Medical Concept Representation Research Articles

Analysis of part-whole relation and subsumption in the medical domain

The part-whole relation has significant effect on classification in the medical domain, since diagnoses, medical procedures and findings commonly relate to anatomical objects and their parts. The paper analyses conventional medical terminology and classification systems with respect to part-whole relations, it investigates how languages of the KL-ONE-family approach the complexity of part-whole relation and subsumption, and it outlines recent developments in medical concept representation. Conventional systems used for medical documentation, indexing of clinical data or bibliographical retrieval are weak for several reasons. Partitive and generic relations are often incompletely represented and both relations are often mixed. This is due to the common combination of a concept system with a coding schema, which often constrains the hierarchical organization of concepts. Terminological languages in the tradition of KL-ONE approach the part-whole relation by different ways: Partly, they use the transitivity of subsumption for representing the transitivity of part-whole. On the other hand, there are arguments for keeping the part-whole relation outside the classifier and for modelling the effect of part-whole on subsumption in the axiomatic component of a terminological reasoning system. GRAIL and BERNWARD are approaches which focus on formal concept representation in the medical domain. GRAIL considers part-whole relations by the classifier and allows for the specification of roles to be refinable along partitive criteria. BERNWARD is based on conceptual graphs and follows a different approach. The transitivity of part-whole is represented by explicit ordering of concepts through a partonomy and by transitive chaining of part-of roles in composite concept descriptions. Both approaches allow for partitive nesting in concept representation and consider the effect of partitive attributes on subsumption by the classifier, but lack a deeper theory of the part-whole relation.

Theoretical considerations on medical concept representation.

Concepts are seen as building elements of more compositional information objects in medicine. Consequently, representation of medical concepts plays a critical role in any information system. The authors present some of the key problems which need solution, such as definition of medical domain, analysis of internal structure, different subsets of medical concepts, and the problem of the 'elementary' concepts. As a result of these considerations we can conclude that the domain of medical concepts can hardly be delimited and consists of different subsets. These subsets need different representation methods according to their different nature. Some of these subsets have a hierarchic structure. In those one can find sometimes multiple hierarchies. We suggest avoiding multiple hierarchies in concept systems by the introduction of new dimensions.

A logical foundation for representation of clinical data.

A general framework for representation of clinical data that provides a declarative semantics of terms and that allows developers to define explicitly the relationships among both terms and combinations of terms. Use of conceptual graphs as a standard representation of logic and of an existing standardized vocabulary, the Systematized Nomenclature of Medicine (SNOMED International), for lexical elements. Concepts such as time, anatomy, and uncertainty must be modeled explicitly in a way that allows relation of these foundational concepts to surface-level clinical descriptions in a uniform manner. The proposed framework was used to model a simple radiology report, which included temporal references. Formal logic provides a framework for formalizing the representation of medical concepts. Actual implementations will be required to evaluate the practicality of this approach.

A system that facilitates the orientation within procedure nomenclatures through a semantic approach.

The representation of medical concepts should provide the flexibility required to support several purposes. We have implemented a model in which medical terms are represented in a standard format based on a semantic description of the terms. We have focused on the description of procedures. Underlying this project is the assumption that information about medical procedures is crucial in the healthcare system. A prototype has been developed for urology. Because of the large number of terms in the Unified Medical Language System (UMLS) and the abundance of links between them, we have experimented in the use of the UMLS as the foundation for our concept base. We assess the usefulness of this approach and discuss its improvements.

Representation of Medical Concepts of the Thyroid Gland by Physicians in Anatomy and Pathology

An experimental study in cognitive psychology is described, concerning the categorization of medical concepts into specific classes, expressed by physicians specialized in anatomic pathology consultations of the thyroid gland. This study belongs to a medical computer science project, called ARISTOTLE, concerning Natural Language Processing of specialized medical reports in anatomic pathology of the thyroid gland. This research has been done for two reasons; first, to specify the characteristics of human expert categorization in an area of medical knowledge and, secondly, to validate the hierarchical organization of a prototype declarative knowledge base. In this experiment, physicians were asked to categorize 121 concepts into 10 proposed classes. These classes and concepts belong to expert knowledge represented in a conceptual graph that was constructed before the experiment. Results show variable semantic distances between concepts of a same class, and dynamic variations of these distances due to contextual representation.

A fuzzy logic inference model for a rule‐based system in medical diagnosis

Abstract: Intrinsically vague knowledge is typical of the decision processes involved in medical diagnosis, especially when they are based on complex and non numeric data. Linguistic descriptions of the symptoms exhibited by a given patient do not, by definition, represent a precise numeric concept and diagnostic classes cannot be modelled in terms of crisp sets. Fuzzy set theory and fuzzy logic provide an appropriate framework for the representation of imprecise medical concepts and imprecise modes of reasoning. A medical expert system with a fuzzy inference model, for the diagnosis of involutional osteoporosis is presented. Medical knowledge is represented in the form of relationships between combinations of symptoms and diagnostic classes. Two categories of disease, postmenopausal osteoporosis and senile osteoporosis are identified and three diagnostic classes are introduced for each disease category expressing the degree of severity of the disease: Definite, Possible, Excluded. For each diagnostic class the system infers a conclusion expressing the degree of satisfaction in the choice of the diagnostic class.

Expert systems for medical consultation

After reviewing some of the elements that permit a clearer understanding of what characterizes the “expert systems” approach, representation of medical concepts, symbolic manipulation rather than numeric calculation, causal reasoning, etc., this paper will try to deal with some of the most noteworthy developments in medical decision aid, teaching, research, before discussing some problems raised by the evaluation of expert systems in medicine.