R. Summers

Ventilator management: the role of knowledge-based technology

The authors discuss the problems associated with introducing an intelligent measurement and information system into a clinical high-dependency environment (HDE), typified by the intensive care unit (ICU) and postoperative recovery room. One specific situation in which intelligent instrumentation is required is during mechanical ventilation. A novel methodology that provides a structure for the incorporation of a knowledge-based component into the measurement process has been proposed. This methodology covers the entire development process, from a particular measurement system to evaluation of the final product. Specification and implementation for a prototype system designed for those patients who require ventilatory therapy as part of their overall management strategy has been developed using this methodology. This system is known as AIRS (Artificial Intelligent Respirator System).<<ETX>>

INFORM: integrated support for decisions and activities in intensive care

SummaryMany medical decision support systems that have been developed in the past have failed to enter routine clinical practice. Often this is because the developers have failed to analyse in sufficient detail the precise user requirements, because they have produced a system which takes too narrow a view of the patient, or because the decision support facilities have not been sufficiently well integrated into the routine clinical data handling activities. In this paper we discuss how the AIM-INFORM project is setting out to deal with these issues, in the context of the provision of decision support in the intensive care unit.

Acid-base chemistry of the blood — a general model

This paper describes a general model of acid-base chemistry of the blood which can be used to simulate physiological perturbation of acid-base chemistry on addition or removal of any buffer acid or base. In particular, it is shown how this model can be used to estimate the concentrations of buffer acid or base. In particular, it is shown how this model can be used to estimate the concentrations of buffer acids and bases when blood is equilibrated to a new pCO2, when hydrogen ions H+ are added to the blood, or when two pools of blood with different concentrations of buffer acids and bases are mixed. The ability of the model to represent the addition or removal of any acid or base is a significant increase in functionality above the Siggaard-Andersen nomogram which is limited to simulating the effects of equilibrating the blood to a new pCO2. When used to represent the situation where blood is equilibrated at a new pCO2 the model enables calculation of the amount CO2 removed during equilibration, a further increase in functionality above the Siggaard-Andersen nomogram. In two experimental situations, equilibrating blood to a new pCO2 and addition of H+ ions, the model predictions are shown to be consistent with existing experimental data in the form of the Siggaard-Andersen nomogram.

Workflow models of hospital discharge communications

The discharge communications between the John Radcliffe Hospital, Oxford, and its referring General Practitioners (GPs) in the community are investigated. These documents are known by a variety of names. To prevent confusion two descriptors are introduced: the immediate discharge document (IDD), and full discharge document (FDD). From a survey of different Hospital Units, four patterns of workflow are identified. A common IDD that meets the majority of the needs of the GP is suggested; this will also allow for a distributed computerized solution to improve workflow processes. Initial results do indicate an increase in efficiency and effectiveness of hospital discharge communications due to the technocentric intervention.

Evaluating intelligent measurement systems: a study in ventilator management

Two types of intelligent measurement systems are considered: commercially produced instrumentation systems with intelligence incorporated as a part of the product and instrumentation systems developed in-house in which the intelligence resides in stand-alone microcomputers linked by an appropriate machine level interface. The system evaluated is an example of the latter type, but the comments are equally relevant to the former. Evaluation is considered as a mainstream activity and illustrated by reference to an intelligent management system for patients who require ventilatory therapy. It is carried out for small functional units individually becoming a more transparent activity. Its more explicit nature has aided system designers and system users to view potential problems from the same perspective.<<ETX>>

Towards the development of an intelligent ITU workstation

A computer-based system is being developed which, when integrated with existing clinical instrumentation, results in an intelligent workstation that can assist the nurse and clinician with management of the critically ill patient. The clinical focus is fluid-electrolyte, acid-base, and respiratory management. The design of the workstation incorporates prototypic components of intelligent instrumentation that have been developed for ventilator management and blood-gas analysis.<<ETX>>

Document management: an Intranet approach

The World Wide Web (Web) offers a very simple and cost effective way of exchanging multimedia information over wide area networks (WAN). In its usual form the Web allows users to download files from a remote server and view them locally as hypertext documents. These documents can contain multimedia data, for example, text, images, and audio clips. Several database vendors provide links between their products and Web servers so that the database can be queried across a WAN using Web viewers such as Netscape/sup TM/. The application described here introduces an Intranet, this uses Web technology for document management within the internal network of the Oxford Radcliffe Hospital NHS Trust.

Towards an optimal data set for intensive care

The use of Artificial Neural Network technology offers an objective way for determining the significance of primary medical evidence. Of interest in this paper is an application in an intensive care setting, an environment which is well known for its problems in dealing with data information explosion. To tame this complexity and provide assistance to the uninitiated physician, a contextual method to demonstrate the relative importance of each clinical variable is offered. Emergent from this work is the generation of an optimal data set, that is, the minimal set of data to provide evidence that still allows determination of patient state and safe practice. Current status and results from an initial study are reported.

Development of an integrated clinical information management system

The requirements for an integrated clinical information management system are considered. A central theme is the use of advanced information technology to deal with the ever increasing data complexity found in critical care medicine. The development of systems for effective use of information derived from clinical data is illustrated with reference to ventilator management and the interpretation of blood-gas analysis test results.

A Framework For Integration Of Knowledge Sources From Diverse Clinical Domains

In recent years there has been a proliferation of publications concerned with research and development of intelligent decision aids in the clinical domain. One fruitful strand of research underway within the Centre for Measurement and Information in Medicine is the investigation of clinical decision aids applicable to the domain of critical care medicine. Four separate intelligent systems have been developed and current endeavour is to integrate these into one single system. But how? Each system has idiosyncratic properties, for example, different methods of knowledge representation have been employed. This paper describes a framework for system integration based on the idea of using a generic definition for a knowledge source. From the experience gained in merging systems from a single clinical domain it is the authors belief that the framework described will be applicable to systems from diverse clinical domains.