Development and evaluation of a biomedical search engine using a predicate-based vector space model

Abstract

Although biomedical information available in articles and patents is increasing exponentially, we continue to rely on the same information retrieval methods and use very few keywords to search millions of documents. We are developing a fundamentally different approach for finding much more precise and complete information with a single query using predicates instead of keywords for both query and document representation. Predicates are triples that are more complex datastructures than keywords and contain more structured information. To make optimal use of them, we developed a new predicate-based vector space model and query-document similarity function with adjusted tf-idf and boost function. Using a test bed of 107,367 PubMed abstracts, we evaluated the first essential function: retrieving information. Cancer researchers provided 20 realistic queries, for which the top 15 abstracts were retrieved using a predicate-based (new) and keyword-based (baseline) approach. Each abstract was evaluated, double-blind, by cancer researchers on a 0-5 point scale to calculate precision (0 versus higher) and relevance (0-5 score). Precision was significantly higher (p<.001) for the predicate-based (80%) than for the keyword-based (71%) approach. Relevance was almost doubled with the predicate-based approach-2.1 versus 1.6 without rank order adjustment (p<.001) and 1.34 versus 0.98 with rank order adjustment (p<.001) for predicate--versus keyword-based approach respectively. Predicates can support more precise searching than keywords, laying the foundation for rich and sophisticated information search.

A Survey of Information Retrieval Techniques

“…In their research, [21] explored the use of semantics in spam filtering by representing e-mails with a recently introduced Information Retrieval model: the enhanced Topicbased Vector Space Model (eTVSM). Based upon this representation, several well-known machine-learning models were applied.…”

Smart Health and Wellbeing

“…Through the application of linguistic processing methods, TM aims to derive structured, semantic information from the content of documents so that they are no longer viewed as sets of unrelated words [Ananiadou and McNaught 2006]. Several approaches exist to extract predicates from terms, either based on generic grammar structures [Kwak et al 2013] or focused on specific relationships of interest [Rindflesch and Fiszman 2003]. As a response to the maturing of the field, several initiatives have been started that aim to test and compare different approaches for standardized tasks.…”

Automated Extraction of Diagnostic Criteria From Electronic Health Records for Autism Spectrum Disorders: Development, Evaluation, and Application (Preprint)

“…The entities themselves have been predominantly single terms or relationships composed of single terms. For example, several projects focus, on annotating diseases or genes/proteins [13][14][15][16] and biomedical relationships between them [17,18] . When working with free text from EHR, a variety of entities have been the focus.…”