MedTQ—a framework for knowledge discovery for clinical practice and biomedical research

MedTQ—a framework for knowledge discovery for clinical practice and biomedical research

March 5, 2018

The rapid proliferation of biomedical data has created a set of challenges. For instance, it has made manual analysis and query processing of large-scale ontologies impractical and computationally expensive. Dr. Feichen Shen and Dr. Yugyung Lee from the School of Computing and Engineering, University of Missouri-Kansas City, MO, USA, believe that instead of applying a slice of reference ontology for a query process or decision support, an advanced approach needs to be employed to understand ontologies.

In the research paper, “MedTQ: Dynamic Topic Discovery and Query Generation for Medical Ontologies”, Feichen Shen and Yugyung Lee present a semantic framework, called the MedTQ framework. MedTQ performs dynamic topic discovery (relationships) and automatic query generation through the analysis of predicates among concepts and role names, called the Predicate Neighborhood Patterns (PNP), in biomedical ontologies. Furthermore, the researchers propose a new clustering technique, the Hierarchical Predicate-based K-Means clustering (HPKM), for dynamically identifying latent topics and automatically generating queries based on the discovered patterns.

Click here to read the more from the original source.

Brought to you by Scope e-Knowledge Center, an SPi Global Company, a trusted global partner for Digital Content Transformation Solutions, Knowledge Modeling (Taxonomies, Thesauri and Ontologies), Abstracting & Indexing (A&I), Metadata Enrichment and Entity Extraction.

Please give your feedback on this article or share a similar story for publishing by clicking here.

Comments are closed.

Start typing and press Enter to search