Abstract
The volume of published biomedical literature on disease related knowledge is expanding rapidly. Traditional information retrieval (IR) techniques, when applied to large databases such as PubMed, often return large, unmanageable lists of citations that do not fulfill the searcher's information needs. In this paper, we present an approach to automatically construct disease related knowledge summarization from biomedical literature. In this approach, firstly Kullback-Leibler Divergence combined with mutual information metric is used to extract disease salient information. Then deep search based on depth first search (DFS) is applied to find hidden (indirect) relations between biomedical entities. Finally random walk algorithm is exploited to filter out the weak relations. The experimental results show that our approach achieves a precision of 60% and a recall of 61% on salient information extraction for Carcinoma of bladder and outperforms the method of Combo.
Highlights
Biomedical literature is growing rapidly in recent decades
(2) The relations most relevant to the seed topic are selected with the summarization algorithm based on Kullback-Leibler Divergence (KLD) [13] and Mutual Information [14, 15] (KM). (3) The hidden relations are extracted using deep search based on depth first search (DFS) from the directed unweighted graph of biomedical entities
We present an approach to automatically construct disease related knowledge summarization from biomedical literature, which can find direct relations
Summary
Biomedical literature is growing rapidly in recent decades. Up till the number of papers indexed in PubMed is over 23 million. Workman and Hurdle presented the Combo algorithm to extract the genetic predicates for a particular disease, which outperformed a conventional summarization schema based on Semantic MEDLINE summarization in a genetic database curation [7]. Later, they proposed a novel dynamic summarization method in identifying decision support data [8]. We present a depth first search (DFS) based knowledge summarization approach, which can find direct relations between biomedical entities and their hidden (indirect) relations In this approach, a novel algorithm of salient information summarization, KM, is used to obtain the direct relations between disease and genes. The approach is applied to automatically construct the knowledge summarization of the disease Carcinoma of bladder from biomedical literature and the experimental results verify its effectiveness
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
