Search

Medicine is evolving at a very fast pace. The overwhelming quantity of new data compels the practician to be consistently informed about the most recent scientific advances. While medical guidelines have proven to be an acceptable tool for bringing new medical knowledge into clinical practice and also support medical personnel, reading them may be rather time-consuming. Clinical decision support systems have been developed to simplify this process. However, the implementation or adaptation of such systems for individual guidelines involves substantial effort. This paper introduces a clinical decision support platform that uses Arden Syntax to implement medical guidelines using client-server architecture. It provides a means of implementing different guidelines without the need for adapting the system's source code. To implement a prototype, three Lyme borreliosis guidelines were aggregated and a knowledge base created. The prototype employs transfer objects to represent any text-based medical guideline. As part of the implementation, we show how Fuzzy Arden Syntax can improve the overall usability of a clinical decision support system.

Expectations and requirements concerning the identification and surveillance of healthcare-associated infections (HAIs) are increasing, calling for differentiated automated approaches. In an attempt to bridge the "definition swamp" of these infections and serve the needs of different users, we improved the monitoring of nosocomial infections (MONI) software to create better surveillance reports according to consented national and international definitions, as well as produce infection overviews on complex clinical matters including alerts for the clinician's ward and bedside work. MONI contains and processes surveillance definitions for intensive-care-unit-acquired infections from the European Centre for Disease Prevention and Control, Sweden, as well as the Centers for Disease Control and Prevention, USA. The latest release of MONI also includes KISS criteria of the German National Reference Center for Surveillance of Nosocomial Infections. In addition to these "classic" surveillance criteria, clinical alert criteria--which are similar but not identical to the surveillance criteria--were established together with intensivists. This is an important step to support both infection control and clinical personnel; and--last but not least--to foster co-evolution of the two groups of definitions: surveillance and alerts.

Arden Syntax is a widely recognized standard for representing clinical and scientific knowledge in an executable format. It has a history that reaches back until 1989 and is currently maintained by the Health Level 7 (HL7) organization. We created a production-ready development environment, compiler, rule engine and application server for Arden Syntax. Over the course of several years, we have applied this Arden - Syntax - based CDS system in a wide variety of clinical problem domains, such as hepatitis serology interpretation, monitoring of nosocomial infections or the prediction of metastatic events in melanoma patients. We found the Arden Syntax standard to be very suitable for the practical implementation of CDS systems. Among the advantages of Arden Syntax are its status as an actively developed HL7 standard, the readability of the syntax, and various syntactic features such as flexible list handling. A major challenge we encountered was the technical integration of our CDS systems in existing, heterogeneous health information systems. To address this issue, we are currently working on incorporating the HL7 standard GELLO, which provides a standardized interface and query language for accessing data in health information systems. We hope that these planned extensions of the Arden Syntax might eventually help in realizing the vision of a global, interoperable and shared library of clinical decision support knowledge., (Copyright © 2012 Elsevier Inc. All rights reserved.)

Nosocomial or hospital-acquired infections (NIs) are a frequent complication in hospitalized patients. The growing availability of computerized patient records in hospitals permits automated identification and extended monitoring for signs of NIs. A fuzzy- and knowledge-based system to identify and monitor NIs at intensive care units (ICUs) according to the European Surveillance System HELICS (NI definitions derived from the Centers of Disease Control and Prevention (CDC) criteria) was developed and put into operation at the Vienna General Hospital. This system, named Moni, for monitoring of nosocomial infections contains medical knowledge packages (MKPs) to identify and monitor various infections of the bloodstream, pneumonia, urinary tract infections, and central venous catheter-associated infections. The MKPs consist of medical logic modules (MLMs) in Arden syntax, a medical knowledge representation scheme, whose definition is part of the HL7 standards. These MLM packages together with the Arden software are well suited to be incorporated in medical information systems such as hospital information or intensive-care patient data management systems, or in web-based applications. In terms of method, Moni contains an extended data-to-symbol conversion with several layers of abstraction, until the top level defining NIs according to HELICS is reached. All included medical concepts such as "normal", "increased", "decreased", or similar ones are formally modeled by fuzzy sets, and fuzzy logic is used to process the interpretations of the clinically observed and measured patient data through an inference network. The currently implemented cockpit surveillance connects 96 ICU beds with Moni and offers the hospital's infection control department a hitherto unparalleled NI infection survey.

