Serdar Uckun

Model-based diagnosis in intensive care monitoring: The YAQ approach

YAQ is an ontology for model-based reasoning in physiologic domains. YAQ is based on a hybrid algebra of qualitative and numerical values, and is designed to benefit from the rich and ever-changing nature of information available in a critical care monitoring environment. The focus of the project is on diagnosis of clinical conditions, prediction of the effects of therapy, and therapy management assistance. Two models of diagnosis are implemented in YAQ: diagnosis based on associations, and model-based diagnosis. The ontology is applied to the domain of ventilator management in infants with respiratory distress syndrome (RDS). The article describes the diagnostic capabilities of YAQ, illustrates these concepts on examples taken from actual patient records, and reports the results of an evaluation of the diagnostic performance on the RDS/assisted ventilation domain model.

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 systems 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>>

SIMON: A distributed computer architecture for intelligent patient monitoring

Abstract Intelligent real-time patient monitoring encompasses data acquisition and reduction, sensor validation, diagnosis, therapy advice, and selective display of information. This paper describes the architecture and the functionality of a prototype intelligent patient monitoring system, named SIMON, designed to meet these requirements. In SIMON, the various aspects of a monitoring task are performed by three semi-independent modules running asynchronously: the feature extraction, the patient model, and the display modules. Central to SIMON is the notion of context sensitivity which permits (a) the adaptation of the monitoring strategy in response to changes either in the patient state or in the monitoring equipment and (b) the contextual interpretation of incoming data. SIMON is currently applied to the task of monitoring newborn infants with respiratory distress syndrome (RDS) and undergoing assisted ventilation.

Model-based signal analysis and interpretation in the intensive care unit

This paper describes the architecture and functionality of a distributed intelligent signal analysis and interpretation system developed for the monitoring of neonates in the intensive care unit. In this system, named SIMON, various aspects of a monitoring task are performed by three independent modules running asynchronously: the feature extraction, the patient model, and the display modules. Central to SIMON is the notion of context sensitivity which permits the adaptation of the monitoring strategy in response to changes either in the patient state or in the monitoring equipment as well as the contextual interpretation of incoming data.

A Framework For Intelligent Multi-channel Biological Signal Interpretation

A framework for adaptive multi-channel signal interpretation tasks is presented, and applied to the problem of monitoring neonates with Respiratory Distress Syndrome. The proposed architecture permits the separation of the de main specific knowledge and the signal processing expertise typically required for signal analysis tasks. Physiological and pathophysiological knowledge is expressed in terms of processes, and parameters on which the processes can act. Information about these parameters is extracted from the monitored signals on an if-needed basis by specialized and independent signal processing modules. Both the number of parameters and the monitoring strategy for each of these parameters can be adapted.

Uncertainty Management in Engineering Risk Assessment

This paper describes a knowledge-based methodology to deal with uncertainty in risk assessment and management. Using the theory of endorsement, the method provides information concerning the uncertainty associated with risk estimates. The information on uncertainty is subsequently evaluated by the risk analyst for better risk assessment and management.

Development of a Generic Knowledge-Based Risk Assessment System

In recent years, artificial intelligence (AI) programs have appeared which contribute significantly to the field in which they are applied. Risk assessment and risk management (RA/RM) is an ideal candidate for such a program, and researchers at the Center for Intelligent Systems of Vanderbilt University are investigating the application of AI techniques to RA/RM, specifically within the context of a knowledge-based system, or expert system. Knowledge-based systems are one of the better known fruits of AI research and offer many benefits. Chief among these are the ability to make expert knowledge available to non-experts, the ability to explore “what it” scenarios safely, improved communication channels, and methods of handling uncertainty. This paper describes the development of a generic knowledge-based risk assessment system. By identifying an underlying representation common to many risk assessment fields (a network), the same architecture and construction techniques embodied in this generic system may be used in numerous individual applications. The system architecture and design principles, as well as the benefits they will provide, are described.