Prediction of Acute Hypotension Episode
Hutashani B. Rayate1, Vidya V. Deshmukh2
1Hutashani B. Rayate, Amrapali Tower, Ashoka Marga, Near Fame Theather. Nashik Nashik Maharashtra, India.
2Vidya V. Deshmukh, Amrapali Tower, Ashoka Marga, Near Fame Theather. Nashik Nashik Maharashtra, India.
Manuscript received on November 27, 2013. | Revised Manuscript received on December 13, 2013. | Manuscript published on December 30, 2013. | PP: 234-236 | Volume-3, Issue-2, December 2013. | Retrieval Number: B2448123213/2013©BEIESP
Open Access | Ethics and Policies | Cite
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Acute hypotensive episodes (AHE) are serious clinical events in intensive care unit. It causes damage of irreversible organ and may lead to death. When occurrence of an Acute Hypotension Episode (AHE) is predicted in advance, an appropriate intervention can reduces the risk for patient. The prediction is to be made using two groups of ICU patient records from the MIMIC II Database from the Physionet. The physionet challenge is divided into two parts. The first part is to distinguish between patients who have experienced acute hypotension episodes and patients who do not. The second part of this challenge is to predict acute hypotension episodes. We here present an algorithm for prediction of AHE using mean arterial blood pressure (MAP). We then used information divergence (or Kullback-Liebler divergence) between two distributions to identify the most discriminative features. The objective of this work is to describe an automated statistical method that produces an automated method to predict AHE using the least data possible.
Keywords: Hypotension Prediction, Information Diversion, K-L Diversion theorem, Mean Arterial Blood Pressure.