Objective: The main aim of this paper is to propose and discuss promising directions of research in the field of temporal representation and reasoning in medicine, taking into account the recent scientific literature and challenging issues of current interest as viewed from the different research perspectives of the authors of the paper., Background: Temporal representation and reasoning in medicine is a well-known field of research in the medical as well as computer science community. It encompasses several topics, such as summarizing data from temporal clinical databases, reasoning on temporal clinical data for therapeutic assessments, and modeling uncertainty in clinical knowledge and data. It is also related to several medical tasks, such as monitoring intensive care patients, providing treatments for chronic patients, as well as planning and scheduling clinical routine activities within complex healthcare organizations., Methodology: The authors jointly identified significant research areas based on their importance as for temporal representation and reasoning issues; the subjects were considered to be promising topics of future activity. Every subject was addressed in detail by one or two authors and then discussed with the entire team to achieve a consensus about future fields of research., Results: We identified and focused on four research areas, namely (i) fuzzy logic, time, and medicine, (ii) temporal reasoning and data mining, (iii) health information systems, business processes, and time, and (iv) temporal clinical databases. For every area, we first highlighted a few basic notions that would permit any reader--including those who are unfamiliar with the topic--to understand the main goals. We then discuss interesting and promising directions of research, taking into account the recent literature and underlining the yet unresolved medical/clinical issues that deserve further scientific investigation. The considered research areas are by no means disjointed, because they share common theoretical and methodological features. Moreover, subjects of imminent interest in medicine are represented in many of the fields considered., Conclusions: We propose and discuss promising subjects of future research that deserve investigation to develop software systems that will properly manage the multifaceted temporal aspects of information and knowledge encountered by physicians during their clinical work. As the subjects of research have resulted from merging the different perspectives of the authors involved in this study, we hope the paper will succeed in stimulating discussion and multidisciplinary work in the described fields of research.

As part of a plan to promote semi-automatic knowledge acquisition for the medical consultant system CADIAG-II/RHEUMA, this study sought to explore and cope with the variability of results that may be anticipated when performing knowledge acquisition with patient data from different patient settings. Patient data were drawn both from a published study for the classification of rheumatoid arthritis (RA) and from a large database of rheumatological patient charts developed for the CADIAG-II/RHEUMA system. An analysis of the relationships between RA and selected CADIAG-II/RHEUMA symptoms was done using two models. In one of them, we controlled for the differences in baseline frequencies of symptoms and diseases in the two study populations as an important factor influencing the results of the calculations. Other factors that were identified included inconsistent definitions of symptoms and diseases, and the different composition of study groups in the two study populations. By eliminating differences in baseline frequencies as the most important bias, the results obtained from the two different knowledge sources became more consistent. All remaining inconsistencies and uncertainties about the contribution and relative importance of the factors were formalized using fuzzy intervals.

Transplacental transmission of Toxoplasma gondii from an infected, pregnant woman to the unborn that occurs with a probability of about 60 percent [1] results in fetal damage to a degree depending on the gestational age. The computer system ToxoNet processes the results of serological antibody tests having been performed during pregnancy by means of a knowledge base containing medical knowledge on the interpretation of Toxoplasmosis serology tests. By applying this knowledge ToxoNet generates interpretive reports consisting of a diagnostic interpretation and recommendations for therapy and further testing. For that purpose it matches the results of all serological investigations of maternal blood with the content of the knowledge base returning complete textual interpretations for all given findings. The interpretation algorithm derives the stage of maternal infection from these that is used to infer the degree of fetal threat. To consider varying immune responses of particular patients, certain time intervals have to be kept between two subsequent tests in order to guarantee a correct interpretation of the test results. These time intervals are modelled as fuzzy sets, since they allow the formal description of the temporal uncertainties. ToxoNet comprises the knowledge base, an interpretation system, and a program for the creation and modification of the knowledge base. It is available from the World Wide Web by starting a standard browser like the Internet Explorer or the Netscape Navigator. Thus ToxoNet supports the physician in Toxoplasmosis diagnostics and in addition allows to adopt the way of making decisions to the characteristics of the particular laboratory by modifying the underlying knowledge base.

Objective: Since the treatment of patients with severe ARDS using the extracorporal lung assist (ECLA) methods remains a cost intensive and speculative procedure, a knowledge based computer system should be created and evaluated in order to support clinical decisions., Methods: The model was based on the fuzzy set theory and therefore able to give decisions between yes and no, that means that a criterion could also be fulfilled to 35% or 80% for example. The development of this computer program consists of two steps: first, the entry criteria for the ECLA therapy were established within a framework of an international evaluation of clinical data from 3 centres (Berlin, Marburg, Vienna). Here, inherent vagueness, uncertainty of the occurrence and limited availability of medical data are to be considered to establish a useful tool. Secondly, this was done by grouping and weighting of parameters by the system and the status of each patient or patient group was assigned by the percentage of fulfillment of the criterion., Results: By using a mixed sample of patients from these three centres, the fulfillment of entry criteria according either to definitions of Berlin or to definition of Marburg was different (68% versus 36%). Other differences (36% vs. 22% and 68% vs. 60%) were found between the fuzzy based score and the crisp score which represents the usually performed method., Conclusions: This now preevaluated minimal data set to describe severe ARDS patients based on the fuzzy set theory may be useful to evaluate patients for ECLA therapy or for another controlled ARDS-therapy.

