Toward discovery support systems: A replication, re‐examination, and extension of Swanson's work on literature‐based discovery of a connection between Raynaud's and fish oil

Abstract

Don R. Swanson has undertaken a program of research to use the published medical literature as a source of discoveries. We have attempted to replicate his discovery of a connection between Raynaud's disease and dietary fish oil, as well as develop computer-based searching methods that could usefully support literature-based discoveries. We have been successful in replicating Swanson's discovery and have developed a method of discovery support based on the complete text of MEDLINE records. From these, we compute statistics based both on the frequency of tokens within a literature and on the number of records containing various tokens. We discuss the use of these statistics, suggesting that token and record frequencies are good indicators of literatures profitably related to some source literature, and that relative record frequencies are useful in isolating literatures with the potential of containing a discovery.

MINING THE WEB FOR MEDICAL HYPOTHESES - A Proof-of-Concept System

“…Most state of the art MKD systems are based on Swanson's original method Gordon and Lindsay, 1996;Pratt and Yetisgen-Yildiz, 2003;Weeber et al, 2001), some with several improvements (Hu, 2005). A limitation of MKD, however, is that it requires both the source and the target terms as input.…”

Enhancing the accuracy of knowledge discovery: A supervised learning method

“…Gordon and Lindsay [5,6] applied several methods of information retrieval, such as token counts, document counts, relative frequencies, and TF*IDF, to LBD. However, the authors exerted much of their effort towards discovering linking concepts instead of target concepts.…”

Text Mining for Finding Functional Community of Related Genes Using TCM Knowledge

“…The work of Swanson gave a set up of knowledge discovery research in medical literature. Gordon and Lindsay got into the literature-based discovery research by applying Information Retrieval (IR) techniques to Swanson's early discoveries [15] [16]. Weeber et al proposed the architecture of DAD-system, a concept-based Natural Language Processing system for PubMed citations, to discover the knowledge of drug and food.…”