NEONATE

Effective Decision Support in the Neonatal Intensive Care Unit

Funded by the ESRC/EPSRC PACCIT Programme

Department of Computing Science - University of Aberdeen
Department of Psychology - University of Aberdeen
Department of Child Life and Health - University of Edinburgh
Neonatal Intensive Care Unit - Simpson Maternity Hospital, Edinburgh

Brief Outline of the Project

The NEONATE project formally started on March 1st 2001, and is supported (for 42 months) by a grant from the ESRC/EPSRC PACCIT Programme.

Introduction

The modern Neonatal Intensive Care Unit is an information-rich environment, and appropriating this varied information is cognitively demanding for medical and nursing staff. With this in mind, the aim of the NEONATE project is to apply information technology to the support of clinical decision-making in neonatal intensive care.

The NEONATE project has 3 major objectives:

• To investigate on a systematic basis, a comprehensive range of actions taken in the Neonatal Intensive Care Unit;
• To identify the terms used to describe patient state by staff at different levels and types of expertise;
• To use the results of these investigations to implement and evaluate computerised aids designed to support clinical decision making

Making more data available to decision makers does not necessarily of itself lead to improved care. This has been demonstrated in the neonatal intensive care unit where providing nurses and junior doctors with detailed trends of physiological information does not lead to improved patient outcomes. Our earlier studies (COGNATE project) have shown that a major reason for this finding is that the staff caring for the infants observe them closely and frequently to obtain more information than just the data shown on the monitors.

It is possible that by incorporating the results of our study into the design of the monitors, and by using some artificial intelligence techniques, the computers could be programmed to offer a more useful presentation of the trend data, and thereby complement the direct observations.

Methods

Junior and senior medical and nursing staff participated in interviews to delineate their roles in the unit and the vocabularies they use to categorise baby data that they obtain by observation and clinical examination. The aim is to enhance the displayed information, in ways that go beyond just the presentation of the raw data collected automatically by the physiological monitoring devices. The intention is to give a more complete picture of the current state of the baby and to offer more effective support for clinical care and decision-making.

Where is All This Going?

The data gleaned from staff, will be analysed, and will be used in the development of a decision support system to help staff when they need it.

Findings will be published in cognitive psychology, artificial intelligence and medical journals and the data will be presented nationally and internationally. The findings will have broad relevance to cognitive science in medicine and particularly to other types of intensive care units.

Project Team

The NEONATE project involves Computer Scientists and Cognitive Psychologists at the University of Aberdeen working with neo-natal intensive care specialists at the Simpson Maternity Hospital in Edinburgh. The people involved with the project are:

• Professor Jim Hunter * (jhunter@csd.abdn.ac.uk )
• Professor Robert Logie * (rlogie@staffmail.ed.ac.uk )
• Professor Neil McIntosh * (NM@srv2.med.ed.ac.uk )
• Dr Yvonne Freer (yvonne.freer@luht.scot.nhs.uk)
• John Quinn

Associate Team Members

• Dr Anna Law * (alaw2@staffmail.ed.ac.uk)
• Peter Badger, Commercial collaborator (Peter@clevermed.com)
• Paul McCue, PhD student (pmccue@csd.abdn.ac.uk)

Former Team Members

• Dr Gary Ewing * (gewing@csd.abdn.ac.uk)
• Alan Maxwell
• Sue Rudkin *
• Lindsey Ferguson*

* These staff are/were formally part of the project (funded) under the ESPRC grant.

Publications

Other Project Documents

• The scientific proposal;
• The slides used at a brief presentation at the first PACCIT program meeting in Glasgow (17th January 2001)
• The slides used at a presentation at the PACCIT program meeting in London (6th November 2001)
• The slides used at a presentation at ECAI 2002 in Lyon, France (July 2002 )
• The slides used at the British Association for the Advancement of Science meeting in Leicester (12th Sept. 2002)
• The poster presented at AIME 03, 9th European Conference on Artificial Intelligence in Medicine in Cyprus (18th - 20th October 2003)
• The slides for "The NEONATE Database" paper at at AIME03
• The slides for "NEONATE: Decision Support in the Neonatal Intensive Care Unit - A Preliminary Report" paper at at AIME03

Related Links

• University of Aberdeen Computing Science Department SumTime project
• Eamon Keogh's Time Series Data mining Archive
• Jim Hunter's Time Series WorkBench
• Institute of Child Life and Health

You can obtain a text only version of this page by clicking here.