Prediction of Sudden Cardiac Death Risk with a Support Vector Machine Based on Heart Rate Variability and Heartprint Indices

Abstract

Most methods for sudden cardiac death (SCD) prediction require long-term (24 h) electrocardiogram recordings to measure heart rate variability (HRV) indices or premature ventricular complex indices (with the heartprint method). This work aimed to identify the best combinations of HRV and heartprint indices for predicting SCD based on short-term recordings (1000 heartbeats) through a support vector machine (SVM). Eleven HRV indices and five heartprint indices were measured in 135 pairs of recordings (one before an SCD episode and another without SCD as control). SVMs (defined with a radial basis function kernel with hyperparameter optimization) were trained with this dataset to identify the 13 best combinations of indices systematically. Through 10-fold cross-validation, the best area under the curve (AUC) value as a function of γ (gamma) and cost was identified. The predictive value of the identified combinations had AUCs between 0.80 and 0.86 and accuracies between 80 and 86%. Further SVM performance tests on a different dataset of 68 recordings (33 before SCD and 35 as control) showed AUC = 0.68 and accuracy = 67% for the best combination. The developed SVM may be useful for preventing imminent SCD through early warning based on electrocardiogram (ECG) or heart rate monitoring.

Machine learning of electrophysiological signals for the prediction of ventricular arrhythmias: systematic review and examination of heterogeneity between studies

“…Ultimately, a total of 46 studies were included in this review. 15 , 16 , 17 , 18 , 30 , 31 , 32 , 33 , 34 , 35 , 36 , 37 , 38 , 39 , 40 , 41 , 42 , 43 , 44 , 45 , 46 , 47 , 48 , 49 , 50 , 51 , 52 , 53 , 54 , 55 , 56 , 57 , 58 , 59 , 60 , 61 , 62 , 63 , 64 , 65 , 66 , 67 , 68 , 69 , 70 , 71 Out of these 46 studies, 36 used one or more ad-hoc dataset(s) and were pooled in separate meta-analysis. 30 , 31 , 32 , 33 , 34 , 35 , 36 , 37 , 39 , 40 , 41 , 42 , 43 , 44 , 46 , 47 , 48 , 49 , 50 , 51 , 52 , 54 , 55 , 57 , …”

“…The characteristics of studies are summarised in Table 1 , details on the electrophysiological signals used are displayed in Supplementary Material Table S6 . 15 , 16 , 17 , 18 , 38 , 45 , 53 , 56 , 62 , 64 Two studies used intracardiac EGMs, 15 , 56 seven used body surface ECG recordings 16 , 17 , 38 , 45 , 53 , 62 , 64 and one study used ventricular monophasic action potentials (MAP) as model input. 18 ECGs ranged from 10 s till 24 h in duration and differed in number of leads (1-, 3-, 7- and 12-leads) and sampling rate (125 Hz–1600 Hz).…”

“… 18 ECGs ranged from 10 s till 24 h in duration and differed in number of leads (1-, 3-, 7- and 12-leads) and sampling rate (125 Hz–1600 Hz). Support vector machine classifiers were implemented as prediction model in six studies, 15 , 17 , 18 , 56 , 62 , 64 ensemble learning methods (random forests, decision tree) in three studies 15 , 38 , 45 and artificial neural network in one study. 53 Kwon et al.…”

“…long-term prediction). K-fold cross-validation and leave-one-out-cross validation were used for model validation in four studies validation, 17 , 56 , 62 , 64 whereas a hold-out test set was used in six studies. 15 , 16 , 18 , 38 , 45 , 53 External validation of the model was performed in two studies.…”

Atrial fibrillation prediction by combining ECG markers and CMR radiomics

“…The models were trained with a Support Vector Machine (SVM) technique which has been widely used in cardiovascular risk predictions 58,59 due to its numerous advantages such as computationally efficient and robustness for real-world applications as well as the ability to find non-linear relationships through the kernel trick.…”