Machine Learning-Based Rapid Prediction of Sudden Cardiac Death (SCD) Using Precise Statistical Features of Heart Rate Variability for Single Lead ECG Signal

Marine n-3 polyunsaturated fatty acids (PUFA) may improve autonomic dysfunction, as indicated by an increase in heart rate variability (HRV) and reduce the risk of sudden cardiac death. Hence, the aim of this study was to investigate the effects of marine n-3 PUFA on 24-h HRV in patients on chronic dialysis, who have a high risk of sudden cardiac death. Between June 2014 and March 2016, 112 patients on chronic dialysis from Denmark were allocated to a daily supplement of 2 g marine n-3 PUFA or control for three months in a randomized, double-blinded, controlled trial. A 48-h Holter monitoring was performed and mean 24-h HRV indices for the two days were available in 85 patients. The mean age was 62.3 years (SD: 14.3) and median dialysis vintage was 1.7 years (IQR: 0.5, 6.4). Within-group and between-group changes in outcome were evaluated by a paired and two sample t-test, respectively. Marine n-3 PUFA did not change the primary endpoint SDNN (SD of all RR-intervals) reflecting overall HRV, but other HRV indices increased and the mean RR-interval increased significantly, corresponding to a decrease in heart rate by 2.5 beats per minute (p = 0.04). In conclusion, marine n-3 PUFA did not change SDNN, but the mean heart rate was significantly reduced and changes in other HRV-indices were also observed, indicating an increase in vagal modulation that might be protective against malignant ventricular arrhythmias.

Download Full-text

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

Sensors ◽

10.3390/s20195483 ◽

2020 ◽

Vol 20 (19) ◽

pp. 5483

Author(s):

Marisol Martinez-Alanis ◽

Erik Bojorges-Valdez ◽

Niels Wessel ◽

Claudia Lerma

Keyword(s):

Heart Rate ◽

Support Vector Machine ◽

Heart Rate Variability ◽

Sudden Cardiac Death ◽

Cardiac Death ◽

Area Under The Curve ◽

Premature Ventricular Complex ◽

Support Vector ◽

Auc Value ◽

Sudden Cardiac Death Risk

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.

Download Full-text