ECG based risk stratification for sudden cardiac death.

Sudden cardiac death (SCD) is one of the main causes of death worldwide, accounting for approximately 4.5 million deaths per year. Since it occurs relatively often in younger people, its socio-economic impact is much higher than the impact of other major health issues like cerebrovascular disease. It is therefore important to accurately determine which patients are at risk for developing dangerous arrhythmias in order to implement optimal treatment and prevention strategies. Prediction of sudden cardiac death is however not an evident task, and providing reliable indicators has been a very active area of research for many decades. This research therefore focuses on the development of algorithms to extract potential SCD risk factors from the ECG signal, through a combination of tensor methods and machine learning approaches.

Tensors are multilinear generalizations of vectors and matrices which can be used to analyse all leads of the ECG channel simultaneously. Since the different spatial leads give a global view of the heart in three dimensions, it makes sense to fully exploit the shared information by combining the information from all leads. The first part of this thesis presents four tensor-based methods to detect and analyse different ECG characteristics. We show that by modifying the tensor decomposition, specific signal characteristics such as changes in heart rate or increased noise levels can be taken into account. This ensures that the developed methods can be optimally used in real-life scenarios, which is confirmed by the good results on different clinical datasets.

The second part of this research is focused on QRS fragmentation (fQRS), a promising risk factor for sudden cardiac death. Detection of fQRS heavily relies on visual inspection, which has been shown to be dependent on rater experience. Therefore, we propose a method to detect and quantify QRS fragmentation using machine learning methods. Quantification of fQRS is a novel approach to examining the biomarker, and we demonstrate that this innovative fQRS score largely correlates to the certainty of QRS fragmentation in a signal. Since the proposed fQRS score is determined objectively, the obtained results can be easily repeated in different datasets, which promotes the clinical use of this parameter.

Finally, the last part of this thesis investigates to what extent advanced machine learning methods can provide added value in modelling the survival of patients. We show that the combination of the proposed fQRS score with advanced survival models is better capable of predicting the survival time of patients than commonly used statistical models.