Limits...
Disease Related Knowledge Summarization Based on Deep Graph Search.

Wu X, Yang Z, Li Z, Lin H, Wang J - Biomed Res Int (2015)

Bottom Line: 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 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.

View Article: PubMed Central - PubMed

Affiliation: College of Computer Science and Technology, Dalian University of Technology, Dalian 116024, China.

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.

No MeSH data available.


Related in: MedlinePlus

Top 10 predications of cooccurence scored by random walk with depth 4.
© Copyright Policy - open-access
Related In: Results  -  Collection


getmorefigures.php?uid=PMC4561941&req=5

figbox3: Top 10 predications of cooccurence scored by random walk with depth 4.

Mentions: To highlight the performance of the AnC model based on KM, the DFS process generated by the cooccurrence pairs from SemRep was carried out. Without the KM summarization, we take Parkinson Disease as the start node and the entities most related to Parkinson Disease by the cooccurrence as the end nodes of the DFS. The DFS outputs are scored by random walk. The top 10 results of depth 4 and 6 are shown in Boxes 3 and 4, respectively. We can see that some general terms, for example, Patients, Neoplasms, Malignant Neoplasms, Carcinoma, and Transitional Cell, appear frequently in the results because these words have high frequency in the cooccurrence with Parkinson Disease; but these relations cannot provide useful information in disease analysis and, therefore, are of little value. To sum up, comparing the results of KM based and cooccurrence based AnC models, the performance of former is much better than that of the latter.


Disease Related Knowledge Summarization Based on Deep Graph Search.

Wu X, Yang Z, Li Z, Lin H, Wang J - Biomed Res Int (2015)

Top 10 predications of cooccurence scored by random walk with depth 4.
© Copyright Policy - open-access
Related In: Results  -  Collection

Show All Figures
getmorefigures.php?uid=PMC4561941&req=5

figbox3: Top 10 predications of cooccurence scored by random walk with depth 4.
Mentions: To highlight the performance of the AnC model based on KM, the DFS process generated by the cooccurrence pairs from SemRep was carried out. Without the KM summarization, we take Parkinson Disease as the start node and the entities most related to Parkinson Disease by the cooccurrence as the end nodes of the DFS. The DFS outputs are scored by random walk. The top 10 results of depth 4 and 6 are shown in Boxes 3 and 4, respectively. We can see that some general terms, for example, Patients, Neoplasms, Malignant Neoplasms, Carcinoma, and Transitional Cell, appear frequently in the results because these words have high frequency in the cooccurrence with Parkinson Disease; but these relations cannot provide useful information in disease analysis and, therefore, are of little value. To sum up, comparing the results of KM based and cooccurrence based AnC models, the performance of former is much better than that of the latter.

Bottom Line: 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 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.

View Article: PubMed Central - PubMed

Affiliation: College of Computer Science and Technology, Dalian University of Technology, Dalian 116024, China.

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.

No MeSH data available.


Related in: MedlinePlus