| Usability-driven pruning of large ontologies: the case of SNOMED CT. | |
| | |
MedLine Citation:
|
PMID: 22268217 Owner: NLM Status: Publisher |
Abstract/OtherAbstract:
|
ObjectivesTo study ontology modularization techniques when applied to SNOMED CT in a scenario in which no previous corpus of information exists and to examine if frequency-based filtering using MEDLINE can reduce subset size without discarding relevant concepts.Materials and MethodsSubsets were first extracted using four graph-traversal heuristics and one logic-based technique, and were subsequently filtered with frequency information from MEDLINE. Twenty manually coded discharge summaries from cardiology patients were used as signatures and test sets. The coverage, size, and precision of extracted subsets were measured.ResultsGraph-traversal heuristics provided high coverage (71-96% of terms in the test sets of discharge summaries) at the expense of subset size (17-51% of the size of SNOMED CT). Pre-computed subsets and logic-based techniques extracted small subsets (1%), but coverage was limited (24-55%). Filtering reduced the size of large subsets to 10% while still providing 80% coverage.DiscussionExtracting subsets to annotate discharge summaries is challenging when no previous corpus exists. Ontology modularization provides valuable techniques, but the resulting modules grow as signatures spread across subhierarchies, yielding a very low precision.ConclusionGraph-traversal strategies and frequency data from an authoritative source can prune large biomedical ontologies and produce useful subsets that still exhibit acceptable coverage. However, a clinical corpus closer to the specific use case is preferred when available. |
| | |
Authors:
|
Pablo López-García; Martin Boeker; Arantza Illarramendi; Stefan Schulz |
Related Documents
:
|
21822967 - Gastric subepithelial masses: evaluation of multidetector ct (multiplanar reconstructio... 21799037 - Ct imaging features of obturator prostheses in patients following palatectomy or maxill... 22186977 - A comparative evaluation of radiologic and clinical scoring systems in the early predic... 8914207 - Treatment of melanoma metastases in the brain. 10741097 - Varix of the inferior pulmonary vein: computed tomography and magnetic resonance angiog... 20634107 - Diagnostic performance of magnetic resonance imaging in the detection of appendicitis i... |
Publication Detail:
|
Type: JOURNAL ARTICLE Date: 2012-1-19 |
Journal Detail:
|
Title: Journal of the American Medical Informatics Association : JAMIA Volume: - ISSN: 1527-974X ISO Abbreviation: - Publication Date: 2012 Jan |
Date Detail:
|
Created Date: 2012-1-23 Completed Date: - Revised Date: - |
Medline Journal Info:
|
Nlm Unique ID: 9430800 Medline TA: J Am Med Inform Assoc Country: - |
Other Details:
|
Languages: ENG Pagination: - Citation Subset: - |
Affiliation:
|
Departamento de Lenguajes y Sistemas Informáticos, Universidad del País Vasco, Donostia-San Sebastián, Spain. |
Export Citation:
|
APA/MLA Format Download EndNote Download BibTex |
| MeSH Terms | |
Descriptor/Qualifier:
|
|
From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine
Previous Document: Use of electronic health record data to evaluate overuse of cervical cancer screening.
Next Document: Shifts in the architecture of the Nationwide Health Information Network.