The software challenge for the next decade: the global objects scenario.

This paper discusses the advantages of developing software as pattern-based components. The design and implementation of a pattern-based suite of software components specially constructed for the electronic patient record is presented. The methodology and the lessons learned in the development of these components are discussed. Finally, some comments about the globalization and the need for more integration among component developers in a worldwide basis is discussed.

Enhancing medical database semantics.

Medical Databases deal with dynamic, heterogeneous and fuzzy data. The modeling of such complex domain demands powerful semantic data modeling methodologies. This paper describes GSM-Explorer a Case Tool that allows for the creation of relational databases using semantic data modeling techniques. GSM Explorer fully incorporates the Generic Semantic Data Model-GSM enabling knowledge engineers to model the application domain with the abstraction mechanisms of generalization/specialization, association and aggregation. The tool generates a structure that implements persistent database-objects through the automatic generation of customized SQL ANSI scripts that sustain the semantics defined in the higher lever. This paper emphasizes the system architecture and the mapping of the semantic model into relational tables. The present status of the project and its further developments are discussed in the Conclusions.

HYCONES II: a tool to build hybrid connectionist expert systems.

This paper describes HYCONES II--a tool to enable the construction of hybrid connectionist expert systems to solve classification problems. HYCONES II offers to the knowledge engineer a hybrid knowledge base that integrates frames with three different neural network models: the combinatorial neural model--CNM, the Fuzzy ARTMAP and the Semantic ART--SMART models. The latter is a new model, introduced by this paper, based on a combination of the two previous models. The validation section compares the performance of these three neural models to solve diagnostic problems in two medical domains. This paper also presents HYCONES II knowledge representation features, built in the symbolic component of its hybrid knowledge-base, to deal and represent fuzzy medical variables. Finally, the present status and future developments of the project are presented.

HYCONES: a hybrid connectionist expert system.

This paper describes HYCONES, a tightly-coupled Hybrid Connectionist Expert System that integrates neural networks with a symbolic approach (frames). The symbolic paradigm provides rich and flexible constructs to describe the domain knowledge, while the connectionist one provides the system with learning capabilities. The paper describes the architecture of the system, focusing on the hybrid aspects of the knowledge base and on its automatic knowledge acquisition technique from a case database. The first validation of the system is presented. At the end, a comparison with related research efforts and future developments are discussed.

Incorporating knowledge to databases--a solution to complex domains.

This paper describes the design of an integrated environment to handle information on congenital heart disease patients. A three-layer model that integrates a database, a knowledge-base and a graphical user-interface is presented. The role of each layer and its connections is discussed. The advantages of using a hypertext front-end system to present and retrieve complex data are also addressed. The current status of the project and its future developments are described in the final section.