Integrating knowledge-based systems and databases.

In recent years, there has been an explosion of interest among the computing community in the field of artificial intelligence, particularly in the areas of natural language processing and knowledge-based systems (KBS). The medical domain has seen the development of hundreds of KBSs and there is substantial evidence to show that the application of a knowledge-based approach to decision support can go a long way towards overcoming the information overload experienced by many clinicians today. Yet many of these medical KBSs are still at the prototype stage and are mainly confined to research laboratories. There are many reasons for this apparently slow take-up of the technology, but one of the most significant is the lack of integration into the regular routine information processing of the organisation, in particular the database processing. This paper discusses the benefits of such integration and methods for achieving it in the context of general trends in information systems. Database technology provides efficient and secure management of large amounts of data in a multi-user, multi-application environment. Knowledge-based technology, on the other hand, provides mechanisms for building intelligent systems. Thus, for example, given a set of facts about a domain (symptoms, laboratory test results, etc.) together with a set of rules which apply to that domain (e.g. 'if TT4 > 150 nmol/l then suspect hyperthyroidism'), a KBS can deduce new information about that domain automatically. The effective integration of these two technologies is seen as a means of achieving the intelligent information systems of the future. There are three basic approaches to integrating KBSs and databases. The first is to start with the KBS and incorporate data management functions. Alternatively, intelligence from the KBS can be incorporated into the database. Finally, the two systems can be allowed to co-exist as independent systems which can talk to each other by means of standard interfaces. There are many advantages to this last approach since it offers much more flexibility and extensibility and is consistent with the general trend in computing towards open systems.

Supporting interoperability between medical knowledge-based systems: experience from pilot implementations.

Interoperability may be defined as the ability of knowledge-based systems to function together in a symbiotic manner. Cooperativity implies interoperability but with the added benefit that the output quality of the cooperative network exceeds the overall performance of the participating sub-systems. A number of candidate architectures to support interoperability and cooperativity between medical knowledge-based systems in laboratory medicine domains are now becoming available. Using rapid prototyping techniques, we have demonstrated the feasibility of one of these approaches by carrying out pilot implementations in two unrelated laboratory medicine domains (an internal consistency checking system for validating patients' results in the laboratory and a system for generating alarms and alerts in high dependency units based on laboratory data). The results of this study are discussed in the context of the available techniques so as to provide a basis for further development of cooperative systems in laboratory medicine.

Knowledge based lipid management system for general practitioners.

The aim of this system is to provide computer generated interpretative reports with management advice for General Practitioners (GPs). The lipid domain was chosen because of its importance in preventive medicine. Request forms to elicit extra clinical information were designed and distributed to a group of randomly selected GPs. Interpretation of laboratory and clinical data categorizes patients according to risk of coronary heart disease. The management system is rule based and provides advice on lifestyle modifications, diet and drug intervention. Previous clinical and laboratory results are taken into account in determining a management strategy. To date 435 request forms have been processed: 309 (71%) from first visits and 126 (29%) from follow-up visits. Normal lipid profiles were found in 19% of cases. There was 93% agreement between management advice given by the system and the expert. The system has now been modified and further evaluation is under way.

A methodology for evaluation of knowledge-based systems in medicine.

Evaluation is critical to the development and successful integration of knowledge-based systems into their application environment. This is of particular importance in the medical domain--not only for reasons of safety and correctness, but also to reinforce the users' confidence in these systems. In this paper we describe an iterative, four-phased development evaluation cycle covering the following areas: (i) early prototype development, (ii) validity of the system, (iii) functionality of the system, and (iv) impact of the system.

From passive to active electronic healthcare records.

OBJECTIVES: The provision of patient data to clinicians as and when it becomes available is a general objective of information systems in healthcare. It is known that the timely receipt of patient data can have a significant bearing on healthcare outcomes. One of the on-going tasks is to provide this data in the form of an Electronic Healthcare Record according to some agreed standard. The aim in this paper is to provide patient data in electronic form by pushing the information to the end users as soon it becomes available, in advance of any explicit request from the users. METHODS: This paper describes how an existing record system, the Synapses Federated Healthcare Records Server, has been extended to incorporate active functionality to facilitate pushing the information to end-user applications. The user must specify the information of interest to him, so that the system pushes only information useful to the final user. The approach proposed here relies solely on the use of callbacks through the middleware layer being used, a mechanism available in all existing middleware implementations. RESULTS: The Synapses Federated Healthcare Records Server which has resulted from this research is a more flexible and scaleable system, capable of fulfilling the needs of a wider range of healthcare organisation than when a strictly passive approach is used. CONCLUSIONS: It is shown that healthcare organisation can incorporate a healthcare record system with active functionality without any large investment or significant risk to their existing information systems.

A CORBA-based integration of distributed electronic healthcare records using the synapses approach.

The ability to exchange in a meaningful, secure, and simple fashion relevant healthcare data about patients is seen as vital in the context of efficient and cost-effective shared or team-based care. The electronic healthcare record (EHCR) lies at the heart of this information exchange, and it follows that there is an urgent need to address the ability to share EHCR's or parts of records between carers and across distributed health information systems. This paper presents the Synapses approach to sharing based on a standardized shared record, the Federated Healthcare Record, which is implemented in an open and flexible manner using the Common Object Request Broker Architecture (CORBA). The architecture of the Federated Healthcare Record is based on the architecture proposed by the Technical Committee 251 of the European Committee for Standardization.

Delivering the electronic healthcare record for the 21st century.

In spite of over four decades of research into Electronic Healthcare Record Systems, the penetration of records which incorporate more than simply basic information, into the working life of healthcare organisations is relatively small. This paper discusses some of the key impediments to progress including in particular, the lack of application of software engineering methodologies, the absence of usable standards, and the failure to acknowledge the impact of record systems on the healthcare system itself. However, Health Informatics researchers need to be preparing for the next generation of systems which will be triggered by the twin revolutions of the Internet and Genetic Medicine. This next generation of EHCR will be a longitudinal cradle-to-the-grave active record readily accessible and available via the Internet, and which will be linked to clinical protocols and guidelines to drive the delivery of healthcare to the individual citizen. Post-genomic research will unravel the link between genes, disease, treatment and the environment and this information will be used to promote health and individualise care. A number of key research issues are identified which need to be addressed in order to realise the delivery of the next generation of EHCR Systems.

A multimedia approach to raising awareness of information and communications technology amongst healthcare professionals.

This study is concerned with the application of advanced multimedia technology to the development of a programme aimed at raising awareness of information and communications technology (ICT) amongst health professionals in Ireland. The programme is delivered in the form of a symposium supplemented by a multimedia CD and associated web site. It examines how ICT can be used effectively in healthcare across all sectors - primary, secondary and tertiary - with a strong emphasis on supporting shared care. The aim is to empower users to make informed technological choices and to actively participate in the exploitation of ICT in the health sector. The programme was successfully completed and delivered to over 2300 health professionals across Ireland and follow-up activities include the active encouragement of leaders and champions within the sector. This will be supported by interactive web-based education and training material focused on specialised topics of particular interest within the broader context of continuing medical education (CME).

Federated healthcare record server--the Synapses paradigm.

The delivery of healthcare relies on the sharing of patient information between those who are providing for the care of the patient and this information is increasingly being expressed in terms of a 'record'. Further, it is desirable that these records are available in electronic form as Electronic HealthCare Records. As it is likely that patient records or parts of records will be stored in many different information systems and in the form of disparate record architectures, uniform access to patient records would be problematic. This paper presents an overview of the Synapses computing environment in which a Federated Healthcare Record Server provides uniform access to patient information stored in connected heterogeneous autonomous information systems and other Synapses servers. The Synapses record architecture is based on the architecture proposed by the Technical Committee 251 of the European Committee for Standardisation and the interfaces to the Synapses server are specified in the ISO standard Interface Definition Language. Synapses is a pan-European project involving a number of hospitals, software companies, universities and research institutes and is partly funded by the EU Health Telematics Programme. The overview is described in terms of the Open Distributed Processing Reference Model.

Specifying an open clinical laboratory information system.

This paper presents an overview of the architectural infrastructure in which existing laboratory information systems can be made to interoperate with additional modules offering a range of advanced clinical laboratory functionalities. The infrastructure is based on an open distributed computing platform, and its specification is described using the open distributed processing reference model.

Computational viewpoint of the OpenLabs architecture.

The computational viewpoint of the OpenLabs architecture specification concentrates on the definition of the functional interfaces between the logical modules that make up the clinical laboratory as defined in the enterprise and information viewpoints. A method is presented which transforms the information models into a specification written in Abstract Syntax Notation One (ASN.1). It is then shown how the specification can be translated into an Interface Definition Language (IDL) of a 'middleware' product which can then be compiled for implementation on a distributed system.

KAVAS-2: Knowledge Acquisition, Visualization and Assessment System.

The objective of KAVAS-2 is the development of a tool, named KAVIAR, with which domain experts can make their knowledge explicit. It contains components for (computer assisted) knowledge elicitation and for machine learning. A key issue in KAVAS is the assessment of the quality of the classification and domain models built. Various quality measures are available and implemented in KAVIAR to assess the quality of models, specifically those developed from data bases by machine learning techniques.

OpenLabs: the application of advanced informatics and telematics for optimization of clinical laboratory services.

OpenLabs has four major objectives: to improve the efficiency and effectiveness of clinical laboratory services by the integration of Knowledge Based Systems (KBSs) with Laboratory Information Systems (LISs) and equipment; to provide and implement standard solutions for Electronic Data Interchange (EDI) between laboratories and other medical systems; to specify a fully Open architecture for an integrated Clinical LIS and demonstrate the integration of various KBS modules on the open architecture platform; and to demonstrate the integration of OpenLabs modules with existing LISs.

Synapses/SynEx goes XML.

This paper describes the first approach to use the Extensible Markup Language (XML) as a data interchange/delivery format in the Synapses and SynEx healthcare environment. It will ease the semantic mapping between healthcare systems (server-server, server-client) and make them more interoperable.

Healthcare users and computerised resources.

This paper concerns users' views on computerised resources. The focus concerns a software tool that could be used to allow safety conscious user manipulation of the combination of these computerised resources. It is of concern to the authors that computerised resources used in healthcare should reflect users' working practices rather than working practices being changed to reflect computerised resources.

An IT awareness programme for the health sector in Ireland.

This paper describes an Awareness Programme delivered throughout Ireland which aims to increase the level of understanding of healthcare professionals as to the benefits of Information and Communications Technology (ICT) and of emerging trends in Health Informatics in Europe. The programme examines the use of ICT across the whole health sector--primary, secondary and tertiary. It has been delivered at over 30 centres to more than 1500 health professionals.

The Jupiter approach to interoperability with healthcare legacy systems.

This paper describes a novel approach to supporting interoperability between autonomous healthcare information systems. The approach, which has been implemented in the Jupiter system, is founded on the development of a formal model of legacy systems that are used as the basis for the definition of a language to support interoperability. Jupiter gives users a uniform, integrated view of heterogeneous, distributed, independent information systems. The target domain of Jupiter is healthcare, although the solution is sufficiently generic to be applicable elsewhere.

The OpenLabs approach to clinical laboratory computing.

This paper describes the architectural infrastructure to support a number of advanced functionalties for the clinical laboratory developed by OpenLabs. This infrastructure is based on an open distributed computing platform. A brief overview is given of the advanced functionalities provided by the OpenLabs modules through the novel application of knowledge-based systems, databases, and telematics; we also describe the communications architecture which allows these modules to interoperate with each other and with existing Laboratory Information Systems and instruments. The OpenLabs approach to the provision of generic interfaces to such existing systems is described, together with the OpenLabs Service Manager which supports the automated management of the laboratory in this distributed computing environment.