Biomedical subjects

Robert H Baud

Publications and source records attributed to Robert H Baud.

3 recordsLinked to original sources

PubMed2005

Desiderata for representing anatomical knowledge.

The general problem of knowledge representation for gross anatomy supporting both computers and human is rarely globally solved. Partial solutions are flourishing, but the actual and potential users are left with a lack of satisfaction and uncomfortable feeling of incompleteness. Moreover, these solutions are not ready for a sound evolution and are at risk to disappear at any moment by default of adequate maintenance. In addition, the problem is complicated by the fact that any solutions should be relevant for Natural Language Processing applications in a multilingual environment.This paper tackles with this problem and defines the basic steps for a proper knowledge representation scheme. Taking the subdomain of gross anatomy, it shows how each step has been solved and what performances and benefits are expected by such a solution. A discussion is done on the way to interface from a common source for both computers and humans.

Anatomy↗

PubMed2004

Coping with the variability of medical terms.

OBJECTIVES: To cope with medical terms, which present a high variability of expression through a single natural language, in the sense that any term may be reformulated in hundred of different ways. METHODS: A typology of term variants is presented as a systematic approach in order to favour the implementation of an exhaustive solution. Then, an algorithm able to handle all variants is designed. RESULTS: Using MetaMap, single terms are analyzed with a success rate varying between 68 and 88 %; the algorithm presented in this paper improves this situation. CONCLUSIONS: This experience shows that a semantic driven method, based on a thesaurus, provides a satisfactory solution to the problem of variability of a single term. The presented typology is representative of most variants in a language.

Algorithms↗

PubMed2002

Multilingual approach to ICD10: on the need for a source reference database.

The distribution of ICD10 is of concern for thousand of developers in numerous countries. The absence of some basic features to facilitate the transfer and consequently to augment the quality of the delivered version is a constant characteristic. Errors, ambiguities, missing terms, unrecognised attributes are quite common, despite the efforts of some national centres doing their best to fill this gap. For other countries and languages, where such centres do not exist or do not have sufficient resources, this problem is even stronger. A reference ICD database is clearly a need today. The following features are to be made available out of an ICD database: exact count of terms, whether they are systematic, include, exclude or daggers and asterisks pairs, eventually at chapter level; exact count of notes, references and indirect exclusions; recommended structure of relational tables for ICD representation; basic structure of the classification at any level of detail. These features are somewhat language dependant and should be repeated for each one. This paper demonstrates the benefits of publishing such ICD reference information in order to improve the future ICD tools to be developed in numerous countries.

Database Management Systems↗