Service-oriented subscription management of medical decision data in the intensive care unit

• Published in: Methods of information in medicine Vol. 47; no. 4; p. 364
• Main Authors: Van Hoecke, S, Decruyenaere, J, Danneels, C, Taveirne, K, Colpaert, K, Hoste, E, Dhoedt, B, De Turck, F
• Format: Journal Article
• Language: English
• Published: Germany 01.01.2008
• Subjects: Decision Making, Computer-Assisted; Decision Support Systems, Clinical - organization & administration; Humans; Intensive Care Units; Internet; Programming Languages; User-Computer Interface
• ISSN: 0026-1270
• DOI: 10.3414/ME0480

This paper addresses the design of a platform for the management of medical decision data in the ICU. Whenever new medical data from laboratories or monitors is available or at fixed times, the appropriate medical support services are activated and generate a medical alert or suggestion to the bedside terminal, the physician's PDA, smart phone or mailbox. Since future ICU systems will rely ever more on medical decision support, a generic and flexible subscription platform is of high importance. Our platform is designed based on the principles of service-oriented architectures, and is fundamental for service deployment since the medical support services only need to implement their algorithm and can rely on the platform for general functionalities. A secure communication and execution environment are also provided. A prototype, where medical support services can be easily plugged in, has been implemented using Web service technology and is currently being evaluated by the Department of Intensive Care of the Ghent University Hospital. To illustrate the platform operation and performance, two prototype medical support services are used, showing that the extra response time introduced by the platform is less than 150 ms. The platform allows for easy integration with hospital information systems. The platform is generic and offers user-friendly patient/service subscription, transparent data and service resource management and priority-based filtering of messages. The performance has been evaluated and it was shown that the response time of platform components is negligible compared to the execution time of the medical support services.