J Korean Soc Med Inform.  2004 Sep;10(3):295-302.

A Study of Effective Unified Medical Language System Concept Indexing in Radiology Reports

• Lee JA
• Seo HJ
• Kim KW
• Kim M
• Hong SK
• Park YR
• Kim JH

Abstract

OBJECTIVE
For the effective retrieval of clinical information, the elaborate indexing is essential. Two major types of indexing are the human indexing and the automatic or machine indexing. Human indexing shows higher quality but is time consuming, labor-intensive and inconsistent in term assignment activity.
METHODS
Using the Unified Medical Language System (UMLS) MetaMap program, we mapped the free text from the diagnosis section of radiology reports into UMLS concepts. To improve the precision of UMLS concept indexing by MetaMap, we evaluated the UMLS subset mapping and semantic type filtering methods, determining the best combination for improved precision.
RESULTS
After calculating the candidates from subset combinations, we obtained more enhanced results by semantic-type filtering.
CONCLUSION
The results may be improved for the complete automation of indexing process.

Keyword

UMLS Concept Indexing; UMLS Subset Mapping; Semantic Type Filtering

MeSH Terms

Abstracting and Indexing as Topic*
Automation
Diagnosis
Humans
Semantics
Unified Medical Language System*