the second step is to use this information to recognize the resuscitation activities. The topic of this paper is the first step, and the object detection and tracking are based on convolutional neural networks followed by post processing. RESULTS: The performance of the object detection during activities were 96.97% (ventilations), 100% (attaching/removing heart rate sensor), and 75% (suction) on a test set of 20 videos. The system also estimate the number of health care providers present with a performance of 71.16%. CONCLUSION: The proposed object detection and tracking system provides promising results in noisy newborn resuscitation videos. SIGNIFICANCE: This is the first step in a thorough analysis of newborn resuscitation episodes, which could provide important insight about the importance and effect of different newborn resuscitation activities.

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.

Automatic Estimation of Coronary Blood Flow Velocity Step 1 for Developing a Tool to Diagnose Patients With Micro-Vascular Angina Pectoris.

Aim: Our aim was to automatically estimate the blood velocity in coronary arteries using cine X-ray angiographic sequence. Estimating the coronary blood velocity is a key approach in investigating patients with angina pectoris and no significant coronary artery disease. Blood velocity estimation is central in assessing coronary flow reserve. Methods and Results: A multi-step automatic method for blood flow velocity estimation based on the information extracted solely from the cine X-ray coronary angiography sequence obtained by invasive selective coronary catheterization was developed. The method includes (1) an iterative process of segmenting coronary arteries modeling and removing the heart motion using a non-rigid registration, (2) measuring the area of the segmented arteries in each frame, (3) fitting the measured sequence of areas with a 7° polynomial to find start and stop time of dye propagation, and (4) estimating the blood flow velocity based on the time of the dye propagation and the length of the artery-tree. To evaluate the method, coronary angiography recordings from 21 patients with no obstructive coronary artery disease were used. In addition, coronary flow velocity was measured in the same patients using a modified transthoracic Doppler assessment of the left anterior descending artery. We found a moderate but statistically significant correlation between flow velocity assessed by trans thoracic Doppler and the proposed method applying both Spearman and Pearson tests. Conclusion: Measures of coronary flow velocity using a novel fully automatic method that utilizes the information from the X-ray coronary angiographic sequence were statistically significantly correlated to measurements obtained with transthoracic Doppler recordings.

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.

A Robust Machine Learning Architecture for a Reliable ECG Rhythm Analysis during CPR.

Chest compressions delivered during cardiopulmonary resuscitation (CPR) induce artifacts in the ECG that may make the shock advice algorithms (SAA) of defibrillators inaccurate. There is evidence that methods consisting of adaptive filters that remove the CPR artifact followed by machine learning (ML) based algorithms are able to make reliable shock/no-shock decisions during compressions. However, there is room for improvement in the performance of these methods. The objective was to design a robust ML framework for a reliable shock/no-shock decision during CPR. The study dataset contained 596 shockable and 1697 nonshockable ECG segments obtained from 273 cases of out-of-hospital cardiac arrest. Shock/no-shock labels were adjudicated by expert reviewers using ECG intervals without artifacts. First, CPR artifacts were removed from the ECG using a Least Mean Squares (LMS) filter. Then, 38 shock/no-shock decision features based on the Stationary Wavelet Transform (SWT) were extracted from the filtered ECG. A wapper-based feature selection method was applied to select the 6 best features for classification. Finally, 4 state-of-the-art ML classifiers were tested to make the shock/no-shock decision. These diagnoses were compared with the rhythm annotations to compute the Sensitivity (Se) and Specificity (Sp). All classifiers achieved an Se above 94.5%, Sp above 95.5% and an accuracy around 96.0%. They all exceeded the 90% Se and 95% Sp minimum values recommended by the American Heart Association.

A Multistage Algorithm for ECG Rhythm Analysis During Piston-Driven Mechanical Chest Compressions.

GOAL: An accurate rhythm analysis during cardiopulmonary resuscitation (CPR) would contribute to increase the survival from out-of-hospital cardiac arrest. Piston-driven mechanical compression devices are frequently used to deliver CPR. The objective of this paper was to design a method to accurately diagnose the rhythm during compressions delivered by a piston-driven device. METHODS: Data was gathered from 230 out-of-hospital cardiac arrest patients treated with the LUCAS 2 mechanical CPR device. The dataset comprised 201 shockable and 844 nonshockable ECG segments, whereof 270 were asystole (AS) and 574 organized rhythm (OR). A multistage algorithm (MSA) was designed, which included two artifact filters based on a recursive least squares algorithm, a rhythm analysis algorithm from a commercial defibrillator, and an ECG-slope-based rhythm classifier. Data was partitioned randomly and patient-wise into training (60%) and test (40%) for optimization and validation, and statistically meaningful results were obtained repeating the process 500 times. RESULTS: The mean (standard deviation) sensitivity (SE) for shockable rhythms, specificity (SP) for nonshockable rhythms, and the total accuracy of the MSA solution were: 91.7 (6.0), 98.1 (1.1), and 96.9 (0.9), respectively. The SP for AS and OR were 98.0 (1.7) and 98.1 (1.4), respectively. CONCLUSIONS: The SE/SP were above the 90%/95% values recommended by the American Heart Association for shockable and nonshockable rhythms other than sinus rhythm, respectively. SIGNIFICANCE: It is possible to accurately diagnose the rhythm during mechanical chest compressions and the results considerably improve those obtained by previous algorithms.

A Machine Learning Shock Decision Algorithm for Use During Piston-Driven Chest Compressions.

GOAL: Accurate shock decision methods during piston-driven cardiopulmonary resuscitation (CPR) would contribute to improve therapy and increase cardiac arrest survival rates. The best current methods are computationally demanding, and their accuracy could be improved. The objective of this work was to introduce a computationally efficient algorithm for shock decision during piston-driven CPR with increased accuracy. METHODS: The study dataset contains 201 shockable and 844 nonshockable ECG segments from 230 cardiac arrest patients treated with the LUCAS-2 mechanical CPR device. Compression artifacts were removed using the state-of-the-art adaptive filters, and shock/no-shock discrimination features were extracted from the stationary wavelet transform analysis of the filtered ECG, and fed to a support vector machine (SVM) classifier. Quasi-stratified patient wise nested cross-validation was used for feature selection and SVM hyperparameter optimization. The procedure was repeated 50 times to statistically characterize the results. RESULTS: Best results were obtained for a six-feature classifier with mean (standard deviation) sensitivity, specificity, and total accuracy of 97.5 (0.4), 98.2 (0.4), and 98.1 (0.3), respectively. The algorithm presented a five-fold reduction in computational demands when compared to the best available methods, while improving their balanced accuracy by 3 points. CONCLUSIONS: The accuracy of the best available methods was improved while drastically reducing the computational demands. SIGNIFICANCE: An efficient and accurate method for shock decisions during mechanical CPR is now available to improve therapy and contribute to increase cardiac arrest survival.