HEPAXPERT is a knowledge-based system that interprets the results of routine serologic tests for infection with hepatitis A and B viruses. The following tests are included: hepatitis A virus anti-bodies (anti-HAV), IgM antibodies to the hepatitis A virus (IgM anti-HAV), hepatitis A virus (HAV in stool, hepatitis B surface antigen (HBsAg) and antibodies (qualitative anti-HBs, quantitative anti-HBs titre), antibodies to hepatitis B core antigen (anti-HBc and IgM anti-HBc), and hepatitis B envelope antigen (HBeAg) and antibodies (anti-HBe). HEPAXPERT/WWW--an implementation of HEPAXPERT-III for WWW--can be reached by URL http://www.swun.com/hepax of the World Wide Web. After selecting HEPAXPERT/WWW, serologic test results can be entered and will be transferred as an e-mail message for subsequent interpretation which is done off-line with HEPAXPERT-III. The textual interpretation is sent back via e-mail. Each qualitative test for hepatitis A and B antibodies and antigens may produce one of four possible results: positive, negative, borderline, and not tested. To cover the resulting 64 (A) and 57344 (B) combinations of findings, the knowledge base of HEPAXPERT/WWW contains 16 rules for hepatitis A and 131 rules for hepatitis B serology interpretation. This basic knowledge is structured such that all possible combinations of findings can be interpreted and there is no overlap in the premises underlying the rules. The reports that the system automatically generates include: (a) the transferred results of the tests; (b) a detailed analysis of the results, including virus exposure, immunity, stage of illness, prognosis, infectiousness, and vaccination recommendation; and (c) optional: an ID to distinguish the origin of the interpretation requests.

Myocardial perfusion scintigraphy is a noninvasive diagnostic method for the evaluation of patients with suspected or proven coronary artery disease (CAD). We utilized case-based reasoning (CBR) methods to develop the computer-based image interpretation system SCINA which automatically derives from a scintigraphic image data set an assessment concerning the presence of CAD. We compiled a case library of 100 patients who underwent both perfusion scintigraphy and coronary angiography to document or exclude the presence of CAD. The angiographic diagnosis of the retrieved nearest neighbor match of a scintigraphic input case was selected as the CBR diagnosis. We examined the effects of input data granularity, case indexing, similarity metric, and adaptation on the diagnostic accuracy of the CBR application SCINA. For the final prototype, sensitivity and specificity for detection of coronary heart disease were 98% and 70% suggesting that CBR systems may achieve a diagnostic accuracy that appears feasible for clinical use.

The medical consultation system MedFrame/CADIAG-IV is a successor of the prior CADIAG projects. It is the result of a complete redesign to account for today's demands on state-of-the-art software. Its knowledge representation and inference process are based on fuzzy set theory and fuzzy logic. Fuzzy sets are used for conversions from measured numeric values and observational data into symbolic ones. Medical relationships between findings, diseases, and therapies, the rules, are represented by fuzzy relations, that express positive or negative associations. Findings, diseases, and therapies are organised in hierarchies.

CADIAG-1 and CADIAG-2 (Computer-Assisted DIAGnosis) are medical expert systems especially designed for ill-defined areas such as internal medicine. Both systems are being tested in the setting of a medical information system. With respect to their knowledge representation, CADIAG-1 has obvious advantages in totally ill-defined areas such as syndromes in internal medicine, whereas CADIAG-2 seems more suited for domains with basic laboratory programs, e.g., hepatology or gall bladder and bile duct diseases. The formalization of relationships between medical entities led to first-order predicate calculus formulas in the case of CADIAG-1 and to a model based on fuzzy set theory in the case of CADIAG-2. In both systems two kinds of relationships between medical entities are considered: (1) necessity of occurrence and (2) sufficiency of occurrence. Statistical interpretations using the 2 X 2 table paradigm yield a way to calculate these relationships automatically from samples of patient data. Results obtained by exploiting 3530 patient records from a rheumatological hospital are presented. The described application is a machine-learning program that allows inductive learning from examples under statistical uncertainty.