"THE PILOT": a tool for connecting existing HIS to an extranet quickly, easily and smoothly.

Migrations and expansions of information systems are constantly at the front line of all the computer science problems to be overcome in medical / health informatics systems. It is shown here that one effective way to open the communication between heterogeneous systems is depending upon the ease of putting all the systems at work together using the middleware level to facilitate the interconnection between heterogeneous applications. However the most difficult application to migrate is certainly the ADT. It is shown here how the Pilot could facilitate the migration of applications namely with the migration of the ADT itself from a centralized platform to a full scale distributed system. Indeed the Pilot has been developed up to the stage of a pre-product and is on sale already. It has been experienced satisfactorily and is presented here.

HONselect: multilingual assistant search engine operated by a concept-based interface system to decentralized heterogeneous sources.

Any new user to the Internet will think that to retrieve the relevant document is an easy task especially with the wealth of sources available on this medium, but this is not the case. Even experienced users have difficulty formulating the right query for making the most of a search tool in order to efficiently obtain an accurate result. The goal of this work is to reduce the time and the energy necessary in searching and locating medical and health information. To reach this goal we have developed HONselect [1]. The aim of HONselect is not only to improve efficiency in retrieving documents but to respond to an increased need for obtaining a selection of relevant and accurate documents from a breadth of various knowledge databases including scientific bibliographical references, clinical trials, daily news, multimedia illustrations, conferences, forum, Web sites, clinical cases, and others. The authors based their approach on the knowledge representation using the National Library of Medicine's Medical Subject Headings (NLM, MeSH) vocabulary and classification [2,3]. The innovation is to propose a multilingual "one-stop searching" (one Web interface to databases currently in English, French and German) with full navigational and connectivity capabilities. The user may choose from a given selection of related terms the one that best suit his search, navigate in the term's hierarchical tree, and access directly to a selection of documents from high quality knowledge suppliers such as the MEDLINE database, the NLM's ClinicalTrials.gov server, the NewsPage's daily news, the HON's media gallery, conference listings and MedHunt's Web sites [4, 5, 6, 7, 8, 9]. HONselect, developed by HON, a non-profit organisation [10], is a free online available multilingual tool based on the MeSH thesaurus to index, select, retrieve and display accurate, up to date, high-level and quality documents.

User acceptance by individuals of health telematics from distributed EPRs associated with knowledge couplers.

The patient in a hospital bed is also a private individual that might access his or her own Electronic Patient Record (EPR) in association with additional tools that are able to show critical up-to-date knowledge about diagnoses, clinical investigations or treatments. The distributed EPRs are shown here in full production with the DOMED application of DIOGENE 2. Besides, in order to facilitate an easier understanding of the EPRs by the patient, the HON Web Site services are at his or her disposal in this respect at the same terminal.

ARCHIMED: a Network of Integrated Information Systems.

ARCHIMED is a Network of Integrated Information Systems (NIIS). This novel concept of hospital information system has a major advantage over the currently used distributed systems. The normalized representation structure of its databases enable its Navigators to reach simultaneously not only the data coming from different hospital departments, laboratories, and other hospital facilities, but also the data from different hospitals associated in the network.

The power and limits of a rule-based morpho-semantic parser.

The venue of Electronic Patient Record (EPR) implies an increasing amount of medical texts readily available for processing, as soon as convenient tools are made available. The chief application is text analysis, from which one can drive other disciplines like indexing for retrieval, knowledge representation, translation and inferencing for medical intelligent systems. Prerequisites for a convenient analyzer of medical texts are: building the lexicon, developing semantic representation of the domain, having a large corpus of texts available for statistical analysis, and finally mastering robust and powerful parsing techniques in order to satisfy the constraints of the medical domain. This article aims at presenting an easy-to-use parser ready to be adapted in different settings. It describes its power together with its practical limitations as experienced by the authors.

MEDTAG: tag-like semantics for medical document indexing.

Medical documentation is central in health care, as it constitutes the main means of communication between care providers. However, there is a gap to bridge between storing information and extracting the relevant underlying knowledge. We believe natural language processing (NLP) is the best solution to handle such a large amount of textual information. In this paper we describe the construction of a semantic tagset for medical document indexing purposes. Rather than attempting to produce a home-made tagset, we decided to use, as far as possible, standard medicine resources. This step has led us to choose UMLS hierarchical classes as a basis for our tagset. We also show that semantic tagging is not only providing bases for disambiguisation between senses, but is also useful in the query expansion process of the retrieval system. We finally focus on assessing the results of the semantic tagger.

