Detailed Description

Section for MEDICAL EXPERT AND KNOWLEDGE-BASED SYSTEMS of the Center for Medical Statistics, Informatics, and Intelligent Systems at the Medical University of Vienna

The Section for Medical Expert and Knowledge-Based Systems' aim is to develop computer systems for broadly applicable computer-based medical decision support in the hospital, the medical laboratory, the physician's office, and within telecommunication-based medical or health care information systems. Although the Section was officially founded in 1987, its thematic roots reach back to 1968, when a computer-assisted diagnostic system for differential diagnosis in hepatology and rheumatology based on symbolic logic and heuristic hypothesis generation was developed and successfully tested. Presently, the work covers formal methodological research in the areas of patient data and medical knowledge representation, medical knowledge acquisition, medical knowledge base consistency checking, medical inference mechanisms and evidence aggregation procedures as well as methods to evaluate the system's accuracy and acceptability. Of special interest are integrating medical expert and knowledge-based systems into the various medical and health care information systems and offering these systems on the World Wide Web (WWW).We also carry out applied interdisciplinary research with our medical and clinical partners, develop our systems as fully functionally prototypes and employ them as operational systems in the cooperating institutions for long-term study purposes. Furthermore, we teach both medical and computer science students at the Medical University of Vienna and the Technical University of Vienna about all aspects of medical expert and knowledge-based systems in medicine. To a certain extent, we offer technical and operational services to the wards, out-patient departments, and institutes of the Medical University of Vienna and its main teaching hospital, the Vienna General Hospital.

Medical expert and knowledge-based systems are designed to give expert-level, problem-specific advice in the areas of medical data interpretation, patient monitoring, disease diagnosis, treatment selection, prognosis, and patient management. They capture and make available the knowledge of experts and-by applying that knowledge to patient data-emulate and assist in the decision making behavior of medical and administrative personnel. Research in medical expert and knowledge-based systems and the development of such systems is most significant to the broad realm of quality assurance and cost containment in medicine. The growing complexity of the fund of knowledge makes the application of such systems more and more indispensable. Provided that they are used correctly, these systems can reduce much of the repetitive and specialized mental efforts made by the treating physician and enable him or her to devote his or her attention to the personal care of the patient.

Medical knowledge is processed by the computer systems on the basis of stored medical knowledge and the current medical and administrative data of a patient, the systems provide a range of alternative suggestions for the course of patient care. The purpose of these decision-oriented suggestions are as follows:

• to ensure high standards in medical quality and to possibly improve patient care
• to provide comprehensive quality management in diagnostic and medical care processes
• to ensure the efficient and cost-oriented utilization of available medical, technical, personnel, and organizational resources.

The results of these research activities have impacted a large number of computer applications in medicine:

• Clinical Patient Management
  helping monitor patient's measured and derived medical data and generate reminders, warnings, and alerts during the automatic comparison with medical protocols and guidelines
• Laboratory Medicine
  providing knowledge-based interpretive reports of laboratory test results and having alerting modules check for notifiable, noteworthy, contradictory, or otherwise remarkable laboratory data
• Anesthesia and Intensive Care
  building monitoring systems for harm prevention and early detection of diseases, checking entry criteria before therapies, and building knowledge-based adaptive control systems for medical devices
• Internal Medicine
  providing knowledge-based filtering, abstraction, and aggregation of medical data considering their context-dependency and temporal course, offering broadly applicable consultation systems for differential diagnosis and therapy to the caring physician in difficult cases, and providing electronic text tools for rare syndromes and rare pathological constellations with knowledge-based searching routines
• Image Generating and Processing Medicine
  introducing systems for knowledge-based navigation and monitoring of diagnostic and surgical procedures including routines to avoid undesired events or anatomical regions, displaying differential diagnostic support during image interpretation, and offering clinical data of patients with preceding knowledge-based filtering to assist the image-diagnosing physician in his or her decision.

The Section for Medical Expert and Knowledge-Based Systems cooperates with institutions of the public sector and commercial partners to transfer its developed prototypes—usually after having been tested practically and studied extensively at the Vienna General Hospital—to other medical institutions.

In building medical expert and knowledge-based systems, special emphasis is put on the utilization of fuzzy set theory and fuzzy logic as methodology underlying the chosen patient data and medical knowledge representation and inference procedures. These methodologies have a number of characteristics that make them highly suitable for modeling uncertain information, which medical concept forming, patient state interpretation, and diagnostic as well as therapeutic decision making is usually based upon. First of all, medical entities such as symptoms, signs, test results, diseases and diagnoses, therapy proposals, and prognostic information items can be defined as fuzzy sets. The inherent vagueness of these entities will thus be conserved. Secondly, fuzzy logic offers reasoning methods capable of drawing strict as well as approximate conclusions. Medicine demands such a broad range of possibilities because the body of medical theory includes definitional, causal, statistical, and heuristic knowledge. Practical medicine even has to accept incomplete medical theories where only vague and uncertain empirical information guides the medical decisions and the diagnostic and therapeutic procedures they are based upon. Finally, fuzzy automata can be used as high-level patient monitoring devices employing real time access to the various medical information systems, such as Hospital Information Systems (HIS), Laboratory Information Systems (LIS), Patient Data Management Systems (PDMS), and others.