Changes in Medical Documentation over the Last Five Decades.

In medical documentation, standardized coding schemes are used to facilitate sharing, transformation and reusability of data. First, classification systems coding schemes have been introduced. While classification systems are mainly used for statistical purposes, individual care documentation moves towards the use of nomenclatures coding schemes. The paper presents an overview of the development of coding schemes. Different coding schemes serve different purposes. Multiaxial schemes are the way of choice for comprehensively documenting complex care processes. There is a movement from mono-hierarchical classification systems to concept-based, multi-purpose and multi-hierarchical terminologies.

A reference model for clinical tumour documentation.

The definition of common system semantics is an explicit and generally accepted precondition for comparability and exchangeability of data from different systems. We have looked back on 15 years of experience with a data model that was developed in a co-operative effort by experts from various hospital cancer registries as the foundation of a new tumour documentation system (GTDS). The data model is based on the definition of a common basic data set for hospital cancer registries which is agreed by the German Association of Comprehensive Cancer Centres (ADT). This paper presents an "entity relationship" view of this model. Since data exchange among registries and with hospital or practice information systems is becoming increasingly important we describe our method to import data from such systems. We discuss the requirements that systems have to have for a most effective way of exchanging data with a hospital cancer registry. The most important feature is the possibility to associate disease phenomena and therapies with each other and with an entity that represents the tumour across encounters. The reference model we present respectively the requirements we propose for other communicating systems might also fit for other chronic diseases.

Advanced Information Retrieval Using XML Standards.

The bulk of clinical data is available in an electronic form. About 80% of the electronic data, however, is narrative text and therefore limited with respect to machine interpretation. As a result, the discussion has shifted from "electronic versus paper based data" towards "structured versus unstructured electronic data". The XML technology of today paves a way towards more structured clinical data and several XML based standards such as the Clinical Document Architecture (CDA) emerge. The implementation of XML based applications is yet a challenge. This paper will focus on XML retrieval issues and describe the difficulties and prospects of such an approach. The result of our work is a search technique called "topic matching" that exploits structured data in order to provide a search quality that is superior to established text matching methods. With this solution we are able to utilize large numbers of heterogeneously structured documents with only a minimum of effort.

Standardized Semantic Markup for Reference Terminologies, Thesauri and Coding Systems: Benefits for distributed E-Health Applications.

With the introduction of the ICD-10 as the standard for diagnosis, the development of an electronic representation of its complete content, inherent semantics and coding rules is necessary. Our concept refers to current efforts of the CEN/TC 251 to establish a European standard for hierarchical classification systems in healthcare. We have developed an electronic representation of the ICD-10 with the extensible Markup Language (XML) that facilitates the integration in current information systems or coding software taking into account different languages and versions. In this context, XML offers a complete framework of related technologies and standard tools for processing that helps to develop interoperable applications.

Implementing health care systems using XML standards.

Most healthcare data is narrative text and often not accessible and easy to find at the clinical workstation. XML related standards (XML schema, XForms, XSL, Topic Maps, etc.) provide an infrastructure that might change the situation. Yet, it is up to the application developers to combine the given standards and tools into a running system. The cost of development is often underestimated and may explain the absence of comprehensive XML applications. Our goal is the clinical application of these standards. We have, therefore, implemented the idea of "plug-and-play XML", i.e. the development of new applications by means of XML standards. This paper will communicate our experience using such an approach at the example of a clinical drug information system.

Mapping various information sources to a semantic network.

Giessen Data Dictionary Server (GDDS) provides context sensitive information services to disparate clinical applications by automatically navigating a semantic network that stores medical knowledge. Mapping multiple information sources to single clinical application becomes a challenge due to different organization of semi-structured information sources. Linking huge unstructured information sources such as medical literature is even more challenging because we need to develop a mechanism to organize unstructured information and take into account the scalability issue. In this paper, we have successfully mapped two drug information sources by developing an independent subnet for each source and linking them at proper nodes. For medical literature, we have demonstrated that the semantic network of the Unified Medical Language Systems and human assigned topics to each document can be used to organize the large amount of medical literature into the framework of the GDDS service.

Knowledge representation in digital medical documents for efficient information access and retrieval.

Information access and retrieval are essential to serve the delivery and application of evidence-based medicine. The literature provides evidence for the effectiveness of computerization of medical knowledge for increasing compliance with current standards and improving patient outcomes. But all efforts in implementing knowledge-based functions remain limited in respect of either the prolonged exposure to live clinical use, the complexity of knowledge content supported, the dependencies on a technology platform and host system, or the proof of use and content sharing across multiple and varying environments. We have to face currently an information overload, especially in medicine. As a result, efficient ways of implementation of evidence-based care become more and more important. Most of the medical knowledge contained in textbooks, guidelines, journals as well as online resources is text-based. In order to present problem-specific information at the point of care the outlined concept relies on a document-based solution with the eXtensible Markup Language (XML). The adoption of XML as a standard for the publication and interchange of documents creates a great opportunity for better information retrieval. On the basis of structured data we are able to improve the search quality for clinical information which forms a crucial pre-requisite for the implementation of evidence-based care.

