Non-linear dynamical signal characterization for prediction of defibrillation success through machine learning

Abstract

BackgroundVentricular Fibrillation (VF) is a common presenting dysrhythmia in the setting of cardiac arrest whose main treatment is defibrillation through direct current countershock to achieve return of spontaneous circulation. However, often defibrillation is unsuccessful and may even lead to the transition of VF to more nefarious rhythms such as asystole or pulseless electrical activity. Multiple methods have been proposed for predicting defibrillation success based on examination of the VF waveform. To date, however, no analytical technique has been widely accepted. We developed a unique approach of computational VF waveform analysis, with and without addition of the signal of end-tidal carbon dioxide (PetCO2), using advanced machine learning algorithms. We compare these results with those obtained using the Amplitude Spectral Area (AMSA) technique.MethodsA total of 90 pre-countershock ECG signals were analyzed form an accessible preshosptial cardiac arrest database. A unified predictive model, based on signal processing and machine learning, was developed with time-series and dual-tree complex wavelet transform features. Upon selection of correlated variables, a parametrically optimized support vector machine (SVM) model was trained for predicting outcomes on the test sets. Training and testing was performed with nested 10-fold cross validation and 6–10 features for each test fold.ResultsThe integrative model performs real-time, short-term (7.8 second) analysis of the Electrocardiogram (ECG). For a total of 90 signals, 34 successful and 56 unsuccessful defibrillations were classified with an average Accuracy and Receiver Operator Characteristic (ROC) Area Under the Curve (AUC) of 82.2% and 85%, respectively. Incorporation of the end-tidal carbon dioxide signal boosted Accuracy and ROC AUC to 83.3% and 93.8%, respectively, for a smaller dataset containing 48 signals. VF analysis using AMSA resulted in accuracy and ROC AUC of 64.6% and 60.9%, respectively.ConclusionWe report the development and first-use of a nontraditional non-linear method of analyzing the VF ECG signal, yielding high predictive accuracies of defibrillation success. Furthermore, incorporation of features from the PetCO2 signal noticeably increased model robustness. These predictive capabilities should further improve with the availability of a larger database.

A support vector machine for predicting defibrillation outcomes from waveform metrics

“…Nevertheless, a rough comparison with an earlier study, also using a nonparametric classifier type, 15 our SVMs performance on specificity and PPR were somehow superior (72% vs 27% and 84% vs 15%, respectively). In more recent studies using similar outcome definitions, Watson et al 27 reported a specificity of 66% and sensitivity of 95% using a linear classifier (vs our 87.6% sensitivity), and Shandilya et al 18 reported a sensitivity of 44.1% and specificity of 77.2% using a linear kernel SVM with C = 4.5 (vs our 71.8% specificity). Larger training sets (e.g., N > 200) and increased number of expert cardiologists (about 6) in the database consensus annotation task, would enable prediction performances >90% without overtuning.…”

“…15,16 The SVM concept derives from recent advances in machine learning theory and has been widely adopted to successfully improve classification performance in circumstances where there is a limited population size (N < 500). [17][18][19][20] In general terms, the goal of a SVM is to produce a prediction model based on a training data, with instances of several attributes or measured features associated to a target outcome value. Thus, using a SVM involves separating data into training and testing sets and implementing some cross validation resampling of the available data.…”

Application of Entropy-Based Features to Predict Defibrillation Outcome in Cardiac Arrest

“…As shown in Table 3, the BER for the best entropy predictor (FuzzEn) was 2.4 points higher than that of the best classical predictor (MSI), which means a combined increase of around five points in SE and SP. There is currently contradictory evidence on the benefits of combining features for shock outcome prediction, with studies showing increases of up to six points in BER for combinations of 3-10 features [57,58] and studies showing no increase in accuracy [23,26]. In a recent study with a large cohort of 1617 patients and 3828 shocks, He et al [26] found no benefits in combining features and showed the strong correlation among features, such as MdS, AMSA, PPA or energy.…”

“…The present study has some limitations. First, the results are based on the retrospective analysis of data, and a prospective study would be needed to confirm the benefits of using entropy-based waveform analysis to improve VF therapy on OHCA patients; second, patient outcome data were missing in many of the cases, so the prediction of survival and survival with good neurological outcome based on entropy could not be assessed; finally, the cohort of patients was comparable or larger than that of many studies addressing shock outcome prediction [24,25,57,58], but still limited to draw conclusive evidence on the benefits of using entropy measures to guide VF therapy during OHCA. Our results should be confirmed on data from larger and independent patient cohorts.…”

“…FuzzEn showed a decrease in BER of 3-5 points with respect to PPA, MdS and/or AMSA. Most likely, shock outcome prediction could be improved by incorporating additional information, such as the relative changes in the predictors between consecutive shocks [59], or other clinical variables, such as end tidal CO2 levels [58].…”