Predicting ventricular fibrillation

A method comprising:

• training a machine learning model to predict an onset of a Ventricular Fibrillation (VF) event, on a training set, the method comprising:
• (i) extracting Heart Rate Variability (HRV) parameters from temporal beat activity signal samples, wherein at least some of said samples include a representation of a VF event, and
• (ii) labeling the signal samples with labels associated with one of:
• a first period of time immediately preceding a VF event in a temporal beat activity sample, a second period of time immediately preceding the first period of time in a temporal beat activity sample, and all other periods of time in a temporal beat activity sample,
• wherein said training set is generated by:
• (i) segmenting each of said samples into a plurality of sample segments, based, at least in part, on a specified minimum number of said beats in each of said sample segments;
• (ii) randomly selecting one or more subsets of said sample segments from said plurality of sample segments;
• and
• (iii) combining one or more of said subsets into said training set.