Accurate searching using XML and topic maps.

Most clinical data is narrative text and often not accessible and searchable at the clinical workstation. We have therefore developed a search engine that allows indexing, searching and linking different kinds of data using web technologies. Text matching methods fail to represent implicit relationships between data, e.g. the relationship between HIV and AIDS. The ISO topic maps standard provides a data model that allows representing arbitrary relationships between resources. Such relationships form the basis for context sensitive searching and accurate search results. XML standards are used for the interchange of data relationships. Our approach has been applied to medical classification systems and clinical practice guidelines with promising results.

Discharge and referral data exchange using global standards--the SCIPHOX project in Germany.

The goal of the German project "Standardization of Communication between Information Systems in Physician Offices and Hospitals using XML" (aka SCIPHOX) in its first phase is to provide information exchange based on the Extended Markup Language XML between Hospital Information Systems (HIS) and Physician Office Systems (POS). The Clinical Document Architecture (CDA), a standard developed by the Health Level Seven organization (HL7), was chosen to serve as the "backbone" specification. The CDA is an ANSI approved document architecture for exchange of clinical information using XML. In phase I of the SCIPHOX project the proposal specifies the use of the CDA as a generalized international standard in the national context of discharge and referral letters in Germany. The specification defines how to use the CDA header and associated vocabularies by providing a translation and interpretation of the CDA header tags and provides a solution for taking local needs (insurance information etc.) into account.

Linking clinical data using XML topic maps.

Most clinical data is narrative text and often not accessible and searchable at the clinical workstation. We have therefore developed a search engine that allows indexing, searching and linking different kinds of data using web technologies. Text matching methods fail to represent implicit relationships between data, e.g. the relationship between HIV and AIDS. The international organization for standardization (ISO) topic maps standard provides a data model that allows representing arbitrary relationships between resources. Such relationships form the basis for a context sensitive search and accurate search results. The extensible markup language (XML) standards are used for the interchange of data relationships. The approach has been applied to medical classification systems and clinical practice guidelines. The search engine is compared to other XML retrieval methods and the prospect of a "semantic web" is discussed.

Transparent ICD and DRG coding using information technology: linking and associating information sources with the eXtensible Markup Language.

With the introduction of ICD-10 as the standard for diagnostics, it becomes necessary to develop an electronic representation of its complete content, inherent semantics, and coding rules. The authors' design relates to the current efforts by the CEN/TC 251 to establish a European standard for hierarchical classification systems in health care. The authors have developed an electronic representation of ICD-10 with the eXtensible Markup Language (XML) that facilitates integration into current information systems and coding software, taking different languages and versions into account. In this context, XML provides a complete processing framework of related technologies and standard tools that helps develop interoperable applications. XML provides semantic markup. It allows domain-specific definition of tags and hierarchical document structure. The idea of linking and thus combining information from different sources is a valuable feature of XML. In addition, XML topic maps are used to describe relationships between different sources, or "semantically associated" parts of these sources. The issue of achieving a standardized medical vocabulary becomes more and more important with the stepwise implementation of diagnostically related groups, for example. The aim of the authors' work is to provide a transparent and open infrastructure that can be used to support clinical coding and to develop further software applications. The authors are assuming that a comprehensive representation of the content, structure, inherent semantics, and layout of medical classification systems can be achieved through a document-oriented approach.

A data model for managing drug therapy within a patient data management system for intensive care units.

The major intent of this article was to describe the design principles of the drug-therapy documentation module of the Patient Data Management System (PDMS) ICUData, in routine use at the intensive care unit (ICU) of the Department of Anesthesiology and Intensive Care Medicine at the University Hospital of Giessen, Germany, since February 1999. The new drug management system has been in routine use since March 2000. Until 8 January 2001, 1140 patients have been documented using this approach. It could be demonstrated that it was possible to transform the formerly unstructured text-based documentation into a detailed and structured model. The mediated benefit resulted in the automatic calculation of fluid balance. Further, detailed statistical analyses of therapeutic behavior in drug administration are now possible.

Representation of relationships between data in healthcare documents.

In healthcare data are to a large extent represented in narrative textual documents. The analysis of narrative text has not been solved successfully up to now. The results of natural language processing or fully indexing systems have not been completely satisfying. It is in particular difficult to detect and describe reliably relationships between data items in narrative text. The eXtensible Markup Language XML has opened new and very promising perspectives in this environment which could improve the storage, processing and analysis of narrative textual documents in particular in healthcare.

