The SIMON project: model-based signal acquisition, analysis, and interpretation in intelligent patient monitoring

The authors describe SIMON (signal interpretation and monitoring), an approach which combines static domain-specific information, which relates variables and alarm events, with dynamic information provided by a model. It is currently being tested for the monitoring of neonates in the intensive care unit. The model component is responsible for estimating the state of the monitored system, predicting the evolution of the system's variables and parameters, and establishing a monitoring contest. This information is then used by the DA (data abstraction) and the data acquisition modules to plan a monitoring strategy to filter, rank, and abstract incoming data. Faults and artifact models included in the DA permit the low-level detection of noise-contaminated episodes. The adaptation of the monitoring strategy to these changes in the environment effectively shields the model from untrustworthy information and thus increases the reliability and robustness of the system. The scheduling mechanism included in the DA permits a continuous evaluation of the system load as well as an ability to process all its tasks.<<ETX>>