Combining multiple ECG features does not improve prediction of defibrillation outcome compared to single features in a large population of out-of-hospital cardiac arrests

Combining Ventricular Fibrillation Features With Defibrillation Waveform Parameters Improves the Ability to Predict Shock Outcomes in a Rabbit Model of Cardiac Arrest

BACKGROUND

Quantitative ventricular fibrillation (VF) analysis has the potential to optimize defibrillation by predicting shock outcomes, but its performance remains unsatisfactory. This study investigated whether combining VF features with defibrillation parameters could enhance the ability of shock outcome prediction.

METHODS

VF was electrically induced and left untreated for 30 to 180 seconds in 55 New Zealand rabbits. A defibrillatory shock was applied with 1 of 9 biphasic waveforms with different tilts and durations. A 4-step up-and-down protocol was used to maintain the success rate near 50% for each waveform. Ten features and 10 parameters were obtained from the recorded VF and defibrillation waveforms. Logistic regression and a convolutional neural network were used to combine VF features with defibrillation parameters.

RESULTS

The area under the curve value for the combination of a single VF feature and a single defibrillation parameter (0.725 [95% CI, 0.676-0.775] versus 0.644 [95% CI, 0.589-0.699]; P=0.002) was significantly greater than that for the optimal VF feature. The area under the curve value for the combination of multiple VF features and multiple defibrillation parameters (0.752 [95% CI, 0.704-0.800] versus 0.657 [95% CI, 0.602-0.712]; P<0.001) was significantly greater than that the combination of multiple VF features. The area under the curve for the combination of the raw VF waveform and raw defibrillation waveform (0.781 [95% CI, 0.734-0.828] versus 0.685 [95% CI, 0.632-0.738]; P=0.007) was significantly greater than that for the raw VF waveform.

CONCLUSIONS

In this animal model, combining VF features with defibrillation parameters greatly enhanced the ability of shock outcome prediction, whether it was based on extracted features/parameters or directly using raw waveforms with machine learning methods.

Prediction of the effect of electrical defibrillation by using spectral feature parameters

This paper proposes a system for predicting the effect of electrical defibrillation using spectral feature parameters. The proposed method consists of two-stage prediction. The first stage involves predicting whether electrical defibrillation is "Successful" or "Ineffective." As the next stage, if the proposed prediction system determines "Ineffective," the proposed system discriminates between "VF recurrence" or "Failure" for electrical defibrillation. To develop the prediction system, feature parameters for the target electrocardiograms (ECGs) were first extracted by using the wavelet transform and spectral analysis. Next, effective feature parameters for prediction are selected through an analysis of variance. Moreover, in the preprocessing phase, the Synthetic Minority Oversampling Technique method and standardization are introduced. Finally, support vector machines with some kernel functions and the regularization method are utilized to predict the three states, i.e., "Successful," "Failure," and "VF recurrence," for electrical defibrillation in two phases. In this paper, we present our analysis method for ECGs and evaluate the effectiveness of the proposed prediction system.

Applications and Performance of Machine Learning Algorithms in Emergency Medical Services: A Scoping Review

OBJECTIVE

The aim of this study was to summarize the literature on the applications of machine learning (ML) and their performance in Emergency Medical Services (EMS).

METHODS

Four relevant electronic databases were searched (from inception through January 2024) for all original studies that employed EMS-guided ML algorithms to enhance the clinical and operational performance of EMS. Two reviewers screened the retrieved studies and extracted relevant data from the included studies. The characteristics of included studies, employed ML algorithms, and their performance were quantitively described across primary domains and subdomains.

RESULTS

This review included a total of 164 studies published from 2005 through 2024. Of those, 125 were clinical domain focused and 39 were operational. The characteristics of ML algorithms such as sample size, number and type of input features, and performance varied between and within domains and subdomains of applications. Clinical applications of ML algorithms involved triage or diagnosis classification (n = 62), treatment prediction (n = 12), or clinical outcome prediction (n = 50), mainly for out-of-hospital cardiac arrest/OHCA (n = 62), cardiovascular diseases/CVDs (n = 19), and trauma (n = 24). The performance of these ML algorithms varied, with a median area under the receiver operating characteristic curve (AUC) of 85.6%, accuracy of 88.1%, sensitivity of 86.05%, and specificity of 86.5%. Within the operational studies, the operational task of most ML algorithms was ambulance allocation (n = 21), followed by ambulance detection (n = 5), ambulance deployment (n = 5), route optimization (n = 5), and quality assurance (n = 3). The performance of all operational ML algorithms varied and had a median AUC of 96.1%, accuracy of 90.0%, sensitivity of 94.4%, and specificity of 87.7%. Generally, neural network and ensemble algorithms, to some degree, out-performed other ML algorithms.

