PubMed Health⌕ Search
Home/Archive/PubMed

PubMed · 7707747

Structuring medical information into a language-independent database.

M B do Amaral·Y Satomura
View original source ↗Export metadata ↓

Abstract

We describe one approach for natural language processing and database representation of medical information. The method is based in the semantic analysis of the statements and in the identification of patterns. The processed information is indexed and structured into a frame format containing semantic slots into the database. We tested our method analysing sentences describing symptoms extracted from case reports presented in the volume 328 of the New England Journal of Medicine. The results are: 73.41% of the sentences were formatted; 81.05% of the analysed words were identified; and 95.33% of the medical terms were indexed. We conclude that this semantic approach is not only efficient for processing natural language texts, but it can also be used for the organization of medical information using a language-independent format. This interlingua that is set into the database can be applied to semantic data retrieval; serving as a basis to organize a problem-orientated medical record; displaying simultaneously the DB information into two or more languages; information interchanging among different human languages and computers; and automatic translation, among others.

Explore related subjects

Abstracting and IndexingAlgorithmsDatabases, BibliographicInformation Storage and RetrievalNatural Language ProcessingPattern Recognition, AutomatedSemanticsSubject HeadingsJournal Article

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

M B do Amaral, Y Satomura. Structuring medical information into a language-independent database.. https://doi.org/10.3109/14639239409025332

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related citations

PubMed2007

A comparative evaluation of full-text, concept-based, and context-sensitive search.

OBJECTIVES: Study comparatively (1) concept-based search, using documents pre-indexed by a conceptual hierarchy; (2) context-sensitive search, using structured, labeled documents; and (3) traditional full-text search. Hypotheses were: (1) more contexts lead to better retrieval accuracy; and (2) adding concept-based search to the other searches would improve upon their baseline performances. DESIGN: Use our Vaidurya architecture, for search and retrieval evaluation, of structured documents classified by a conceptual hierarchy, on a clinical guidelines test collection. MEASUREMENTS: Precision computed at different levels of recall to assess the contribution of the retrieval methods. Comparisons of precisions done with recall set at 0.5, using t-tests. RESULTS: Performance increased monotonically with the number of query context elements. Adding context-sensitive elements, mean improvement was 11.1% at recall 0.5. With three contexts, mean query precision was 42% +/- 17% (95% confidence interval [CI], 31% to 53%); with two contexts, 32% +/- 13% (95% CI, 27% to 38%); and one context, 20% +/- 9% (95% CI, 15% to 24%). Adding context-based queries to full-text queries monotonically improved precision beyond the 0.4 level of recall. Mean improvement was 4.5% at recall 0.5. Adding concept-based search to full-text search improved precision to 19.4% at recall 0.5. CONCLUSIONS: The study demonstrated usefulness of concept-based and context-sensitive queries for enhancing the precision of retrieval from a digital library of semi-structured clinical guideline documents. Concept-based searches outperformed free-text queries, especially when baseline precision was low. In general, the more ontological elements used in the query, the greater the resulting precision.

Abstracting and Indexing↗
PubMed2007

Improvements to the Red List Index.

The Red List Index uses information from the IUCN Red List to track trends in the projected overall extinction risk of sets of species. It has been widely recognised as an important component of the suite of indicators needed to measure progress towards the international target of significantly reducing the rate of biodiversity loss by 2010. However, further application of the RLI (to non-avian taxa in particular) has revealed some shortcomings in the original formula and approach: It performs inappropriately when a value of zero is reached; RLI values are affected by the frequency of assessments; and newly evaluated species may introduce bias. Here we propose a revision to the formula, and recommend how it should be applied in order to overcome these shortcomings. Two additional advantages of the revisions are that assessment errors are not propagated through time, and the overall level extinction risk can be determined as well as trends in this over time.

Abstracting and Indexing↗