摘要:

A fundamental understanding of the anatomy of the human body is a prerequisite for the successful application of a rheumatological expert system designed for use in an outpatient setting. MESICAR incorporates extensive anatomical knowledge that provides the basis for the reasoning methods, which try to explain which structures may be the cause of visible problems of the patient. Associative relations between diseases and manifestations are combined with expressions that define conditions on the manifestations. These conditions are evaluated following the causal relations in the anatomical net. This paper concentrates on the associative and causal reasoning methods of MESICAR and their integration.

ISSN:0883-9514    

DOI:10.1080/08839518908949929

出版商:Taylor & Francis Group    

年代:1989

数据来源: Taylor

摘要:

This paper describes a series of experiments in which expert diagnostic systems were constructed to analyze human pathologic gait. The difference between successive systems is the recognition of the need for both causal reasoning about the process of gait and experiential, associational knowledge that can control causal reasoning. The performance of the first system (DR. GAIT-1), which relies exclusively on associational knowledge, is quite limited. The second system (DR. GAIT-2), because it is based on a qualitative causal model of gait, overcame many of the difficulties faced by the first system, but its ability to diagnose cases is limited by the complexity of causal reasoning. The third system (QUAWDS), which we are currently developing, is an experiment in integrating causal reasoning with associational knowledge so that robust conclusions can be produced efficiently.

ISSN:0883-9514    

DOI:10.1080/08839518908949930

出版商:Taylor & Francis Group    

年代:1989

数据来源: Taylor

摘要:

Associational reasoning solves common problems quickly. Model-based reasoning can be used to solve unfamiliar, unusual, or difficult problems, but it does so slowly. This paper describes a method for overcoming the speed limitations of model-based reasoning by remembering a previous similar problem and making small changes to its solution. The method described here was used to develop a medical diagnosis system. The method was shown to result in solutions identical to those derived by a model-based expert system for the same domain, but with an increase of several orders of magnitude in efficiency. Furthermore, the method used by the system is domain independent and should be applicable in other domains with models of a similar form.

ISSN:0883-9514    

DOI:10.1080/08839518908949931

出版商:Taylor & Francis Group    

年代:1989

数据来源: Taylor

摘要:

This paper relates our experience in developing a mechanism for reasoning about the differential diagnosis of cases involving the symptoms of heart failure by using a causal model of the cardiovascular hemodynamics with probabilities relating cause to effect. Since the problem requires the determination of causal mechanism as well as primary cause, the model has many intermediate nodes as well as causal circularities requiring a heuristic approach to evaluating probabilities. The method we have developed builds hypotheses incrementally by adding the highest probability path to each finding to the hypothesis. With a number of enhancements and computational tactics, this method has proved effective for generating good hypotheses for typical cases in less than a minute.

ISSN:0883-9514    

DOI:10.1080/08839518908949932

出版商:Taylor & Francis Group    

年代:1989

数据来源: Taylor

摘要:

Causal probabilistic networks have proved to be a useful knowledge representation tool for domains having a natural description in terms of causal relations involving uncertainty between domain concepts. This article describes a network modeling diseases affecting the median nerve. The qualitative structure of the model and the quantitative pathophysiological

ISSN:0883-9514    

DOI:10.1080/08839518908949933

出版商:Taylor & Francis Group    

年代:1989

数据来源: Taylor