High frequency distributed data stream event correlation to improve neonatal clinical management

  • Authors:

  • Carolyn McGregor;Mike Stacey

  • Affiliations:

  • University of Western Sydney, Penrith, South DC;University of Western Sydney, Penrith South DC

  • Venue:
  • Proceedings of the 2007 inaugural international conference on Distributed event-based systems
  • Year:
  • 2007

Quantified Score

Hi-index 0.00

Visualization

Abstract

Approximately eighteen percent (18%) of babies born in New South Wales (NSW), Australia require special care or neonatal intensive care admission. Premature babies can be up to 17 weeks early and may only weigh 450gms; they can spend 3 or 4 months in intensive care and have dozens of specific diseases before discharge, many of these may have long term implications for the future health of the individual. In addition, fifteen percent of neonatal intensive care admissions are transferred after delivery from smaller regional or remote hospitals without intensive care facilities to larger Tertiary Referral or Children's Hospitals with Neonatal Intensive Care Units (NICUs). Similar conditions apply within Australia, New Zealand, Canada, USA and elsewhere where small non-tertiary units are spread throughout the country. This paper presents case study based applied research in progress supporting the development of a distributed event stream processing framework to enable high frequency distributed data stream event correlation to improve neonatal clinical management. This research extends the traditional notion of event-based approaches by extending the notion of an event to incorporate a composite event that exists over a period of time, as is required within the domain of health and medicine. This is achieved through a multi-agent event calculus based approach that supports temporal abstraction. A key contribution of this research is the ability to support automated medical condition onset detection.