作者: Filipe Portela , Manuel Filipe Santos , Alvaro Silva , Fernando Rua , Antonio Abelha
DOI: 10.1109/IECBES.2014.7047478
关键词:
摘要: Cardiac Arrhythmia (CA) is very dangerous and can significantly undermine patient condition. New tools are fundamental to forecast prevent possible critical situations. In order help clinicians acting proactively, predictive data mining real-time models were induced using online-learning. As input variables considered those acquired at the admission complementary (vital signs, laboratory results, therapeutics) hourly collected. The results motivating; sensitivity near 95% was obtained when Support Vector Machines. approach explored in this work reveals be an interesting contribution healthcare terms of predicting CA a good direction further explored.