Search

Arrhythmic Sudden Cardiac Death (SCD) is still a major clinical challenge even though much research has been done in the field. Machine learning techniques give a powerful tool for stratifying arrhythmic risk. We analyzed 40 Holter recordings from heart failure patients, 20 of which were characterized as high arrhythmia risk after 16 months follow up. The two groups (high and low risk) were not statistically different in basic clinical characteristics. We performed windowed analysis and computed 25 Heart Rate Variability (HRV) indices. We fed these indices as input to two classifiers: Support Vector Machines (SVM) and Random Forests (RF). The classification results showed that the automatic classification of the two groups of subjects is possible. [ABSTRACT FROM PUBLISHER]

While Non-Sustained Ventricular Tachycardia (NSVT) can be characterized as innocent in healthy persons, such arrhythmias in post-infarction patients can be associated with an increased risk for Arrhythmic Sudden Cardiac Death (SCD). The Autonomic Nervous System (ANS) may influence the electrical status before fatal arrhythmias initiations. In this work we study the differences between the behavior of Deceleration Capacity (DC) of heart rate before the onset of NSVT and in the rest of the signal. Twenty (20) patients having presented NSVT episodes are examined. Nine (9) of them have been classified as high risk for SCD after 16 months of follow up, while the rest (11) have been considered as low risk. For each NSVT episode the 30 min period before the episode and the 150 min period exactly before this period were compared. Windowed analysis was performed. Mean values showed that DC is reduced before NSVT episodes in both high and low risk patients. High risk patients presented lower mean values for DC compared to the low risk. [ABSTRACT FROM PUBLISHER]