Developing an ability to classify ventricular fibrillation (VF) into cases where restoration of an organized electrical activity (ROEA) is achieved after the application of a defibrillatory shock, and telling these cases apart from cases where such a restoration does not happen, is of paramount importance to guide first- aid therapy in patients in cardiac arrest. Indeed, VF is a medical emergency of enormous proportions and it is one of the first causes of sudden death in a large range of population's age. In this article, we address this problem in the light of recent achievements in the field of machine learning and present results with the use of a new machine called GEM (Guaranteed Error Machine) applied to a group of patients with out-of-hospital cardiac arrest. While our results indicate that this methodology is promising, it remains a fact that this study is still at the outset, and by this article we also want to make the current state of the art available with the use of GEM to others and indicate what we believe are the research priorities for the near future. This is done in the belief that this important medical endeavor is better addressed by the cooperation of various teams, possibly carrying complementary expertise.
|Titolo:||Ventricular Defibrillation: Classification with GEM and a Roadmap for Future Investigations|
|Data di pubblicazione:||2017|
|Appare nelle tipologie:||04.1 Contributo in Atti di convegno|
File in questo prodotto: