Ventricular fibrillation frequency characteristics and time evolution in piglets: a developmental study

MLWAVE: A novel algorithm to classify primary versus secondary asphyxia-associated ventricular fibrillation

INTRODUCTION/HYPOTHESIS

The outcome of cardiopulmonary resuscitation (CPR) depends on timely recognition of the underlying cause of cardiac arrest. Ventricular fibrillation (VF) waveform analysis to differentiate primary VF from secondary asphyxia-associated VF may allow tailoring of therapies to improve cardiac arrest outcomes. Therefore, the primary goal of this investigation was to develop a novel technique utilizing wavelet synchrosqueezed transform (WSST) and decision-tree classifier that was specifically adapted to discriminate between these two incidents of VF.

METHODS

Secondary analytical investigation of electrocardiography (ECG) data obtained from swine models of either primary VF (n=18) or secondary asphyxia-associated VF (7min of asphyxia prior to VF induction; n=12). In the primary analysis, WSST technique was applied to the first 35s of the VF ECG signal to identify the most differentiating characteristics of the signal for use as features to develop a machine learning algorithm to classify the arrest as either primary VF vs. secondary asphyxia-associated VF. The performance of this new interactive Machine Learning algorithm with Wavelet Energy features of ECG (MLWAVE) was assessed using both classification accuracy and area under the receiver operating characteristic curve (AUCROC). To evaluate the validity of the new technique, the amplitude spectrum area (AMSA)-based technique, a well-established defibrillation classification method, was also applied to the same ECG signals. The classification accuracy and AUCROC were then compared between the two techniques.

RESULTS

For the primary analysis evaluating the first 35s of the VF waveform, the MLWAVE technique classified the type of VF with high accuracy (28/28 [100%], AUCROC: 1.00). The MLWAVE technique performed better than the AMSA technique across all comparisons, but given the small sample sizes, differences were not statistically significant (accuracy: 100% vs. 85.7%; p=0.24; AUCROC: 1.00 vs. 0.82; p=0.24).

CONCLUSION

This analytical investigation illustrates the advantages of the MLWAVE signal processing method which was associated with 100% accuracy in classifying the type of VF waveform: primary vs. asphyxia-associated. Such classification could lead to personalized tailoring of resuscitation (e.g., immediate defibrillation vs. continued CPR and treatment of reversible cardiac arrest causes before defibrillation) to improve outcomes for cardiac arrest.

The influence of myocardial substrate on ventricular fibrillation waveform: a swine model of acute and postmyocardial infarction

OBJECTIVE

In cardiac arrest resulting from ventricular fibrillation, the ventricular fibrillation waveform may be a clue to its duration and predict the likelihood of shock success. However, ventricular fibrillation occurs in different myocardial substrates such as ischemia, heart failure, and structurally normal hearts. We hypothesized that ventricular fibrillation is altered by myocardial infarction and varies from the acute to postmyocardial infarction periods.

DESIGN

An animal intervention study was conducted with comparison to a control group.

SETTING

This study took place in a university animal laboratory.

SUBJECTS

Study subjects included 37 swine.

INTERVENTIONS

Myocardial infarction was induced by occlusion of the midleft anterior descending artery. Ventricular fibrillation was induced in control swine, acute myocardial infarction swine, and in postmyocardial infarction swine after a 2-wk recovery period.

MEASUREMENTS AND MAIN RESULTS

Ventricular fibrillation was recorded in 11 swine with acute myocardial infarction, ten postmyocardial infarction, and 16 controls. Frequency (mean, median, dominant, and bandwidth) and amplitude-related content (slope, slope-amp [slope divided by amplitude], and amplitude-spectrum area) were analyzed. Frequencies at 5 mins of ventricular fibrillation were altered in both acute myocardial infarction (p < .001 for all frequency characteristics) and postmyocardial infarction swine (p = .015 for mean, .002 for median, .002 for dominant frequency, and <.001 for bandwidth). At 5 mins, median frequency was highest in controls, 10.9 +/- .4 Hz; lowest in acute myocardial infarction, 8.4 +/- .5 Hz; and intermediate in postmyocardial infarction, 9.7 +/- .5 Hz (p < .001 for acute myocardial infarction and p = .002 for postmyocardial infarction compared with control). Slope and amplitude-spectrum area were similar among the three groups with a shallow decline after minute 2, whereas slope-amp remained significantly altered for acute myocardial infarction swine at 5 mins (p = .003).

CONCLUSIONS

Ventricular fibrillation frequencies depend on myocardial substrate and evolve from the acute through healing phases of myocardial infarction. Amplitude related measures, however, are similar among these groups. It is unknown how defibrillation may be affected by relying on the ventricular fibrillation waveform without considering myocardial substrate.