Jean Lieber

ADAPTATION KNOWLEDGE ACQUISITION: A CASE STUDY FOR CASE-BASED DECISION SUPPORT IN ONCOLOGY

Kasimir is a case‐based decision support system in the domain of breast cancer treatment. For this system, a problem is given by the description of a patient and a solution is a set of therapeutic decisions. Given a target problem, Kasimir provides several suggestions of solutions, based on several justified adaptations of source cases. Such adaptation processes are based on adaptation knowledge. The acquisition of this kind of knowledge from experts is presented in this paper. It is shown how the decomposition of adaptation processes by introduction of intermediate problems can highlight simple and generalizable adaptation steps. Moreover, some adaptation knowledge units that are generalized from those acquired for Kasimir are presented. This knowledge can be instantiated in other case‐based decision support systems, in particular in medicine.

Application of the Revision Theory to Adaptation in Case-Based Reasoning: The Conservative Adaptation

Case-based reasoning aims at solving a problem by the adaptation of the solution of an already solved problem that has been retrieved in a case base. This paper defines an approach to adaptation called conservative adaptation; it consists in keeping as much as possible from the solution to be adapted, while being consistent with the domain knowledge. This idea can be related to the theory of revision: the revision of an old knowledge base by a new one consists in making a minimal change on the former, while being consistent with the latter. This leads to a formalization of conservative adaptation based on a revision operator in propositional logic. Then, this theory of conservative adaptation is confronted to an application of case-based decision support to oncology: a problem of this application is the description of a patient ill with breast cancer, and a solution, the therapeutic recommendation for this patient. Examples of adaptations that have actually been performed by experts and that can be captured by conservative adaptation are presented. These examples show a way of adapting contraindicated treatment recommendations and treatment recommendations that cannot be applied.

RespiDiag: A Case-Based Reasoning System for the Diagnosis of Chronic Obstructive Pulmonary Disease

In this paper a decision support system for the diagnosis of a very serious respiratory disease caused by tobacco named the chronic obstructive pulmonary disease is presented. The system is based on case-based reasoning principles and gathers the experience of experts of the pneumology department of Dorban Hospital (Annaba, Algeria). A critical issue about the case base is that some values of the features are missing in most cases. Five approaches for managing this problem of missing data are proposed. Three of them allow evaluating the similarity despite the missing information. The two other approaches fill the voids with plausible values using a statistical method and the principles of case-based reasoning itself.

Automatic case acquisition from texts for process-oriented case-based reasoning

This paper introduces a method for the automatic acquisition of a rich case representation from free text for process-oriented case-based reasoning. Case engineering is among the most complicated and costly tasks in implementing a case-based reasoning system. This is especially so for process-oriented case-based reasoning, where more expressive case representations are generally used and, in our opinion, actually required for satisfactory case adaptation. In this context, the ability to acquire cases automatically from procedural texts is a major step forward in order to reason on processes. We therefore detail a methodology that makes case acquisition from processes described as free text possible, with special attention given to assembly instruction texts. This methodology extends the techniques we used to extract actions from cooking recipes. We argue that techniques taken from natural language processing are required for this task, and that they give satisfactory results. An evaluation based on our implemented prototype extracting workflows from recipe texts is provided.

Knowledge editing and maintenance tools for a semantic portal in oncology

The research work presented in this paper is about the design of a knowledge system architecture applied to oncology and relying on the semantic Web principles. The core of this architecture is a working knowledge system, called KASIMIR, using an object-based representation formalism and classification-based reasoning. The ontology editor PROTEGE is connected with the KASIMIR system, and is adapted to the particular requirements of KASIMIR. The PROTEGE system enables the integration of several editing and visualization modules. A first knowledge editing module relies on classification-based reasoning for detecting mismatches and redundancies in the edited knowledge hierarchy. A second knowledge editing module also uses classification-based reasoning for comparing two versions of the knowledge base for maintenance purposes. This last module is particularly useful for extracting and analysing the changes occurred during an editing session. Three modules are combined to visualize hierarchies, based on three different techniques having complementary advantages. All these modules--including KASIMIR and PROTEGE--are integrated in a semantic portal architecture based on semantic Web principles. The proposed architecture takes advantage of the semantic Web technologies for integrating the different modules, and for providing a reusable environment for distributed knowledge management in oncology.

Reformulation in Case-Based Reasoning

By generalising our common experience, this paper addresses case-based reasoning that employs reformulations. Reformulation is useful when standard mapping is insufficient to retrieve a case. The paper provides a definition of reformulation and shows how reformulation is linked to retrieval and adaptation in the case-based reasoning cycle. Examples from case-based proof planning and case-based synthesis planning are used to illustrate the importance and realization of reformulation.

Case-Based Reasoning for Breast Cancer Treatment Decision Helping

This paper presents two applications for the breast cancer treatment decision helping. The first one is called CASIMIR/RBR and can be likened to a rule-based reasoning system. In some situations, the application of the rules of this system does not provide a satisfying treatment. Then, the application CASIMIR/CBR-which is not fully implemented-can be used. CASIMIR/CBR uses principles of case-based reasoning in order to suggest solutions by adapting the rules of CASIMIR/RBR. In this framework, the rules are considered as cases: they are adapted rather than used literally.

Text adaptation using formal concept analysis

This paper addresses the issue of adapting cases represented by plain text with the help of formal concept analysis and natural language processing technologies. The actual cases represent recipes in which we classify ingredients according to culinary techniques applied to them. The complex nature of linguistic anaphoras in recipe texts make usual text mining techniques inefficient so a stronger approach, using syntactic and dynamic semantic analysis to build a formal representation of a recipe, had to be used. This representation is useful for various applications but, in this paper, we show how one can extract ingredient–action relations from it in order to use formal concept analysis and select an appropriate replacement sequence of culinary actions to use in adapting the recipe text.

Belief Merging-Based Case Combination

Integrity constraint belief merging aims at producing from several knowledge bases, that may be mutually inconsistent, a synthetic knowledge base satisfying a given integrity constraint. It is applied here to case combination for case-based reasoning. This approach is shown to extend Eyke Hullermeiers credible case-based inference and to be reducible under some assumptions to linear programming.

Conservative Adaptation in Metric Spaces

Conservative adaptation consists in a minimal change on a source case to be consistent with the target case, given the domain knowledge. It has been formalised in a previous work thanks to the AGMtheory of belief revision applied to propositional logic. However, this formalism is rarely used in case-based reasoning systems. In this paper, conservative adaptation is extended to a more general representation framework, that includes also attribute-value formalisms. In this framework, a case is a class of case instances, which are elements of a metric space. Conservative adaptation is formalised in this framework and is extended to a-conservative adaptation, that relaxes the conservativeness. These approaches to adaptation in a metric space transform adaptation problems to well-formulated optimization problems. A running example in the cooking domain is used to illustrate the notions that are introduced.