CONCLUSION

Triaging and managing different prehospital medical conditions and augmenting ambulance performance can be improved by ML algorithms. Future reports should focus on a specific clinical condition or operational task to improve the precision of the performance metrics of ML models.

An acoustic method (Spectral Flux) to analyze ECG signals for optimizing timing for defibrillation in a porcine model of ventricular fibrillation

Aim

Spectral Flux (SF), which is based on common algorithms in the audio processing field, was applied to quantitatively analyze ECG signals to optimize the timing of defibrillation. With the aim of proving the performance in optimizing the timing of defibrillation, SF was compared with Amplitude Spectrum Area (AMSA) in a porcine model of ventricular fibrillation (VF) in a retrospective analysis experiment.

Methods

A total of 56 male domestic pigs, weighing 40 ± 5 kg, were induced to undergo VF. Animals were then left untreated for 10 min, and after 6 min of cardiopulmonary resuscitation (CPR) defibrillation was performed. The respective SF and AMSA values were calculated every minute during VF and CPR. Comparisons were made through receiver operating characteristic (ROC) curves, one-way analyses of variance (one-way ANOVA), and scatterplots for the successful initial defibrillation sample (positive samples, Group R) and the failed initial defibrillation sample (negative samples, Group N) to illustrate the performance in optimizing the timing of defibrillation for the AMSA and SF methods.

Result

Values of SF and AMSA gradually decreased during the 10 min VF period and increased in during the 6 min CPR period. The scatterplots showed that both metrics had the ability to distinguish positive and negative samples (p < .001). Meanwhile, ROC curves showed that SF (area under the curve, AUC = 0.798, p < .001) had the same ability as AMSA (AUC = 0.737, p < .001) to predict the successful defibrillation (Z = 1.35, p = 0.177). Moreover, when comparing the values for AMSA and SF between the successful initial defibrillation samples (Group R) and the failed initial defibrillation samples (Group N), the results showed that the values of both AMSA and SF in Group R were significantly higher than those in Group N (p < .001).

Conclusion

In the present study, SF method had the same ability as AMSA to predict successful defibrillation with significantly higher values in cases of successful defibrillation than the instances in which defibrillation failed. Additionally, SF method might be more stable than AMSA for filtering out the higher frequency interference signals due to the narrower frequency range and had higher specificity and predictive accuracy than AMSA. So SF method had high clinical potential to optimize the timing of defibrillation. Nevertheless, further animal and clinical studies are still needed to confirm the effectiveness and practicality of SF as a predictive module for defibrillators in clinical practice.

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.

The ability of machine learning algorithms to predict defibrillation success during cardiac arrest: A systematic review

OBJECTIVE

To evaluate the existing knowledge on the effectiveness of machine learning (ML) algorithms inpredicting defibrillation success during in- and out-of-hospital cardiac arrest.

METHODS

MEDLINE, Embase, CINAHL and Scopus were searched from inception to August 30, 2022. Studies were included that utilized ML algorithms for prediction of successful defibrillation, observed as return of spontaneous circulation (ROSC), survival to hospital or discharge, or neurological status at discharge.Studies were excluded if involving a trauma, an unknown underlying rhythm, an implanted cardiac defibrillator or if focused on the prediction or onset of cardiac arrest. Risk of bias was assessed using the PROBAST tool.

RESULTS

There were 2399 studies identified, of which 107 full text articles were reviewed and 15 observational studies (n = 5680) were included for final analysis. 29 ECG waveform features were fed into 15 different ML combinations. The best performing ML model had an accuracy of 98.6 (98.5 - 98.7)%, with 4 second ECG intervals. An algorithm incorporating end-tidal CO2 reported an accuracy of 83.3% (no CI reported). Meta-analysis was not performed due to heterogeneity in study design, ROSC definitions, and characteristics.

CONCLUSION

Machine learning algorithms, specifically Neural Networks, have been shown to have potential to predict defibrillation success for cardiac arrest with high sensitivity and specificity.Due to heterogeneity, inconsistent reporting, and high risk of bias, it is difficult to conclude which, if any, algorithm is optimal. Further clinical studies with standardized reporting of patient characteristics, outcomes, and appropriate algorithm validation are still required to elucidate this. PROSPERO 2020 CRD42020148912.

