Validation of ICTERUS, a knowledge-based expert system for Jaundice diagnosis.

The study aimed to describe an example of the assessment and validation of knowledge-based clinical expert systems. The paper focuses on ICTERUS, an expert system for jaundice diagnosis. It describes system design, the methodology applied for upgrading and validating the program, and the most important outcomes of the validation procedure. The clinical validation of the system on a very large European database (Euricterus Project) shows that diagnostic conclusions are reliable in about 70% of eligible cases. This figure appears acceptable for a system which provides decision support only on the basis of clinical data, assuming that the final decision is achieved under user responsibility. Expected biases, limitations and inconsistencies in the practical application of the system are discussed.

[HEPASCORE: a decision-support system for the identification, clinical staging and functional assessment of hepatopathies]. / HEPASCORE: un sistema di supporto alla decisione per l'identificazione, la stadiazione clinica e la valutazione funzionale delle epatopatie.

A decision support system (HEPASCORE) has been developed to optimize the application of objective criteria for qualitative and quantitative assessment of liver function; clinical and laboratory data are automatically processed, and conclusions are explained. Early recognition of abnormal liver states is performed according to a sequential approach, based at first on clinical rules utilizing data from history and physical examination, then confirming or denying the hypothesis by means of selected laboratory tests. Once an abnormal condition is defined, clinical severity can be evaluated by use of suitable scores, either prognostic or focused on major clinical complications. In addition, selected sets of biochemical tests can be used to score one or more functional aspects. Lastly, whenever quantitative estimates of residual liver function are requested, dynamic tests can be applied to measure meaningful parameters such as functioning liver mass and functional hepatic plasma flow. HEPASCORE has been successfully applied to exclude liver abnormalities in subjects at risk, to follow up liver patients, to predict the natural outcomes of severe liver diseases, to foresee the adverse effects of drugs undergoing first-pass liver extraction and the side effects of invasive procedures. While the proposals contained in the system could be further modified for specific needs, they reflect a satisfactory methodological approach, and the program serves as a useful support to decisions regarding the identification and functional evaluation of hepatopathies. The system was developed with Microsoft Access 7.0 and runs on a personal computer under Windows 95.

An expert system for the evaluation of liver functional assessment.

The paper describes an expert system for the assessment of the liver function. Since the system must act as an intelligent assistant for a general physician, a major emphasis has been laid upon its interactive capabilities. In particular, the user can ask the system how a given conclusion has been reached (explanation facilities) and can alter the normal operation flow. In the design of the system, the different significance and availability of the clinical data and the laboratory tests have been taken into account: The investigations about a given patient start from the clinical data, and only when there is some evidence of hepatopathy are the results of some laboratory tests requested. The final result of the investigations consists of the assessment of the liver function in terms of four aspects (biosynthesis, cholestasis, cytolysis, reactivity), each of which is assigned a linguistic value describing its impairment degree. The techniques adopted in the system are based on Artificial Intelligence methodologies augmented with linguistic terms handled according to the fuzzy set theory.

Contextual and temporal clinical guidelines.

In this paper, we propose an approach for managing clinical guidelines. We sketch a modular architecture, allowing us to separate conceptually distinct aspects in the management and use of clinical guidelines. In particular, we describe the clinical guidelines knowledge representation module and we sketch the acquisition module. The main focus of the paper is the definition of an expressive formalism for representing clinical guidelines, which allows one to deal with the context dependent character of clinical guidelines and takes into account different temporal aspects.