Improving MeSH classification of biomedical articles using citation contexts

Abstract

Medical Subject Headings (MeSH) are used to index the majority of databases generated by the National Library of Medicine. Essentially, MeSH terms are designed to make information, such as scientific articles, more retrievable and assessable to users of systems such as PubMed. This paper proposes a novel method for automating the assignment of biomedical publications with MeSH terms that takes advantage of citation references to these publications. Our findings show that analysing the citation references that point to a document can provide a useful source of terms that are not present in the document. The use of these citation contexts, as they are known, can thus help to provide a richer document feature representation, which in turn can help improve text mining and information retrieval applications, in our case MeSH term classification. In this paper, we also explore new methods of selecting and utilising citation contexts. In particular, we assess the effect of weighting the importance of citation terms (found in the citation contexts) according to two aspects: (i) the section of the paper they appear in and (ii) their distance to the citation marker. We conduct intrinsic and extrinsic evaluations of citation term quality. For the intrinsic evaluation, we rely on the UMLS Metathesaurus conceptual database to explore the semantic characteristics of the mined citation terms. We also analyse the "informativeness" of these terms using a class-entropy measure. For the extrinsic evaluation, we run a series of automatic document classification experiments over MeSH terms. Our experimental evaluation shows that citation contexts contain terms that are related to the original document, and that the integration of this knowledge results in better classification performance compared to two state-of-the-art MeSH classification systems: MeSHUP and MTI. Our experiments also demonstrate that the consideration of Section and Distance factors can lead to statistically significant improvements in citation feature quality, thus opening the way for better document feature representation in other biomedical text processing applications.

Comparison of indexing times among articles from medical, nursing, and pharmacy journals

“…For example, NLM has implemented automated methods to assist human indexers, and other efforts have been exerted to improve both the expediency and the accuracy of the indexing process. 3,11,12 Preliminary findings from this analysis indicated that journal identity was significantly associated with time to indexing and that the methodological quality of articles did not appear to influence the time to indexing. Perhaps a protocol directing that indexing be based on publication characteristics that indicate methodological quality, provided to NLM by authors, would help facilitate more rapid identification of practice-changing publications.…”

“…1,2 There are over 26,000 MeSH terms for unique concepts, including disease states, drugs, and publication characteristics such as type of article or research (e.g., randomized controlled trial [RCT], case report) and type of research funding, which are curated by the NLM's Medical Subject Headings Section staff. 3 Searches of the medical literature that use only plaintext search terms (i.e., search terms that do not invoke an algorithmic search function) may omit relevant results from articles that use terminology different from words inputted by the searcher. With MeSH terms, clinicians can search for concepts rather than plaintext search terms, obtaining more relevant results on the same topic, albeit with different terminology.…”

Spectral Clustering Wikipedia Keyword-Based Search Results

“…The authors use the text surrounding the references to extend the text representation for document clustering. The proposed approach has been also used for text classification in the medical domain (Ortuño et al, 2013), where it showed an improvement of processing results in comparison to the typical content-based representations (Aljaber et al, 2011).…”

A Health Surveillance Software Framework to deliver information on preventive healthcare strategies

“…They collected the top-ranked documents in retrieved sets to generate aspect queries. Aljaber et al used terms of citation contexts and UMLS to improve the MeSH classification [39]. Considering the same information, Ortuno et al exploited cited references to support the retrieval of related biomedical documents [40].…”