Andrea Rappelsberger

Fuzziness in healthcare-associated infection monitoring and surveillance

Automated identification, monitoring, and reporting of health care-associated infections in intensive care units by connecting intensive-care medical information, laboratory information, and Arden-Syntax-based clinical decision support systems was proven feasible and operable. Raw clinical and laboratory data of patients are transferred to the systems data warehouse. Ontologies listing all of the applied terms and a structured knowledge base with procedural and rule-based formalizations of the involved concepts and their relationships between them are part of the system. The inherent linguistic uncertainty of clinical terms is modeled by fuzzy sets. Degrees of compatibility (fuzzy degrees of membership) between data and the respective clinical terms under consideration are propagated by fuzzy logic. Uncertainty when it is a part of clinical propositions is modeled by truth values, and propagated by fuzzy logic as well. This large-scale system is known as Moni-ICU and runs as a routine clinical application at Vienna General Hospital, Austria.

Knowledge-based generation of diagnostic hypotheses and therapy recommendations for toxoplasma infections in pregnancy

Primary infection of pregnant women with the parasite Toxoplasma gondii results in infections of the unborn by transplacental transmission in about 50% of the cases. The degree of possible damage depends on the duration of parasitical impact on fetal tissues. The web-based software system ToxoNet processes the results of serological antibody tests performed during pregnancy by means of a knowledge base containing medical knowledge on the interpretation of toxoplasmosis serology findings. For this purpose, it matches the results of all serological investigations of maternal blood with the content of the knowledge base and generates interpretive reports consisting of a diagnostic hypothesis, recommendations for therapy, and proposals for further investigations. Fuzzy sets are used to formalize certain intervals between subsequent investigations to take the varying immune responses of individual patients into account. In a retrospective study, ToxoNet classified 100% of the trivial serological cases and about 87.8% of the more complex cases correctly. ToxoNet comprises a knowledge base, a system for interpretation, and a knowledge acquisition and modification program. It is available on the WWW by accessing a medical knowledge-base server via standard browsers.

Knowledge-based interpretation of toxoplasmosis serology test results including fuzzy temporal concepts

Transplacental transmission of Toxoplasma gondii from an infected pregnant woman to the unborn occurs with a probability of about 60 percent and results in fetal damage to a degree depending on the gestational age. The computer system ToxoNet processes the results of serological antibody tests performed during pregnancy by means of a knowledge base containing the medical knowledge concerning the interpretation of toxoplasmosis serology test results. The interpretation algorithm infers the stage of maternal infection to determine the degree of imminent fetal damage. For this purpose, it matches the results of all serological investigations of maternal blood with the content of the knowledge base and generates interpretive reports consisting of a diagnostic interpretation and recommendations for therapy and further testing. In order to take the varying immune responses of individual patients into account, certain intervals between two consecutive tests have to be maintained. These time intervals are modelled as fuzzy sets, since they allow the formal description of temporal uncertainty. ToxoNet comprises the knowledge base, an interpretation system, and a knowledge acquisition and modification program.

Executable medical guidelines with Arden Syntax—Applications in dermatology and obstetrics

INTRODUCTION Clinical decision support systems (CDSSs) are being developed to assist physicians in processing extensive data and new knowledge based on recent scientific advances. Structured medical knowledge in the form of clinical alerts or reminder rules, decision trees or tables, clinical protocols or practice guidelines, score algorithms, and others, constitute the core of CDSSs. Several medical knowledge representation and guideline languages have been developed for the formal computerized definition of such knowledge. One of these languages is Arden Syntax for Medical Logic Systems, an International Health Level Seven (HL7) standard whose development started in 1989. Its latest version is 2.10, which was presented in 2014. In the present report we discuss Arden Syntax as a modern medical knowledge representation and processing language, and show that this language is not only well suited to define clinical alerts, reminders, and recommendations, but can also be used to implement and process computerized medical practice guidelines. METHODS This section describes how contemporary software such as Java, server software, web-services, XML, is used to implement CDSSs based on Arden Syntax. Special emphasis is given to clinical decision support (CDS) that employs practice guidelines as its clinical knowledge base. RESULTS Two guideline-based applications using Arden Syntax for medical knowledge representation and processing were developed. The first is a software platform for implementing practice guidelines from dermatology. This application employs fuzzy set theory and logic to represent linguistic and propositional uncertainty in medical data, knowledge, and conclusions. The second application implements a reminder system based on clinically published standard operating procedures in obstetrics to prevent deviations from state-of-the-art care. A to-do list with necessary actions specifically tailored to the gestational week/labor/delivery is generated. DISCUSSION Today, with the latest versions of Arden Syntax and the application of contemporary software development methods, Arden Syntax has become a powerful and versatile medical knowledge representation and processing language, well suited to implement a large range of CDSSs, including clinical-practice-guideline-based CDSSs. Moreover, such CDS is provided and can be shared as a service by different medical institutions, redefining the sharing of medical knowledge. Arden Syntax is also highly flexible and provides developers the freedom to use up-to-date software design and programming patterns for external patient data access.

Web-Based Decision Support in Selecting Patients with Parkinson's Disease for Deep Brain Stimulation

Parkinsons disease is a progressive neurological disorder. Treatment of this disease is limited to dopamine replacement therapy, which successfully alleviates major signs of the disease. However, the treatment is associated with long-term side effects. Only a neurosurgical intervention is able to curtail the otherwise intolerable symptoms. One of the interventions is deep brain stimulation (DBS). Indications or contraindications for DBS surgery depend on (a) the course of previous treatment, (b) the patients current symptoms and signs, (c) the patients subjective quality of life, and (d) the anticipated prognosis of the disease. A web-based system, named FuzzyDBSexpert, was established to support the decision concerning the suitability of DBS surgery in a particular case. It consists of five main components: (1) the database that contains the patients medical data, (2) a user interface that implements the Unified Parkinsons Disease Rating Scale and some further forms, (3) a knowledge base that contains fuzzy IF-THEN rules, (4) a medical specialist user interface, and (5) a fuzzy inference engine. The development of the system has been completed. Initial tests have shown that it is helpful for physicians treating patients with Parkinsons disease as well as patients in making the decision as to whether DBS surgery should be performed.

Embedded Knowledge-Based Diagnostic Intelligence to Interpret Hepatitis Serology Test Results

Software-based medical knowledge modules are being increasingly integrated into health-care information systems in the hospital, the laboratory, the medical practice, and application systems for Web-based medical decision support. They have been developed to contribute to quality assurance in patient care, enhance the productivity and efficiency of medical work, and reduce costs in health care. This has been achieved by deploying medical knowledge modules to automatically interpret laboratory findings such as hepatitis A, B, and C serology test results in various health-care information systems

Medical Fuzzy Control Systems with Fuzzy Arden Syntax

Arden Syntax is a formal language for representing and processing medical knowledge that is employed by knowledge-based medical systems. In HL7 International’s Arden Syntax version 2.9 (Fuzzy Arden Syntax), the syntax was extended by formal constructs based on fuzzy set theory and fuzzy logic, including fuzzy control. These concepts are used to model linguistic and propositional uncertainty – which is inherent to medical knowledge – in a variety of clinical situations. Using these fuzzy methods, we can create medical fuzzy control systems (MFCSs), in which linguistic control rules are used and evaluated in parallel. Their results are aggregated so that gradual transitions between otherwise discrete control states are enabled. In this paper, we discuss the implementation of MFCSs in Fuzzy Arden Syntax. Through code examples from FuzzyArdenKBWean, an MFCS for weaning support in mechanically ventilated patients after cardiac surgery, we illustrate the implementation of fuzzy control.