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

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.

Artificial intelligence and machine learning in prehospital emergency care: A scoping review

Our scoping review provides a comprehensive analysis of the landscape of artificial intelligence (AI) applications in prehospital emergency care (PEC). It contributes to the field by highlighting the most studied AI applications and identifying the most common methodological approaches across 106 included studies. The findings indicate a promising future for AI in PEC, with many unique use cases, such as prognostication, demand prediction, resource optimization, and the Internet of Things continuous monitoring systems. Comparisons with other approaches showed AI outperforming clinicians and non-AI algorithms in most cases. However, most studies were internally validated and retrospective, highlighting the need for rigorous prospective validation of AI applications before implementation in clinical settings. We identified knowledge and methodological gaps using an evidence map, offering a roadmap for future investigators. We also discussed the significance of explainable AI for establishing trust in AI systems among clinicians and facilitating real-world validation of AI models.

Airline Point-of-Care System on Seat Belt for Hybrid Physiological Signal Monitoring

With a focus on disease prevention and health promotion, a reactive and disease-centric healthcare system is revolutionized to a point-of-care model by the application of wearable devices. The convenience and low cost made it possible for long-term monitoring of health problems in long-distance traveling such as flights. While most of the existing health monitoring systems on aircrafts are limited for pilots, point-of-care systems provide choices for passengers to enjoy healthcare at the same level. Here in this paper, an airline point-of-care system containing hybrid electrocardiogram (ECG), breathing, and motion signals detection is proposed. At the same time, we propose the diagnosis of sleep apnea-hypopnea syndrome (SAHS) on flights as an application of this system to satisfy the inevitable demands for sleeping on long-haul flights. The hardware design includes ECG electrodes, flexible piezoelectric belts, and a control box, which enables the system to detect the original data of ECG, breathing, and motion signals. By processing these data with interval extraction-based feature selection method, the signals would be characterized and then provided for the long short-term memory recurrent neural network (LSTM-RNN) to classify the SAHS. Compared with other machine learning methods, our model shows high accuracy up to 84-85% with the lowest overfit problem, which proves its potential application in other related fields.

Machine learning and feature engineering for predicting pulse presence during chest compressions

Current resuscitation protocols require pausing chest compressions during cardiopulmonary resuscitation (CPR) to check for a pulse. However, pausing CPR when a patient is pulseless can worsen patient outcomes. Our objective was to design and evaluate an ECG-based algorithm that predicts pulse presence with or without CPR. We evaluated 383 patients being treated for out-of-hospital cardiac arrest with real-time ECG, impedance and audio recordings. Paired ECG segments having an organized rhythm immediately preceding a pulse check (during CPR) and during the pulse check (without CPR) were extracted. Patients were randomly divided into 60% training and 40% test groups. From training data, we developed an algorithm to predict the clinical pulse presence based on the wavelet transform of the bandpass-filtered ECG. Principal component analysis was used to reduce dimensionality, and we then trained a linear discriminant model using three principal component modes as input features. Overall, 38% (351/912) of checks had a spontaneous pulse. AUCs for predicting pulse presence with and without CPR on test data were 0.84 (95% CI (0.80, 0.88)) and 0.89 (95% CI (0.86, 0.92)), respectively. This ECG-based algorithm demonstrates potential to improve resuscitation by predicting the presence of a spontaneous pulse without pausing CPR with moderate accuracy.

Atrial Fibrillation Prediction from Critically Ill Sepsis Patients

Sepsis is defined by life-threatening organ dysfunction during infection and is the leading cause of death in hospitals. During sepsis, there is a high risk that new onset of atrial fibrillation (AF) can occur, which is associated with significant morbidity and mortality. Consequently, early prediction of AF during sepsis would allow testing of interventions in the intensive care unit (ICU) to prevent AF and its severe complications. In this paper, we present a novel automated AF prediction algorithm for critically ill sepsis patients using electrocardiogram (ECG) signals. From the heart rate signal collected from 5-min ECG, feature extraction is performed using the traditional time, frequency, and nonlinear domain methods. Moreover, variable frequency complex demodulation and tunable Q-factor wavelet-transform-based time-frequency methods are applied to extract novel features from the heart rate signal. Using a selected feature subset, several machine learning classifiers, including support vector machine (SVM) and random forest (RF), were trained using only the 2001 Computers in Cardiology data set. For testing the proposed method, 50 critically ill ICU subjects from the Medical Information Mart for Intensive Care (MIMIC) III database were used in this study. Using distinct and independent testing data from MIMIC III, the SVM achieved 80% sensitivity, 100% specificity, 90% accuracy, 100% positive predictive value, and 83.33% negative predictive value for predicting AF immediately prior to the onset of AF, while the RF achieved 88% AF prediction accuracy. When we analyzed how much in advance we can predict AF events in critically ill sepsis patients, the algorithm achieved 80% accuracy for predicting AF events 10 min early. Our algorithm outperformed a state-of-the-art method for predicting AF in ICU patients, further demonstrating the efficacy of our proposed method. The annotations of patients' AF transition information will be made publicly available for other investigators. Our algorithm to predict AF onset is applicable for any ECG modality including patch electrodes and wearables, including Holter, loop recorder, and implantable devices.

