False Alarm Reduction in ICU Using Ensemble Classifier Approach

During patient monitoring, false alert in the Intensive Care Unit (ICU) becomes a major problem. In the category of alarms, pseudo alarms are regarded as having no clinical or therapeutic significance, and thus they result in fatigue alarms. Artifacts are misrepresentations of tissue structures produced by imaging techniques. These Artifacts can invalidate the Arterial Blood Pressure (ABP) signal. Therefore, it is very important to develop algorithms that can detect artifacts. However, ABP has algorithmic shortcomings and limitations of design. This study is aimed at developing a real-time enhancement of independent component analysis (EICA) and time-domain detection of QRS that can be used to distinguish between imitation and false alarms. QRS detection is used to examine the waveform values appropriately by calculating the signal values, which are then utilized to identify the areas of high-frequency noise. AHE method is tapped to find the signal saturation values after the removal of such noise values. For artifact detection, Haar Wavelet Transform (HWT) and QRS detection methods are proposed. These operations are performed under the time domain. The classification model is proposed and trained by Fuzzy Neural Network (FNN), Extreme Random Trees (ERTs), and Extreme Learning Machine (ELM).