Real-time trend analysis for an intensive care unit patient data management system

Abstract

A real-time trend analysis module is currently being developed for the Patient Data Management System (PDMS) at the pediatric intensive care unit of the Montreal Children's Hospital. The PDMS is based on a personal computer acquiring, in real-time, patient data from a bcal area network of fourteen bedside monitors and displaying their trends graphically, among other tasks. The system is based on IBM model 50 running under the OS/2 multitasking operating system and uses the 8514/A high resolution color video display.Although threshold alarms are an efficient way of attracting the user's attention, only an automatic mal-time analysis of the trends can provide a warning about slowly varying trends or short interval disturbances before the underlying condition results in a critical situation. This paper presents the design and implementation of the real-time trend analysis module of the PDMS system based on two different supervised neural networks using the general delta rule karning mechanism. The integration of such a module with a diagnosis expert system is also discussed.

A data model for a patient data management system in an intensive care unit

“…The Trend Analysis Module is a multilevel expert system. It performs appropriate d y s i s on the real-time data, scanning the trends for critical combinations and transmitting messages in case of triggering [5]. The Nursing Workload Scheduler Module focuses on improving the process of nursing care pIan generation, workload measurement and workload scheduling [3].…”