A 24/7 Monitorization Tool for Avoiding Hypotensive Episodes in Critical Care

Authors

Abstract

The sudden fall of blood pressure (hypotension) is a common complication in medical care. In critical care patients, hypotension (HT) may cause serious heart, endocrine or neurological disorders, inducing severe or even lethal events. Moreover, recent studies report an increase of mortality in HT prone hemodialysis patients in need of critical care. If HT could be predicted in advance, medical staff could take action to minimize its effects, or even avoid its occurrence. Typically, most medical systems have focused on monitoring and detecting current patient status, rather than determining biosignal trends or predicting a patient’s future status. Therefore, predicting HT episodes in advance remains a challenge. Furthermore, since critical care actions such as hemodialysis are oftenly inconvenient and uncomfortable procedures, HT prediction or detection methods should be non-invasive, whenever possible. In this paper, we present a solution for continuous monitorization and prediction of HT episodes, using heart rate (HR) and mean blood pressure (BP) non-invasive measured biosignals. We propose an architecture for a HT Predictor (HTP) Tool, presenting a set of tools and a real-time database capable of continuously storing and real-time monitoring all patient’s historical HR and BP biosignal data, and efficiently alerting both probable and detected occurrences of HT episodes for each patient for the following 60 minutes. Additionally, the system promotes medical staff mobility, by taking advantage of using mobile personal devices such as mobile phones and PDA’s, optimizing human resources. Finally, an experimental evaluation on real-life data from the well known Physionet database shows the efficiency of the tool, outperforming the winning proposal of the Physionet 2009 Challenge.

Keywords

Hypotension detection and prediction, Medical and health care systems and applications, Biosignals analysis and processing

Subject

Healthcare Information Systems

Conference

IDEAS 2010 - International Database Engineering & Applications Symposium, August 2010

PDF File