Discrimination between the presence and absence of spontaneous circulation using smartphone seismocardiography: A preliminary investigation

BACKGROUND

Seismocardiography measures the vibrations produced by the beating heart using an accelerometer sensor placed on the chest. We evaluated the ability of smartphone seismocardiography to distinguish between the presence and absence of spontaneous circulation.

METHODS

Seismocardiography signals were obtained using a smartphone placed on the sternum in a convenience sample of 60 adult patients (30 comatose patients with spontaneous circulation and 30 deceased patients). The maximum, minimum, and standard deviation (SD) of acceleration values for head-to-foot, right-to-left, and dorsoventral axes and the three axis-root mean square (RMS) of the acceleration signals were calculated. Blinded observers (n = 156) were each asked to determine the presence or absence of spontaneous circulation based on seismocardiography video clips for each of the 60 patients.

RESULTS

The seismocardiography revealed periodic large positive peaks in the patients with spontaneous circulation, which were absent in the patients without spontaneous circulation. For each of the four output measurements (three independent axes plus the three-axis RMS), the acceleration maxima and SD were significantly higher and the minima significantly lower in the patients with spontaneous circulation than in those without spontaneous circulation (all P < 0.001 except the minimum of three axis-RMS results [P = 0.009]). The observers accurately identified the seismocardiography signals from patients without spontaneous circulation, with a sensitivity of 97.6% (95% confidence interval, 97.0%-98.2%) and a specificity of 98.4% (95% confidence interval, 97.8%-99.0%).

CONCLUSIONS

In conclusion, blinded observers accurately distinguished between seismocardiography signals from patients with and without spontaneous circulation.

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.

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.

Random forest-based prediction of stroke outcome

We research into the clinical, biochemical and neuroimaging factors associated with the outcome of stroke patients to generate a predictive model using machine learning techniques for prediction of mortality and morbidity 3-months after admission. The dataset consisted of patients with ischemic stroke (IS) and non-traumatic intracerebral hemorrhage (ICH) admitted to Stroke Unit of a European Tertiary Hospital prospectively registered. We identified the main variables for machine learning Random Forest (RF), generating a predictive model that can estimate patient mortality/morbidity according to the following groups: (1) IS + ICH, (2) IS, and (3) ICH. A total of 6022 patients were included: 4922 (mean age 71.9 ± 13.8 years) with IS and 1100 (mean age 73.3 ± 13.1 years) with ICH. NIHSS at 24, 48 h and axillary temperature at admission were the most important variables to consider for evolution of patients at 3-months. IS + ICH group was the most stable for mortality prediction [0.904 ± 0.025 of area under the receiver operating characteristics curve (AUC)]. IS group presented similar results, although variability between experiments was slightly higher (0.909 ± 0.032 of AUC). ICH group was the one in which RF had more problems to make adequate predictions (0.9837 vs. 0.7104 of AUC). There were no major differences between IS and IS + ICH groups according to morbidity prediction (0.738 and 0.755 of AUC) but, after checking normality with a Shapiro Wilk test with the null hypothesis that the data follow a normal distribution, it was rejected with W = 0.93546 (p-value < 2.2e-16). Conditions required for a parametric test do not hold, and we performed a paired Wilcoxon Test assuming the null hypothesis that all the groups have the same performance. The null hypothesis was rejected with a value < 2.2e-16, so there are statistical differences between IS and ICH groups. In conclusion, machine learning algorithms RF can be effectively used in stroke patients for long-term outcome prediction of mortality and morbidity.

Classification of electrocardiogram signal using an ensemble of deep learning models

Purpose

According to the World Health Organization, arrhythmia is one of the primary causes of deaths across the globe. In order to reduce mortality rate, cardiovascular disease should be properly identified and the proper treatment for the same should be immediately provided to the patients. The objective of this paper was to implement a better heartbeat classification model which will work better than the other implemented heartbeat classification methods.

Design/methodology/approach

In this paper, the ensemble of two deep learning models is proposed to classify the MIT-BIH arrhythmia database into four different classes according to ANSI-AAMI standards. First, a convolutional neural network (CNN) model is used to classify heartbeats on a raw data set. Secondly, four features (wavelets, R-R intervals, morphological and higher-order statistics) are extracted from the data set and then applied to a long short-term memory (LSTM) model to classify the heartbeats. Finally, the ensemble of CNN and LSTM model with sum rule, product rule and majority voting has been used to identify the heartbeat classes.

Findings

Among these, the highest accuracy obtained is 98.58% using ensemble method with product rule. The results show that the ensemble of CNN and BLSTM has offered satisfactory performance compared to other techniques discussed in this study.