Hydrogen therapy after resuscitation improves myocardial injury involving inhibition of autophagy in an asphyxial rat model of cardiac arrest

Hydrogen (H₂) therapy is a therapeutic strategy using molecular H₂. Due to its ability to regulate cell homeostasis, H₂ therapy has exhibited marked therapeutic effects on a number of oxidative stress-associated diseases. The present study investigated the effectiveness of H₂ therapy in protecting against myocardial injury in a rat model of asphyxial cardiac arrest and cardiopulmonary resuscitation. Rats underwent 10-min asphyxia-induced cardiac arrest (CA) and cardiopulmonary resuscitation (CPR), and were randomly divided into control and H₂ therapy groups. After resuscitation, the H₂ therapy group was administered room air mixed with 2% H₂ gas for respiration. During CA/CPR, the arterial pressure and heart rate were measured every minute. Survival rate, cardiac function, myocardial injury biomarkers creatine kinase-MB and cardiac troponin-T, and histopathological changes were evaluated to determine the protective effects of H₂ therapy in CA/CPR. Immunohistochemistry and western blot analysis were used to determine the expression levels of autophagy-associated proteins. In vitro, H9C2 cells were subjected to hypoxia/reoxygenation and H₂-rich medium was used in H₂ treatment groups. Western blotting and immunofluorescence were used to observe the expression levels of autophagy-associated proteins. Moreover, an adenovirus-monomeric red fluorescent protein-green fluorescent protein-LC3 construct was used to explore the dynamics of autophagy in the H9C2 cells. The results showed that H₂ therapy significantly improved post-resuscitation survival and cardiac function. H₂ therapy also improved mitochondrial mass and decreased autophagosome numbers in cardiomyocytes after resuscitation. The treatment inhibited autophagy activation, with lower expression levels of autophagy-associated proteins and decreased autophagosome formation in vivo and vitro. In conclusion, H₂ gas inhalation after return of spontaneous circulation improved cardiac function via the inhibition of autophagy.

Optimizing defibrillation during cardiac arrest

PURPOSE OF REVIEW

Current cardiac arrest guidelines are based on a fixed, time-based defibrillation strategy. Rhythm analysis and shock delivery (if indicated) are repeated every 2 min requiring cyclical interruptions of chest compressions. This approach has several downsides, such as the need to temporarily stop cardiopulmonary resuscitation (CPR) for a variable amount of time, thus reducing myocardial perfusion and decreasing the chance of successful defibrillation. A tailored defibrillation strategy should identify treatment priority for each patient, that is chest compressions (CCS) or defibrillation, minimize CCs interruptions, speed up the delivery of early effective defibrillation and reduce the number of ineffective shocks.

RECENT FINDINGS

Real-time ECG analysis (using adaptive filters, new algorithms robust to chest compressions artifacts and shock-advisory algorithms) is an effective strategy to correctly identify heart rhythm during CPR and reduce the hands-off time preceding a shock. Similarly, ventricular fibrillation waveform analysis, that is amplitude spectrum area (AMSA) represents a well established approach to reserve defibrillation in patients with high chance of shock success and postpone it when ventricular fibrillation termination is unlikely. Both approaches demonstrated valuable results in improving cardiac arrest outcomes in experimental and observational study.

SUMMARY

Real-time ECG analysis and AMSA have the potential to predict ventricular fibrillation termination, return of spontaneous circulation and even survival, with discretely high confidence. Prospective studies are now necessary to validate these new approaches in the clinical scenario.

Estimating the amplitude spectrum area of ventricular fibrillation during cardiopulmonary resuscitation using only ECG waveform

Background

Amplitude spectrum area (AMSA) calculated from ventricular fibrillation (VF) can be used to monitor the effectiveness of chest compression (CC) and optimize the timing of defibrillation. However, reliable AMSA can only be obtained during CC pause because of artifacts. In this study, we sought to develop a method for estimating AMSA during cardiopulmonary resuscitation (CPR) using only the electrocardiogram (ECG) waveform.

