1 Objectives and the research question

This research aims to identify, on streaming data, abnormal hearth electric patterns, specifically those which are life-threatening, to be a reliable signal for Intensive Care Units to respond quickly to those situations. It also may be able to continuously analyze new data and correct itself shutting off false alarms.

As it is known, this goal is not a new problem, so the main questions to solve are: (1) Can we reduce the number of false alarms in the ICU setting? (2) Can we accomplish this objective using a minimalist approach (low CPU, low memory) while maintaining robustness? (3) Can this approach be used in other health domains other than ICU or ECG?