PREDICTOR

Abstract

Intensive Care Units (ICUs) are sections within hospitals which look after patients who are critically ill, or unstable, and require intensive treatment and monitoring to help restore them to more normal physiological ranges. Further, the ICU at Glasgow Royal Infirmary has developed a scoring system based on the severity of the patient's illness. This scoring system has 5 levels of severity: A to E (A means that the patient is ready to be discharged and E means that the patient is extremely ill). The clinicians and the analysts of Glasgow Royal Infirmary¿s ICU want to perform statistical studies on their patients¿ data and hourly scores using the available information produced by the ICU¿s patient management system. An additional program was needed to study the relationship between these scores and the other patient parameters. I-PREDICTOR, developed for my project, is a user-friendly tool, which offers the clinicians and the analysts the facility to read their datasets and apply a group of statistical functions to these. This document describes the process carried out to develop I-PREDICTOR, the evaluations carried out and possible future work.