Using contextual and lexical features to restructure and validate the classification of biomedical concepts

@article{Fan2007UsingCA,
  title={Using contextual and lexical features to restructure and validate the classification of biomedical concepts},
  author={Jung-wei Fan and Huan Xu and Carol Friedman},
  journal={BMC Bioinformatics},
  year={2007},
  volume={8},
  pages={264 - 264}
}
BackgroundBiomedical ontologies are critical for integration of data from diverse sources and for use by knowledge-based biomedical applications, especially natural language processing as well as associated mining and reasoning systems. The effectiveness of these systems is heavily dependent on the quality of the ontological terms and their classifications. To assist in developing and maintaining the ontologies objectively, we propose automatic approaches to classify and/or validate their… 
Combining Contextual and Lexical Features to Classify UMLS Concepts
TLDR
This paper extended the classifiers for 8 broad clinically relevant classes to reclassify and validate UMLS concepts by adding an "other" class to categorize concepts not belonging to any of the 8 classes by training a meta-classifier that performs dynamic combination to exploit the strength of each classifier.
Semantic reclassification of the UMLS concepts
TLDR
This work automatically reclassified the concepts of the Unified Medical Language System (UMLS) concepts based on their lexical and contextual features to benefit applications using the semantic classification of the UMLS concepts.
Semantic Classification of Nouns in UMLS Using Google Web 1 T 5-gram
TLDR
This work performed semantic classification of nouns in UMLS using Web 1T 5-gram, the large-scale words co-occurrence data provided by Google, and measured the classification accuracy in each semantic level.
The Need of a Semantic Layer between UMLS and Biomedical Information Systems
TLDR
The need of new tools, which transform whole or part of UMLS content to a semantically sharable and reusable format, is revealed to support knowledge-intensive biomedical actions.
A review of auditing techniques for the Unified Medical Language System
TLDR
Categorizing the auditing techniques according to the various aspects will enable the curators of the UMLS as well as researchers comprehensive easy access to this wealth of knowledge.
Alternative representations of Unified Medical Language System Semantic Network elements in Web Ontology Language
  • B. G. OzdemirN. Baykal
  • Computer Science
    2011 International Symposium on Innovations in Intelligent Systems and Applications
  • 2011
TLDR
Representing the UMLS SN in Web Ontology Language (OWL), which has semantically reusable and sharable format developed for use in theSemantic Web, allows applications to use the Semantic Network for supporting knowledge-intensive biomedical actions.
Determining the Semantic Similarities Among Gene Ontology Terms
  • K. Taha
  • Computer Science
    IEEE Journal of Biomedical and Health Informatics
  • 2013
TLDR
The results of measuring the semantic similarities among genes in KEGG and Pfam pathways retrieved from the DBGET and Sanger Pfam databases, respectively, have shown that the method outperforms the other three methods in recall and precision.
The Unified Medical Language System at 30 Years and How It Is Used and Published: Systematic Review and Content Analysis (Preprint)
  • X. Jing
  • Computer Science, Medicine
  • 2020
TLDR
The results, although largely related to academia, demonstrate that UMLS achieves its intended uses successfully, in addition to achieving uses broadly beyond its original intentions.
Leveraging Sublanguage Features for the Semantic Categorization of Clinical Terms
TLDR
A method for the semantic categorization of clinical terms based on their surface form is presented and it is found that features based on sublanguage properties can provide valuable cues for the classification of term variants.
...
...

References

SHOWING 1-10 OF 51 REFERENCES
Research Paper: Semantic Classification of Biomedical Concepts Using Distributional Similarity
TLDR
The results demonstrated that the distributional similarity approach can recommend high level semantic classification suitable for use in natural language processing.
An Upper-Level Ontology for the Biomedical Domain
  • A. McCray
  • Computer Science
    Comparative and functional genomics
  • 2003
TLDR
In order to provide an overarching conceptual framework for all UMLS concepts, an upper-level ontology, called the U MLS semantic network, is developed, which provides a consistent categorization of all concepts represented in the UMLs.
Auditing concept categorizations in the UMLS
Using name-internal and contextual features to classify biological terms
Sharing knowledge in medicine: semantic and ontologic facets of medical concepts
TLDR
The problem of making medical knowledge and medical data sharable over applications and reusable for several purposes is crucial and principles for the construction of ontologies have been proposed: parsimony, clarity, categories versus terms, and coherence.
Text mining and ontologies in biomedicine: Making sense of raw text
TLDR
This paper summarises different approaches in which ontologies have been used for text-mining applications in biomedicine.
Using distributional similarity to organise biomedical terminology
TLDR
It is shown that distributional similarity can be used to predict semantic type with a good degree of accuracy and is carried out using the Pro3Gres parser.
Viewpoint: The Unified Medical Language System: Toward a Collaborative Approach for Solving Terminologic Problems
TLDR
This framework provides a model for the collaborative evolution of biomedical terminology and allows a synergistic relationship between the UMLS and its source terminology systems.
...
...