Preliminary Content

Acknowledgements

I want to thank a few people.

Preface

This is an example of a thesis setup to use the reed thesis document class (for LaTeX) and the R bookdown package, in general.

Dedication

You can have a dedication here if you wish.

Abstract

Currently, Point-of-Care (POC) ECG monitoring works either as plot devices or alarms for abnormal cardiac rhythms using predefined normal trigger ranges and some rhythm analysis, which raises the problem of false alarms. In comparison, complex 12-derivation ECG machines are not suitable to use as simple monitors and are used with strict techniques for formal diagnostics. We aim to identify, on streaming data, life-threatening hearth electric patterns to reduce the number of false alarms, using low CPU and memory maintaining robustness. The study design is comparable to a diagnostic study, where high accuracy is essential. Physionet’s 2015 challenge yielded very good algorithms for reducing false alarms. However, none of the authors reported benchmarks, memory usage, robustness test, or context invariance that could assure its implementation on real monitors to reduce alarm fatigue indeed. We expect to identify the obstacles of detecting life-threatening ECG changes within memory, space, and CPU constraints and to reduce ECG monitor’s false alarms using the proposed methodology, and assess the feasibility of implementing the algorithm in the real world and other settings than ICU monitors.