Originality/value

In this study, we have developed a new combination of two deep learning models to enhance the performance of arrhythmia classification using segmentation of input ECG signals. The contributions of this study are as follows: First, a deep CNN model is built to classify ECG heartbeat using a raw data set. Second, four types of features (R-R interval, HOS, morphological and wavelet) were extracted from the raw data set and then applied to the bidirectional LSTM model to classify the ECG heartbeat. Third, combination rules (sum rules, product rules and majority voting rules) were tested to ensure the accumulated probabilities of the CNN and LSTM models.

Novel Density Poincaré Plot Based Machine Learning Method to Detect Atrial Fibrillation From Premature Atrial/Ventricular Contractions

OBJECTIVE

Detection of Atrial fibrillation (AF) from premature atrial contraction (PAC) and premature ventricular contraction (PVC) is difficult as frequent occurrences of these ectopic beats can mimic the typical irregular patterns of AF. In this paper, we present a novel density Poincaré plot-based machine learning method to detect AF from PAC/PVCs using electrocardiogram (ECG) recordings.

METHODS

First, we propose the generation of this new density Poincaré plot which is derived from the difference of the heart rate (DHR) and provides the overlapping phase-space trajectory information of the DHR. Next, from this density Poincaré plot, several image processing domain-based approaches including statistical central moments, template correlation, Zernike moment, discrete wavelet transform and Hough transform features are used to extract suitable features. Subsequently, the infinite latent feature selection algorithm is implemented to rank the features. Finally, classification of AF vs. PAC/PVC is performed using K-Nearest Neighbor, Support vector machine (SVM) and Random Forest (RF) classifiers. Our method is developed and validated using a subset of Medical Information Mart for Intensive Care (MIMIC) III database containing 10 AF and 10 PAC/PVC subjects. Results- During the segment-wise 10-fold cross-validation, SVM achieved the best performance with 98.99% sensitivity, 95.18% specificity and 97.45% accuracy with the extracted features. In subject-wise scenario, RF achieved the highest accuracy of 91.93%. Moreover, we further validated the proposed method using two other databases: wearable armband ECG data and the Physionet AFPDB. 100% PAC detection accuracy was obtained for both databases without any further training.

CONCLUSION

Our proposed density Poincaré plot-based method showed superior performance when compared with four existing algorithms; thus showing the efficacy of the extracted image domain-based features.

SIGNIFICANCE

From intensive care unit's ECG to wearable armband ECGs, the proposed method is shown to discriminate PAC/PVCs from AF with high accuracy.

Demonstration of the potential of white-box machine learning approaches to gain insights from cardiovascular disease electrocardiograms

We present the results from a white-box machine learning approach to detect cardiac arrhythmias using electrocardiographic data. A C5.0 is trained to recognize four classes using common features. The four classes are (i) atrial fibrillation and atrial flutter, (ii) tachycardias (iii), sinus bradycardia and (iv) sinus rhythm. Data from 10,646 subjects, 83% of whom have at least one arrhythmia and 17% of whom exhibit a normal sinus rhythm, are used. The C5.0 is trained using 10-fold cross-validation and is able to achieve a balanced accuracy of 95.35%. By using the white-box machine learning approach, a clear and comprehensible tree structure can be revealed, which has selected the 5 most important features from a total of 24 features. These 5 features are ventricular rate, RR-Interval variation, atrial rate, age and difference between longest and shortest RR-Interval. The combination of ventricular rate, RR-Interval variation and atrial rate is especially relevant to achieve classification accuracy, which can be disclosed through the tree. The tree assigns unique values to distinguish the classes. These findings could be applied in medicine in the future. It can be shown that a white-box machine learning approach can reveal granular structures, thus confirming known linear relationships and also revealing nonlinear relationships. To highlight the strength of the C5.0 with respect to this structural revelation, the results of further white-box machine learning and black-box machine learning algorithms are presented.

A Random Forest-Based Accuracy Prediction Model for Augmented Biofeedback in a Precision Shooting Training System

In the military, police, security companies, and shooting sports, precision shooting training is of the outmost importance. In order to achieve high shooting accuracy, a lot of training is needed. As a result, trainees use a large number of cartridges and a considerable amount of time of professional trainers, which can cost a lot. Our motivation is to reduce costs and shorten training time by introducing an augmented biofeedback system based on machine learning techniques. We are designing a system that can detect and provide feedback on three types of errors that regularly occur during a precision shooting practice: excessive hand movement error, aiming error and triggering error. The system is designed to provide concurrent feedback on the hand movement error and terminal feedback on the other two errors. Machine learning techniques are used innovatively to identify hand movement errors; the other two errors are identified by the threshold approach. To correct the excessive hand movement error, a precision shot accuracy prediction model based on Random Forest has proven to be the most suitable. The experimental results show that: (1) the proposed Random Forest (RF) model achieves the prediction accuracy of 91.27%, higher than any of the other reference models, and (2) hand movement is strongly related to the accuracy of precision shooting. Appropriate use of the proposed augmented biofeedback system will result in a lower number of rounds used and shorten the precision shooting training process.

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.

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.