Methods

Intervals of 8 seconds ECG and CC-related references, including 4 seconds during CC and an adjacent 4 seconds without CC, were collected before 1,008 defibrillation shocks from 512 out-of-hospital cardiac arrest patients. Signal quality was analyzed based on the irregularity of autocorrelation of VF. If signal quality index (SQI) was high, AMSA would be calculated from the original signal. Otherwise, CC-related artifacts would be constructed and suppressed using the least mean square filter from VF before calculation of AMSA. The algorithm was optimized using 480 training shocks and evaluated using 528 independent testing shocks.

Results

Overall, CC resulted in lower SQI [0.15 (0.04-0.61) with CC vs. 0.75 (0.61-0.83) without CC, P<0.01] and higher AMSA [11.2 (7.7-16.2) with CC vs. 7.2 (4.9-10.6) mVHz without CC, P<0.01] values. The predictive accuracy (49.2% vs. 66.5%, P<0.01) and area under the receiver operating characteristic curve (AUC) (0.647 vs. 0.734, P<0.01) were significantly decreased during CC. Using the proposed method, the estimated AMSA was 7.1 (5.0-15.2) mVHz, the predictive accuracy was 67.0% and the AUC was 0.713, which were all comparable with those calculated without CC.

Conclusions

Using the signal quality-based artifact suppression method, AMSA can be reliably estimated and continuously monitored during CPR.

ECG waveform dataset for predicting defibrillation outcome in out-of-hospital cardiac arrested patients

The provided database of 260 ECG signals was collected from patients with out-of-hospital cardiac arrest while treated by the emergency medical services. Each ECG signal contains a 9 second waveform showing ventricular fibrillation, followed by 1 min of post-shock waveform. Patients’ ECGs are made available in multiple formats. All ECGs recorded during the prehospital treatment are provided in PFD files, after being anonymized, printed in paper, and scanned. For each ECG, the dataset also includes the whole digitized waveform (9 s pre- and 1 min post-shock each) and numerous features in temporal and frequency domain extracted from the 9 s episode immediately prior to the first defibrillation shock. Based on the shock outcome, each ECG file has been annotated by three expert cardiologists, - using majority decision -, as successful (56 cases), unsuccessful (195 cases), or indeterminable (9 cases). The code for preprocessing, for feature extraction, and for limiting the investigation to different temporal intervals before the shock is also provided. These data could be reused to design algorithms to predict shock outcome based on ventricular fibrillation analysis, with the goal to optimize the defibrillation strategy (immediate defibrillation versus cardiopulmonary resuscitation and/or drug administration) for enhancing resuscitation.

Predicting defibrillation success in out-of-hospital cardiac arrested patients: Moving beyond feature design

OBJECTIVE

Optimizing timing of defibrillation by evaluating the likelihood of a successful outcome could significantly enhance resuscitation. Previous studies employed conventional machine learning approaches and hand-crafted features to address this issue, but none have achieved superior performance to be widely accepted. This study proposes a novel approach in which predictive features are automatically learned.

METHODS

A raw 4s VF episode immediately prior to first defibrillation shock was feed to a 3-stage CNN feature extractor. Each stage was composed of 4 components: convolution, rectified linear unit activation, dropout and max-pooling. At the end of feature extractor, the feature map was flattened and connected to a fully connected multi-layer perceptron for classification. For model evaluation, a 10 fold cross-validation was employed. To balance classes, SMOTE oversampling method has been applied to minority class.

RESULTS

The obtained results show that the proposed model is highly accurate in predicting defibrillation outcome (Acc = 93.6 %). Since recommendations on classifiers suggest at least 50 % specificity and 95 % sensitivity as safe and useful predictors for defibrillation decision, the reported sensitivity of 98.8 % and specificity of 88.2 %, with the analysis speed of 3 ms/input signal, indicate that the proposed model possesses a good prospective to be implemented in automated external defibrillators.

CONCLUSIONS

The learned features demonstrate superiority over hand-crafted ones when performed on the same dataset. This approach benefits from being fully automatic by fusing feature extraction, selection and classification into a single learning model. It provides a superior strategy that can be used as a tool to guide treatment of OHCA patients in bringing optimal decision of precedence treatment. Furthermore, for encouraging replicability, the dataset has been made publicly available to the research community.

Validation of spectral energy for the quantitative analysis of ventricular fibrillation waveform to guide defibrillation in a porcine model of cardiac arrest and resuscitation

Background

The amplitude spectrum area (AMSA), a frequency-domain ventricular fibrillation (VF) waveform metric, can predict successful defibrillation and the return of spontaneous circulation (ROSC) after defibrillation attempts. We aimed to investigate the validation of Spectral Energy for the quantitative analysis of the VF waveform to guide defibrillation in a porcine model of cardiac arrest and compare it with the AMSA metric. In addition, we sought to determine the effects of epinephrine and cardiopulmonary resuscitation (CPR) on AMSA and Spectral Energy.

