Second evaluation of HEPAR, an expert system for the diagnosis of disorders of the liver and biliary tract

A probabilistic and decision-theoretic approach to the management of infectious disease at the ICU

The medical community is presently in a state of transition from a situation dominated by the paper medical record to a future situation where all patient data will be available on-line by an electronic clinical information system. In data-intensive clinical environments, such as intensive care units (ICUs), clinical patient data are already fully managed by such systems in a number of hospitals. However, providing facilities for storing and retrieving patient data to clinicians is not enough; clinical information systems should also offer facilities to assist clinicians in dealing with hard clinical problems. Extending an information system's capabilities by integrating it with a decision-support system may be a solution. In this paper, we describe the development of a probabilistic and decision-theoretic system that aims to assist clinicians in diagnosing and treating patients with pneumonia in the intensive-care unit. Its underlying probabilistic-network model includes temporal knowledge to diagnose pneumonia on the basis of the likelihood of laryngotracheobronchial-tree colonisation by pathogens, and symptoms and signs actually present in the patient. Optimal antimicrobial therapy is selected by balancing the expected efficacy of treatment, which is related to the likelihood of particular pathogens causing the infection, against the spectrum of antimicrobial treatment. The models were built on the basis of expert knowledge. The patient data that were available were of limited value in the initial construction of the models because of problems of incompleteness. In particular, detailed temporal information was missing. By means of a number of different techniques, among others from the theory of linear programming, these data have been used to check the probabilistic information elicited from infectious-disease experts. The results of an evaluation of a number of slightly different models using retrospective patient data are discussed as well.

Computer-assisted diagnosis in gastroenterology

During the last 20 years, Danish gastroenterologists and biostatisticians have been involved in practical and theoretical research aimed at providing computer-assisted decision support in clinical practice. On the practical side, we summarize two clinical applications, one in the acute abdomen, the other in jaundice. The former project is part of a worldwide effort which appears able to reduce considerably the perforated appendix rate and the negative laparotomy rate. In the latter project, also entwined in international activities, three methods of early statistical discrimination of jaundice causes have been tested, and it has been shown how ultrasonographic data can be incorporated into the diagnostic assessment. On the theoretical side, a Dutch-Danish group has been looking into how one best designs a trial and analyses its data in the context of measuring the quality and impact of machine-made diagnostic advice. Having pointed out the international ramifications of these activities, we outline what may lie ahead: Gastroenterologists must be prepared to join large-scale field trials of clinical advice-giving software. In the future, however, such software will often become embedded in general hospital recordkeeping systems.

Prediction of rib fracture injury outcome by an artificial neural network

Outcome-based therapy is becoming the standard for assessing patient care efficacy. This study examines the ability of an artificial neural network to predict rib fracture injury outcome based on 20 intake variables determined within 1 hour of admission. The data base contained 580 patient records with four outcome variables: Length of hospital stay (LOS), ICU days, Lived, and Died. A 522-patient training set and a 58-patient test set were randomly selected. Nine networks were set up in a feed-forward, back-propagating design with each trained under different initial conditions. These networks predicted the test set outcome variables with an accuracy as high as 98% at the 80% testing level. Internal weight matrix examination indicated that age, ventilatory support, and high trauma scores were strongly associated with both ICU days and mortality. Being female, injury severity, and injury type were associated with increased LOS. Smoking and rib fracture number were low-level predictors of the four outcome variables.

Refinement of the HEPAR expert system: tools and techniques

Methods and tools for the static and dynamic verification and validation of software systems are commonplace in the field of software engineering. In the field of expert systems, where it is more difficult to ensure that a system meets the specifications and expectations than in traditional software engineering, such tools are generally not available. In this paper, the need for more support of the development process by methods and tools is illustrated by the approach taken in building the HEPAR system, a rule-based expert system that can be used as a supportive tool in the diagnosis of disorders of the liver and biliary tract. At a certain stage in the development of this system an incremental development methodology has been adopted, in which implementation of parts of the expert system was followed by dynamic validation. For this purpose, a collection of software tools were implemented as extensions to a rule-based expert-system shell. These tools provide valuable information about the effects of modification of the HEPAR knowledge base, and indicate places in the knowledge base for refinement. It is believed that similar software tools may prove helpful in the development of other expert systems as well.

The representation of medical reasoning models in resolution-based theorem provers

First-order predicate logic essentially is a language to express knowledge concerning objects and relationships between objects in a domain. Many medical problems can be cast naturally in such terms. In this paper the suitability of logic as a knowledge-representation formalism for building medical expert systems is investigated. In particular, we investigate the logical representation of three typical reasoning models in medicine: diagnostic, anatomical and causal reasoning. It turns out that each of these models has its own characteristic logical structure. Furthermore, the pragmatics of using theorem-proving techniques in consulting such logic-based medical expert systems is discussed. In particular, attention is paid to the use of a meta-level architecture to improve the applicability of theorem-proving techniques in building expert systems.

Converting a rule-based expert system into a belief network

The theory of belief networks offers a relatively new approach for dealing with uncertain information in knowledge-based (expert) systems. In contrast with the heuristic techniques for reasoning with uncertainty employed in many rule-based expert systems, the theory of belief networks is mathematically sound, based on techniques from probability theory. It therefore seems attractive to convert existing rule-based expert systems into belief networks. In this article we discuss the design of a belief network reformulation of the diagnostic rule-based expert system HEPAR. For the purpose of this experiment we have studied several typical pieces of medical knowledge represented in the HEPAR system. It turned out that, due to the differences in the type of knowledge represented and in the formalism used to represent uncertainty, much of the medical knowledge required for building the belief network concerned could not be extracted from HEPAR. As a consequence, significant additional knowledge acquisition was required. However, the objects and attributes defined in the HEPAR system, as well as the conditions in production rules mentioning these objects and attributes, were useful for guiding the selection of the statistical variables for building the belief network. The mapping of objects and attributes in HEPAR to statistical variables is discussed in detail.