PubMed Health⌕ Search

Biomedical subjects

H P Eich

Publications and source records attributed to H P Eich.

12 recordsLinked to original sources
PubMed2001

Towards integration of clinical decision support in commercial hospital information systems using distributed, reusable software and knowledge components.

PROBLEM: Clinicians' acceptance of clinical decision support depends on its workflow-oriented, context-sensitive accessibility and availability at the point of care, integrated into the Electronic Patient Record (EPR). Commercially available Hospital Information Systems (HIS) often focus on administrative tasks and mostly do not provide additional knowledge based functionality. Their traditionally monolithic and closed software architecture encumbers integration of and interaction with external software modules. Our aim was to develop methods and interfaces to integrate knowledge sources into two different commercial hospital information systems to provide the best decision support possible within the context of available patient data. METHODS: An existing, proven standalone scoring system for acute abdominal pain was supplemented by a communication interface. In both HIS we defined data entry forms and developed individual and reusable mechanisms for data exchange with external software modules. We designed an additional knowledge support frontend which controls data exchange between HIS and the knowledge modules. Finally, we added guidelines and algorithms to the knowledge library. RESULTS: Despite some major drawbacks which resulted mainly from the HIS' closed software architectures we showed exemplary, how external knowledge support can be integrated almost seamlessly into different commercial HIS. This paper describes the prototypical design and current implementation and discusses our experiences.

Abdominal Pain↗
PubMed2001

Comparison of three databases with a decision tree approach in the medical field of acute appendicitis.

Decision trees have been successfully used for years in many medical decision making applications. Transparent representation of acquired knowledge and fast algorithms made decision trees one of the most often used symbolic machine learning approaches. This paper concentrates on the problem of separating acute appendicitis, which is a special problem of acute abdominal pain from other diseases that cause acute abdominal pain by use of an decision tree approach. Early and accurate diagnosing of acute appendicitis is still a difficult and challenging problem in everyday clinical routine. An important factor in the error rate is poor discrimination between acute appendicitis and other diseases that cause acute abdominal pain. This error rate is still high, despite considerable improvements in history-taking and clinical examination, computer-aided decision-support and special investigation, such as ultrasound. We investigated three different large databases with cases of acute abdominal pain to complete this task as successful as possible. The results show that the size of the database does not necessary directly influence the success of the decision tree built on it. Surprisingly we got the best results from the decision trees built on the smallest and the biggest database, where the database with medium size (relative to the other two) was not so successful. Despite that we were able to produce decision tree classifiers that were capable of producing correct decisions on test data sets with accuracy up to 84%, sensitivity to acute appendicitis up to 90%, and specificity up to 80% on the same test set.

Abdomen, Acute↗
PubMed2000

Internet-based decision-support server for acute abdominal pain.

The paper describes conception and prototypical design of a decision-support server for acute abdominal pain. Existing formal methods to develop and exchange scores, guidelines and algorithms are used for integration. For scoring systems a work-up to separate terminological information from structure is described. The terminology is separately stored in a data dictionary and the structure in a knowledge base. This procedure enables a reuse of terminology for documentation and decision-support. The whole system covers a decision-support server written in C++ with underlying data dictionary and knowledge base, a documentation module written in Java and a CORBA middleware that establishes a connection via Internet.

Abdominal Pain↗
PubMed2000

Integrating knowledge based functionality in commercial hospital information systems.

Successful integration of knowledge-based functions in the electronic patient record depends on direct and context-sensitive accessibility and availability to clinicians and must suit their workflow. In this paper we describe an exemplary integration of an existing standalone scoring system for acute abdominal pain into two different commercial hospital information systems using Java/Corba technolgy.

Abdomen, Acute↗
PubMed1999

Generalisation and extension of a web-based data collection system for clinical studies using Java and CORBA.

Inadequate informatical support of multi-centre clinical trials lead to pure quality. In order to support a multi-centre clinical trial a data collection via WWW and Internet based on Java has been developed. In this study a generalization and extension of this prototype has been performed. The prototype has been applied to another clinical trial and a knowledge server based on C+t has been integrated via CORBA. The investigation and implementation of security aspects of web-based data collection is now under evaluation.

Artificial Intelligence↗
PubMed1999

European and Latin-American countries associated in a networked database of outstanding guidelines in unusual clinical cases (ELCANO).

The aim of ELCANO, an EU-funded project, is to build a virtual multilingual multimedia library of unusual clinical cases related to gastroenterology. Based on a standardisation of the format to report and the representation of clinical information on WWW, the multilingual multimedia case has been developed and till now 350 cases have been included. User satisfaction and user acceptance of ELCANO are under evaluation.

Databases as Topic↗
PubMed1998

Data collection in multi-center clinical trials via Internet. A generic system in Java.

Data collection via Internet is usually performed with an HTML/CGI combination, which has a lot of disadvantages, most important the lack of security features. We therefore have developed a system written entirely in Java, which implements a true client/server application based on TCP/IP. The documents are created using a multi-lingual data dictionary, and the used GUI components are able to perform plausibility checks, which improves quality of the data. The system is designed to be easily extensible so that it can be used in almost any kind of clinical trials. It is based on a three-tier model where client requests are handled and monitored by an application server. We will describe this system and it's implementation and compare it to the HTML/CGI approach. Of special interest are security features, which are possible through the use of Java.

Computer Systems↗
PubMed1998

A data dictionary approach to multilingual documentation and decision support for the diagnosis of acute abdominal pain. (COPERNICUS 555, an European concerted action).

This paper describes the design and development of a multilingual documentation and decision support system for the diagnosis of acute abdominal pain. The work was performed within a multi-national COPERNICUS European concerted action dealing with information technology for quality assurance in acute abdominal pain in Europe (EURO-AAP, 555). The software engineering was based on object-oriented analysis design and programming. The program cover three modules: a data dictionary, a documentation program and a knowledge based system. National versions of the software were provided and introduced into 16 centers from Central and Eastern Europe. A prospective data collection was performed in which 4020 patients were recruited. The software design has been proven to be very efficient and useful for the development of multilingual software.

Abdomen, Acute↗
PubMed1997

Integration of a knowledge-based system and a clinical documentation system via a data dictionary.

This paper describes the design and realisation of a knowledge-based system and a clinical documentation system linked via a data dictionary. The software was developed as a shell with object oriented methods and C++ for IBM-compatible PC's and WINDOWS 3.1/95. The data dictionary covers terminology and document objects with relations to external classifications. It controls the terminology in the documentation program with form-based entry of clinical documents and in the knowledge-based system with scores and rules. The software was applied to the clinical field of acute abdominal pain by implementing a data dictionary with 580 terminology objects, 501 document objects, and 2136 links; a documentation module with 8 clinical documents and a knowledge-based system with 10 scores and 7 sets of rules.

Abdominal Pain↗
PubMed1997

Collection of data in clinical studies via Internet.

This paper describes a system enabling data collection in multicenter clinical trials via WWW and Internet. The form-based data entry is based on HTML documents with JavaScript linked to a relational database (mSQL) via a cgi program (w3-msql). The design has been applied to a multi-national study in acute abdominal pain, for which eight clinical forms have been developed. The system is now in test use and experiences with this approach are presented.

Abdominal Pain↗