liu.seSearch for publications in DiVA
Change search
ReferencesLink to record
Permanent link

Direct link
Design, implementation and evaluation of a knowledge-based system to support ventilator therapy management
Linköping University, Department of Biomedical Engineering, Medical Informatics. Linköping University, The Institute of Technology.
1993 (English)Doctoral thesis, comprehensive summary (Other academic)
Abstract [en]

A good deal of research has been directed toward developing medical knowledge-based systems to assist the health care provider in both diagnostic and management decisions. Different studies by various groups have resulted in clinically useful knowledge-based systems with great potential for supporting decision-making, but due to a lack of methodology in the clinical integration and evaluation of these systems, only a few of them are in regular use. This thesis is devoted to the following aspects of knowledge-based system development:

  • Knowledge Representarion: Representing knowledge and mimicking the decision making behavior of domain experts is a central problem in the development of medical knowledge-based systems. The chosen representation scheme should cover all pieces of the domain knowledge. Reusability and shareability of the knowledge are other desirable features, since the development of useful knowledge bases is a very time and cost consuming process.
  • Knowledge Acquisition: There are a variety of knowledge acquisition techniques, but all techniques are not suitable for all domains. A successful outcome requires comprehensive knowledge in the knowledge-base. The quality of expert knowledge in the knowledge-base determines the quality of the system.
  • Knowledge-Base Maintenance: Verification and maintenance of the knowledge-base by the domain experts themselves is the main issue here. Since knowledge develops continuously, it is mandatory that the knowledge-base is updateable. The knowledge-base contents should be correct and free from redundancy and inconsistency.
  • lntegration: Integrating the system into the real environment, particularly with real patient data, constitutes a critical step, because prototype environments often differ from the clinical setting. A knowledge-based system can hardly be useful if it cannot be integrated with other applications in the real environment.
  • Evaluation: The evaluation of medical decision-support systems is important, and it is also difficult because there is no generally accepted methodology for carrying out this evaluation. The major aspect in the evaluation of a medical knowledge-based system is to find out whether the system is safe and legal, and to study the impact of the system on patients and the organization.

This thesis examines and discusses the aforementioned factors based on experiences from the design, development, implementation and evaluation of VentEx, a knowledge-based decisionsupport and monitoring system we have built and applied in ventilator therapy. Our experience covers the whole development process from the prototype to an integrated on-line system. A hybrid knowledge representation has been used and a domain-specific knowledge acquisition tool (KAVE) equipped with a simulator has been developed. Real patient data has been used to validate the knowledge-base and a study to measure the impact of the system is ongoing. Evaluation results indicate a high consensus between the doctors and VentEx according to a "gold " standard.

Place, publisher, year, edition, pages
Vimmerby: VTT Grafiska , 1993. , 68 p.
Linköping Studies in Science and Technology. Dissertations, ISSN 0345-7524 ; 317
National Category
Medical and Health Sciences
URN: urn:nbn:se:liu:diva-29467Local ID: 14815ISBN: 91-7871-168-1OAI: diva2:250282
Public defence
1993-11-26, Aulan, Administrationsbyggnaden, Universitetssjukhuset, Linköping, 10:00 (Swedish)

Papers, included in the Ph.D. thesis, are not registered and included in the posts from 1999 and backwards.

Available from: 2009-10-09 Created: 2009-10-09 Last updated: 2013-01-15

Open Access in DiVA

No full text

Search in DiVA

By author/editor
Shahsavar, Nosrat
By organisation
Medical InformaticsThe Institute of Technology
Medical and Health Sciences

Search outside of DiVA

GoogleGoogle Scholar
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Total: 515 hits
ReferencesLink to record
Permanent link

Direct link