Machine Learning
Time series data mining: identifying temporal patterns for characterization and prediction of time series events
Artificial Intelligence in Medicine
| Hi-index | 0.00 |
Changes in the normal rhythmicity of a human heart may result in different cardiac arrhythmias, which may be immediately fatal or cause irreparable damage to the heart when sustained over long periods of time. The ability to automatically identify arrhythmias from ECG recordings is important for clinical diagnosis and treatment, as well as, for understanding the electrophysiological mechanisms of the arrhythmias. This paper proposes a novel approach to efficiently and accurately identify normal sinus rhythm and various ventricular arrhythmias through a combination of phase space reconstruction and machine learning techniques. Data was recorded from patients experiencing spontaneous arrhythmia, as well as, induced arrhythmia. The phase space attractors of the different rhythms were learned from both inter- and intra-patient arrhythmic episodes. Out-of-sample ECG rhythm recordings were classified using the learned attractor probability distributions with an overall accuracy of 83.0%.