Methods

Sixty male domestic pigs weighing 35 to 45 kg were involved in this study. VF was initially untreated for 10 min followed by 6 min of CPR. Epinephrine was administered to the animals after 2 min of CPR. After the CPR, a single 120-J biphasic shock was applied to the animals. AMSA and Spectral Energy values were measured every minute from the electrocardiogram (ECG) to defibrillation. Receiver operating characteristic (ROC) curves were calculated for both the Spectral Energy and AMSA methods.

Results

Spectral Energy and AMSA values gradually decayed during untreated VF in all the animals. However, after the application of CPR and epinephrine, Spectral Energy and AMSA values were significantly increased in animals which were later successfully defibrillated, but did not increase in animals in which defibrillation was unsuccessful. The ROC curves showed that the Spectral Energy and AMSA methods possessed similar levels of sensitivity and specificity in predicting defibrillation success (P<0.001).

Conclusions

Both the Spectral Energy and AMSA methods accurately predict successful defibrillation. Moreover, increases in the value of either Spectral Energy or AMSA after application of CPR and epinephrine may also predict successful defibrillation.

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.

Amplitude screening improves performance of AMSA method for predicting success of defibrillation in swine model

PURPOSE

A novel amplitude screening method, termed Optimal Amplitude Spectrum Area (Opt-AMSA) with the aim of improving the performance of the Amplitude Spectrum Area (AMSA) method, was proposed to optimize the timing of defibrillation. We investigated the effects of the Opt-AMSA method on the prediction of successful defibrillation when compared with AMSA in a porcine model of ventricular fibrillation (VF).

METHOD

60 male domestic pigs were untreated in the first 10 min of VF, then received cardiopulmonary resuscitation (CPR) for 6 min. Values of Opt-AMSA and AMSA were calculated every minute before defibrillation. Linear regression was used to evaluate the correlation between Opt-AMSA and AMSA. Receiver Operating Characteristic (ROC) analysis was conducted for the two methods and to compare their predictive values.

RESULTS

The values of both AMSA and Opt-AMSA gradually decreased over time during untreated VF in all animals. The values of both methods of defibrillation were slightly increased after the implementation of CPR in animals that were successfully resuscitated, while there were no significant changes in either method in those who ultimately failed to resuscitate. The significant positive correlation between Opt-AMSA and AMSA was shown by Pearson correlation analysis. ROC analysis showed that Opt-AMSA (AUC = 0.87) significantly improved the performance of AMSA (AUC = 0.77) to predict successful defibrillation (Z = 2.27, P < 0.05).

CONCLUSION

Both the Opt-AMSA and AMSA methods showed high potential to predict the success of defibrillation. Moreover, the Opt-AMSA method improved the performance of the AMSA method, and may be a promising tool to optimize the timing of defibrillation.

Fuzzy and Sample Entropies as Predictors of Patient Survival Using Short Ventricular Fibrillation Recordings during out of Hospital Cardiac Arrest

Optimal defibrillation timing guided by ventricular fibrillation (VF) waveform analysis would contribute to improved survival of out-of-hospital cardiac arrest (OHCA) patients by minimizing myocardial damage caused by futile defibrillation shocks and minimizing interruptions to cardiopulmonary resuscitation. Recently, fuzzy entropy (FuzzyEn) tailored to jointly measure VF amplitude and regularity has been shown to be an efficient defibrillation success predictor. In this study, 734 shocks from 296 OHCA patients (50 survivors) were analyzed, and the embedding dimension (m) and matching tolerance (r) for FuzzyEn and sample entropy (SampEn) were adjusted to predict defibrillation success and patient survival. Entropies were significantly larger in successful shocks and in survivors, and when compared to the available methods, FuzzyEn presented the best prediction results, marginally outperforming SampEn. The sensitivity and specificity of FuzzyEn were 83.3% and 76.7% when predicting defibrillation success, and 83.7% and 73.5% for patient survival. Sensitivities and specificities were two points above those of the best available methods, and the prediction accuracy was kept even for VF intervals as short as 2s. These results suggest that FuzzyEn and SampEn may be promising tools for optimizing the defibrillation time and predicting patient survival in OHCA patients presenting VF.

