Related Experiment Videos
A computational model of information retrieval with UMLS
1CERTIM, Faculté de Médecine, Marseille, France.
Proceedings. Symposium on Computer Applications in Medical Care
|January 1, 1994
Summary
A new conceptual model simplifies the Unified Medical Language System (UMLS) data structure. This model enhances user ability to query medical information databases efficiently using semantic networks and conceptual graphs.
Area of Science:
- Medical Informatics
- Knowledge Representation
- Computational Linguistics
Background:
- The Unified Medical Language System (UMLS) contains a complex collection of medical concepts, terms, and relationships.
- A high-level data representation is needed to clarify this complexity and improve data accessibility.
Purpose of the Study:
- To describe a conceptual model for representing the UMLS data structure.
- To enable users to easily build queries to information databases based on this data structure.
Main Methods:
- Utilized semantic networks and conceptual graphs to build the conceptual model.
- Developed an object-oriented computational model to implement the conceptual model.
- Reused existing C++ classes from the National Institutes of Health library and added new classes.
Main Results:
- A conceptual model representing the UMLS data structure was developed.
- The model facilitates easier query building for information databases.
- An object-oriented implementation was created, extending existing libraries.
Conclusions:
- The proposed conceptual model effectively represents complex medical terminology.
- The model enhances usability for querying medical information systems.
- The object-oriented implementation provides a robust framework for managing UMLS data.