XML-based application interface services--a method to enhance integrability of disease specific systems.

Disease specific systems usually offer excellent functionality for the management of the covered diseases. But the restriction to a certain disease often hampers their wide spread use since they are not optimised for clinical workflow. The Giessener Tumordokumentationssystem (GTDS) is a disease specific system that is not only designed for the use in tumour registries but also to support clinical care. In order to integrate it into hospital information systems, we implemented standard communication interfaces. However, interfaces are not satisfactory since they do not consider aspects of the normal workflow of a clinical user. Therefore, we developed a strategy that should ease the access to the system in the environment of existing systems. From the technical point of view, XML with its capabilities to represent even complex data in a rather simple way helped to implement this strategy. We use XML to communicate with API-like services and created a WWW environment to demonstrate the access to these services. Since HTML based access itself is a means to integrate systems, we intend to expand this environment to an appropriate region based means to improve the communication with registries. Another application using the services is the transfer of data between two registries with common patients.

XML representation of hierarchical classification systems: from conceptual models to real applications.

With the introduction of the ICD-10 as the standard for diagnosis, the development of an electronic representation of its complete content, inherent semantics and coding rules is necessary. Our concept refers to current efforts of the CEN/TC 251 to establish a European standard for hierarchical classification systems in healthcare. We have developed an electronic representation of the ICD-10 with the extensible Markup Language (XML) that facilitates the integration in current information systems or coding software taking into account different languages and versions. In this context, XML offers a complete framework of related technologies and standard tools for processing that helps to develop interoperable applications.

Indexing of Internet resources in order to improve the provision of problem-relevant medical information.

Due to the information overload and the unstructured access to (medical) information of the internet, it isn't hardly possible to find problem-relevant medical information in an appropriate time (e.g. during a consultation). The web offers a mixture of web pages, forums, newsgroups and databases. The search for problem-relevant information for a certain knowledge area encounters on two basic problems. On the one hand, you have to find in the jungle of the information, relevant resources for your individual clinical case (treatment, diagnosis, therapeutic option etc..). The second problem consists of being able to judge the quality of individual contents of inteernet pages. On the basis of the different informational needs of health care professionals and patients a catalog with inteernet resources was created to tumor diseases such as lung cancer (small cell and non-small cell carcinoma), colorectal cancer and thyroid cancer. Explicit and implicit metainformation, if available, such as the title of the document, language, date or keywords are stored in the database. The database entries are editorially revised, so that further specific metainformation is available for the information retrieval. Our pragmatic approach of searching, editing, and archiving of internet content is still necessary since most of the web documents are based on HTML, which doesn't allow for structuring (medical) information and assigning metainformation sufficiently. The use of specific metainformation is crucial in order to improve the recall and precision of internet searches. In the future, XML and related technologies (RDF) will meet these requirements.

Supporting clinical practice guidelines: lifecycle of guidelines for oncology within an XML-based guideline framework.

Clinical Practice Guidelines (CPGs) have become important instruments for supporting patient care. Many structure models for CPGs have been developed to explicitly gain structured CPG documents, some of them using XML. Often, however, problems arise in filling these structures with content and integrating CPG applications into an EPR/HIS The Universities of Giessen and Heidelberg have each presented an XML-based CPG structure, which are actually being merged into one. The obtained CPG structure will build our common "xCPG core model" embedded in an "XML framework", an authoring environment. This paper shows how this model used in the framework could support the entire 5-step CPG lifecycle, spanning CPG development, the integration of a CPG into an EPR/HIS, as well as maintenance. Furthermore, this paper points out how the method draws on the different information management services as a precondition for successful CPG implementation.

Discharge and referral data exchange using global standards--the SCIPHOX project in Germany.

The goal of the German project "Standardization of Communication between Information Systems in Physician Offices and Hospitals using XML" (aka SCIPHOX) is to provide an XML based information exchange between Hospital Information Systems (HIS) and Physician Office Systems (POS). HL7's Clinical Document Architecture (CDA) was chosen to serve as the "backbone" specification. The CDA is an ANSI approved document architecture for exchange of clinical information using XML. The SCIPHOX proposal specifies the use of the CDA in the context of discharge and referral letters in Germany, taking local needs (insurance information etc.) into account.

Plug-and-play XML: a health care perspective.

The application of XML (Extensible Markup Language) is still costly. The authors present an approach to ease the development of XML applications. They have developed a Web-based framework that combines existing XML resources into a comprehensive XML application. The XML framework is model-driven, i.e., the authors primarily design XML document models (XML schema, document type definition), and users can enter, search, and view related XML documents using a Web browser. The XML model itself is flexible and might be composed of existing model standards. The second part of the paper relates the approach of the authors to some problems frequently encountered in the clinical documentation process.