Healthcare information system architecture (HISA) and its middleware models.

The use of middleware to develop widely distributed healthcare information systems (HIS) has become inevitable. However, the fact that many different platforms, even sometimes heterogeneous to each other, are hooked into the same network makes the integration of various middleware components more difficult than some might believe. This paper discusses the HISA standard and proposes extensions to the model that, in turn, could be compliant with other various existing distributed platforms and their middleware components.

Happy birthday DIOGENE: a hospital information system born 20 years ago.

Since its birth in 1978, DIOGENE, the hospital information system of Geneva University Hospital has been constantly evolving, with a major change in 1995, when migrating from a centralized to an open distributed architecture. For a few years, the hospital had to face health policy revolution with both economical constraints and opening of the healthcare network. The hospital information system DIOGENE plays a significant role by integrating four axes of knowledge: medico-economical context for better understanding and influencing resources consumption; the whole set of patient reports and documents (reports, encoded summaries, clinical findings, images, lab data, etc.), patient-dependent knowledge, in a vision integrating time and space; external knowledge bases such as Medline (patient-independent knowledge); integration of these patient-dependent and independent knowledge in a case-based reasoning format, providing on the physician desktop all relevant information for helping him to take the most appropriate adequate decision.

Natural language generation of surgical procedures.

A number of compositional Medical Concept Representation systems are being developed. Although these provide for a detailed conceptual representation of the underlying information, they have to be translated back to natural language for used by end-users and applications. The GALEN programme has been developing one such representation and we report here on a tool developed to generate natural language phrases from the GALEN conceptual representations. This tool can be adapted to different source modelling schemes and to different destination languages or sublanguages of a domain. It is based on a multilingual approach to natural language generation, realised through a clean separation of the domain model from the linguistic model and their link by well defined structures. Specific knowledge structures and operations have been developed for bridging between the modelling 'style' of the conceptual representation and natural language. Using the example of the scheme developed for modelling surgical operative procedures within the GALEN-IN-USE project, we show how the generator is adapted to such a scheme. The basic characteristics of the surgical procedures scheme are presented together with the basic principles of the generation tool. Using worked examples, we discuss the transformation operations which change the initial source representation into a form which can more directly be translated to a given natural language. In particular, the linguistic knowledge which has to be introduced--such as definitions of concepts and relationships is described. We explain the overall generator strategy and how particular transformation operations are triggered by language-dependent and conceptual parameters. Results are shown for generated French phrases corresponding to surgical procedures from the urology domain.

Towards specialised middleware for healthcare information systems.

Middleware is now a commonly used expression and anyone building distributed applications is referring to 'middleware services'. Nevertheless this notion lacks of sound theoretical foundation. This paper tries to clarify the relationship between the components of distributed environments, especially in healthcare and to establish some classification aiming at gaining a common understanding of the functionality and interdependency of the existing modules of distributed environments. A case study is presented and the potential benefits of using a middleware approach are discussed.

[Internet for physicians: a tool for today and tomorrow ]. / Internet pour les médecins: un outil d'aujourd'hui et de demain.

The Internet is becoming more and more part of our habits regarding documentation and communication, thus limiting the frontiers to only that of the language. As in many other fields, the Internet is also present in the medical domain. The Internet is accessible to all, providing a technology which is simple and ergonomic and furthermore less costly. A growing number of individuals are indeed offering information, and the multiplication and diversification of documentary thus resulting renders the quality often questionable and the search for information difficult. This article firstly presents the Internet services with examples in the medical domain and more particularly in paediatrics. It then identifies the problems related to the Internet and further details three tools useful to find medical information and to surf on the Internet: Medline, a bibliographical reference search tool (from the National Library of Medicine-NLM); Medhunt, a search tool of the Health on the Net Foundation specialised in the health domain; and the HONcode, a code of ethics developed to homogenize medical information on the Internet.

Authorization & security aspects in the middleware-based healthcare information system.

The integration and evolution of existing systems represents one of the most urgent priorities of health care information systems in order to allow the whole organisation to meet the increasing clinical organisational and managerial needs. The CEN ENV 12967-1 'Healthcare Information Systems Architecture'(HISA) standard defines an architectural approach based on a middleware of business-specific common services, enabling all parts of the local and geographical system to operate on the common information heritage of the organisation and on exploiting a set of common business-oriented functionality. After an overview on the key aspects of HISA, this paper discusses the positioning of the authorization and security aspects in the overall architecture. A global security framework is finally proposed.

Internet integrated in the daily medical practice within an electronic patient record.

Healthcare enters the information age and professionals are finding an ever-growing role for computers in the daily practice of medicine. However, a number of problematic issues are associated with electronic publications, especially through Internet. Whilst access to any information has been improved, access to specific information has become more and more difficult [1], due to the lack of a general meta-knowledge allowing to structure Internet resources. Physicians have to learn and adapt themselves to computers and Internet, but Internet has to meet the specific requirements of Healthcare. Important issues must therefore be addressed to allow a real and daily use of Internet in the medical practice. The paper discusses most of these issues and proposes a solution developed at the University Hospital of Geneva that integrates an Electronic Patient Record with Internet, without compromises on security or on performances and that runs on standard PCs'.

The Health On the Net Code of Conduct for medical and health Websites.

Internet has become one of the most used communication media. This and the fact that no constraining information publishing policy exists have created an urgent need to control the quality of information circulating through this media. To this purpose, the Health On the Net Foundation has initiated the Code of Conduct (HONcode) for the health/medical domain. This initiative proposes guidelines to information providers, with the aim, on the one hand, of raising the quality of data available on the Net and, on the other hand, of helping to identify Internet sites that are maintained by qualified people and contain reliable data. The HONcode mainly includes the following ethical aspects: the author's credentials, the date of the last modification with respect to clinical documents, confidentiality of data, source data reference, funding and the advertising policy. This article presents the HONcode and its evolution since it was launched in 1996.

Telematics techniques for image based diagnosis, therapy planning and monitoring.

This paper is intended to describe and illustrate some of the actual use of telematics related techniques together with modern biomedical imaging capabilities for helping in diagnosis, as well as for the planning and monitoring of therapy. To this end, most current imaging modalities are initially introduced. Then it is shown how telematics related techniques are necessary to improve the outcome of current image-based protocols. Such techniques allow data, means, or competencies--which may intrinsically be of a complementary nature or distributed at many different locations--to be integrated together and transcend the simple sum of individual expectations. Examples of actual implementations are given in the fields of radio-oncology, neurosurgery and orthopedics. To conclude, the papers and posters presented in the corresponding session of the MIE'97 symposium are summarized to provide further telematics references for the reader.

Concepts, knowledge and language in healthcare information systems: follow-up 30 months later.

The paper reviews the last IMIA-WG6 recommendations, issued along two themes: (1) how to better share common results and (2) how to conduct new research and development efforts. Some of the major discrepancies in the field are reviewed. The paper intends to offer insight into two areas, first, in the issue of knowledge representation and, second, in the science of meaning, incorporating the broad intersection of computational linguistics, semantics, conceptual approach, and denotation. The Ogden-Richards meaning triangle is used as a convenient organizing principle to maximize the scope of understanding among the different schools, particularly in areas of linguistics and semantics on the one side and denotation and conceptual approach on the other. In conclusion, there is a need for clarification and for more scientific pragmatism.

Alternative ways for knowledge collection, indexing and robust language retrieval.

Definitions are provided of the key entities in knowledge representation for Natural Language Processing (NLP). Starting from the words, which are the natural components of any sentence, both the role of expressions and the decomposition of words into their parts are emphasized. This leads to the notion of concepts, which are either primitive or composite depending on the model where they are created. The problem of finding the most adequate degree of granularity for a concept is studied. From this reflection on basic Natural Language Processing components, four categories of linguistic knowledge are recognized, that are considered to be the building blocks of a Medical Linguistic Knowledge Base (MLKB). Following on the tracks of a recent experience in building a natural language-based patient encoding browser, a robust method for conceptual indexing and query of medical texts is presented with particular attention to the scheme of knowledge representation.

Modeling concepts in medicine for medical language understanding.

Over the past two decades, the construction of models for medical concept representation and for understanding of the deep meaning of medical narrative texts have been challenging areas of medical informatics research. This review highlights how these two inter-related domains have evolved, emphasizing aspects of medical modeling as a tool for medical language understanding. A representation schema, which balances partially but accurately with complete but complex representations of domain-specific knowledge, must be developed to facilitate language understanding. Representative examples are drawn from two major independent efforts undertaken by the authors: the elaboration and the subsequent adjustment of the RECIT multilingual analyzer to include a robust medical concept model, and the recasting of a frame-based interlingua system, originally developed to map equivalent concepts between controlled clinical vocabularies, to invoke a similar concept model.