June 21, 2017
Schloss Wilhelminenberg
Savoyenstraße 2
A-1160 Vienna, Austria
has worked in medical informatics at the medical university for six years before becoming a Product and Quality Manager at Medexter Healthcare. He has worked on knowledge-based clinical decision support projects in various fields of healthcare, including intensive care medicine, infection control, thoracic surgery, anesthesiology and oncology. Currently, he is tasked with the implementation of Arden Syntax libraries for the standardized retrieval and analysis of clinical and microbiological data.
klaus-peter.adlassnig@meduniwien.ac.at
kpa@medexter.com
worked on medical fuzzy systems for almost 40 years. From 1988 to 2015, he was head of the Section on Medical Expert and Knowledge-Based Systems at the Department of Medical Computer Sciences of the University of Vienna Medical School (later: Section for Medical Expert and Knowledge-Based Systems at the Center for Medical Statistics, Informatics, and Intelligent Systems, Medical University of Vienna).
Furthermore, he is co-founder, CEO, and Scientific Head of Medexter Healthcare, a company established to broadly disseminate intelligent medical systems with clinically proven usefulness. Since its inception in 2002, Medexter succeeded in establishing technical platforms and clinical decision support systems for a number of academic, commercial, and clinical institutions.
Everyone with an interest in the computerized representation, fuzzification, and processing of medical knowledge for the use in clinical fuzzy control systems and clinical fuzzy automata is welcome.
All software and documents needed for the tutorial will be available online, and provided on paper where needed.
Arden Syntax is a formal language for representing and processing medical knowledge that can be employed by medical logic systems (MLSs). Since the release of Version 2.9 of HL7’s Arden Syntax (Fuzzy Arden Syntax), the modeling of linguistic and propositional uncertainty—which are inherent to medical knowledge—is intrinsically supported. Fuzzy Arden Syntax contains formal constructs based on fuzzy set theory and fuzzy logic, which can be used to model linguistic and propositional uncertainty. With fuzzy sets, the relationship between linguistic terms and measured raw data or observed patient data is expressed as a degree of compatibility, which formally models the unsharpness of the boundaries of clinical terms. With fuzzy logic, propositional uncertainty due to incomplete knowledge of relationships between medical concepts is modeled. Using fuzzy methods, we can create fuzzy control systems to tune and optimize the control of medical devices. Furthermore, we can create fuzzy automata, which use patient data to calculate patient physiological states, thereby allowing a gradual transition between healthy and pathological states.
Given these improvements, and the emergence of new technologies for electronic and online patient data collection and storage (e.g., ELGA, the Austrian Electronic Lifelong Health Record, which has only recently become widely available), a whole new generation of knowledge-based fuzzy medical logic systems can be built to improve patient healthcare in ways previously impossible. In this tutorial, we instruct how to create fuzzy knowledge-based control systems and fuzzy knowledge-based automata using Fuzzy Arden Syntax. We instruct the attendants on the Fuzzy Arden Syntax and—using examples of MLSs operating in clinical routine—show how fuzzy automata and fuzzy control programs can be implemented for a variety of clinical situations and needs.
Clinical examples will come from intensive care medicine (ventilator control, monitoring therapy entry criteria for ARDS patients). Examples from other medical specialties and applications include discharge management, laboratory medicine, internal medicine, and oncology.
Interoperability mechanisms with various data sources or host systems (EMR, PDMS, LIS, Activiti workflow engine, etc.) are also provided.