Association between ventricular fibrillation amplitude immediately prior to defibrillation and defibrillation success in out-of-hospital cardiac arrest

BACKGROUND

Several characteristics of the ventricular fibrillation (VF) waveform during cardiac arrest are associated with defibrillation success, including peak amplitude in the seconds prior to defibrillation. It is not known if immediate pre-defibrillation amplitude is associated with successful defibrillation, return of spontaneous circulation (ROSC) or survival to hospital discharge (SHD).

METHODS

We analyzed automated external defibrillation recordings of 80 patients with out-of-hospital VF cardiac arrest who received 284 defibrillations. We recorded the maximum amplitude during 3-second ECG tracings prior to each defibrillation attempt and the amplitude immediately prior to defibrillation.

RESULTS

Both the amplitude just prior to defibrillation and the highest amplitude within 3 seconds of the defibrillation were significantly higher in successful vs unsuccessful defibrillations (0.21 vs 0.11 mV, P = <.0001 and 0.51 vs 0.36 mV, P = <.0001). Amplitude immediately prior to defibrillation and maximal amplitude within 3 seconds of defibrillation were also higher in defibrillations with ROSC vs. defibrillations without ROSC (0.23 vs. 0.12 mV, P < .0001; and 0.52 vs. 0.38 mV, P < .0001). In defibrillations that resulted in SHD, immediate pre-defibrillation amplitude and maximum amplitude were also significantly larger (0.20 vs. 0.11 mV, P < .0001; and 0.52 vs. 0.35 mV, P < .0001). Binary logistic regression including both measures showed that only immediate pre-defibrillation amplitude remained significantly associated with ROSC while maximal amplitude did not (P = .006 and P = .135).

CONCLUSIONS

Amplitude of the VF waveform at the moment of defibrillation has a strong association with successful defibrillation, ROSC, and SHD.

Systematic mapping study of data mining–based empirical studies in cardiology

Data mining provides the methodology and technology to transform huge amount of data into useful information for decision making. It is a powerful process to extract knowledge and discover new patterns embedded in large data sets. Data mining has been increasingly used in medicine, particularly in cardiology. In fact, data mining applications can greatly benefits all parts involved in cardiology such as patients, cardiologists and nurses. This article aims to perform a systematic mapping study so as to analyze and synthesize empirical studies on the application of data mining techniques in cardiology. A total of 142 articles published between 2000 and 2015 were therefore selected, studied and analyzed according to the four following criteria: year and channel of publication, research type, medical task and empirical type. The results of this mapping study are discussed and a list of recommendations for researchers and cardiologists is provided.

Novel CPR system that predicts return of spontaneous circulation from amplitude spectral area before electric shock in ventricular fibrillation

AIM

Amplitude spectral area (AMSA), an index for analysing ventricular fibrillation (VF) waveforms, is thought to predict the return of spontaneous circulation (ROSC) after electric shocks, but its validity is unconfirmed. We developed an equation to predict ROSC, where the change in AMSA (ΔAMSA) is added to AMSA measured immediately before the first shock (AMSA1). We examine the validity of this equation by comparing it with the conventional AMSA1-only equation.

METHOD

We retrospectively investigated 285 VF patients given prehospital electric shocks by emergency medical services. ΔAMSA was calculated by subtracting AMSA1 from last AMSA immediately before the last prehospital electric shock. Multivariate logistic regression analysis was performed using post-shock ROSC as a dependent variable.

RESULTS

Analysis data were subjected to receiver operating characteristic curve analysis, goodness-of-fit testing using a likelihood ratio test, and the bootstrap method. AMSA1 (odds ratio (OR) 1.151, 95% confidence interval (CI) 1.086-1.220) and ΔAMSA (OR 1.289, 95% CI 1.156-1.438) were independent factors influencing ROSC induction by electric shock. Area under the curve (AUC) for predicting ROSC was 0.851 for AMSA1-only and 0.891 for AMSA1+ΔAMSA. Compared with the AMSA1-only equation, the AMSA1+ΔAMSA equation had significantly better goodness-of-fit (likelihood ratio test P<0.001) and showed good fit in the bootstrap method.

CONCLUSIONS

Post-shock ROSC was accurately predicted by adding ΔAMSA to AMSA1. AMSA-based ROSC prediction enables application of electric shock to only those patients with high probability of ROSC, instead of interrupting chest compressions and delivering unnecessary shocks to patients with low probability of ROSC.