Abstract
Acute life threatening events such as cardiac/respiratory arrests are often predictable in adults and children. However critical events such as unplanned extubations are considered as not predictable. This paper seeks to evaluate the ability of automated prediction systems based on feature space embedding and time series methods to predict unplanned extubations in paediatric intensive care patients. We try to exploit the trends in the physiological signals such as Heart Rate, Respiratory Rate, Systolic Blood Pressure and Oxygen saturation levels in the blood using signal processing aspects of a frame-based approach of expanding signals using a nonorthogonal basis derived from the data. We investigate the significance of the trends in a computerised prediction system. The results are compared with clinical observations of predictability. We will conclude by investigating whether the prediction capability of the system could be exploited to prevent future unplanned extubations.
Original language | English |
---|---|
Title of host publication | 2014 IEEE-EMBS international conference on Biomedical and Health Informatics (BHI) |
Publisher | IEEE |
Pages | 488-491 |
Number of pages | 4 |
ISBN (Print) | 978-1-4799-2131-7 |
DOIs | |
Publication status | Published - 2014 |
Event | 2014 IEEE-EMBS international conference on Biomedical and Health Informatics - Valencia, Spain Duration: 1 Jun 2014 → 4 Jun 2014 |
Conference
Conference | 2014 IEEE-EMBS international conference on Biomedical and Health Informatics |
---|---|
Abbreviated title | BHI 2014 |
Country/Territory | Spain |
City | Valencia |
Period | 1/06/14 → 4/06/14 |