Contact
schliessen

Filtern

 

Bibliotheken

Logo der Bibliothek

Siegel TU Braunschweig Universitätsbibliothek Braunschweig
You do not seem to be within the network of Braunschweig University.
As student, researcher or staff member of Braunschweig University you can use the VPN service to gain access to electronic publications.
Alternatively, you can use your university username and password via Shibboleth to gain access to electronic publications with certain publishers. You can find more details in our Blog (in German).

On building a diabetes centric knowledge base via mining the web

Abstract Background Diabetes has become one of the hot topics in life science researches. To support the analytical procedures, researchers and analysts expend a mass of labor cost to collect experimental data, which is also error-prone. To reduce the cost and to ensure the data quality, there is a... Full description

Main Author: Fan Gong
Contributors: Yilei Chen | Author
Haofen Wang | Author
Hao Lu | Author
Contained in: BMC Medical Informatics and Decision Making (01.04.2019)
Journal Title: BMC Medical Informatics and Decision Making
Fulltext access: Fulltext access (direct link - free access) 10.1186/s12911-019-0771-6
Availability is being checked...
Interlibrary loan: Check possibility for interlibrary loan
Links: Additional Link (dx.doi.org)
Additional Link (doaj.org)
Additional Link (link.springer.com)
Fulltext access (doaj.org)
ISSN: 1472-6947
DOI: 10.1186/s12911-019-0771-6
Language: English
Physical Description: Online-Ressource
ID (e.g. DOI, URN): 10.1186/s12911-019-0771-6
PPN (Catalogue-ID): DOAJ040451801
more publication details ...

Associated Publications/Volumes

  • Associated records are being queried...
more (+)
Internes Format
LEADER 03136nma a2200313 c 4500
001 DOAJ040451801
003 DE-601
005 20190419075838.0
007 cr uuu---uuuuu
008 190412s2019 000 0 eng d
024 7 |a 10.1186/s12911-019-0771-6  |2 doi 
035 |a (DE-599)DOAJ3f03fc3cf0e342439e8bffe67d125777 
040 |b ger  |c GBVCP 
041 0 |a eng 
100 0 |a Fan Gong  |e verfasserin  |4 aut 
245 1 0 |a On building a diabetes centric knowledge base via mining the web  |h Elektronische Ressource 
300 |a Online-Ressource 
520 |a Abstract Background Diabetes has become one of the hot topics in life science researches. To support the analytical procedures, researchers and analysts expend a mass of labor cost to collect experimental data, which is also error-prone. To reduce the cost and to ensure the data quality, there is a growing trend of extracting clinical events in form of knowledge from electronic medical records (EMRs). To do so, we first need a high-coverage knowledge base (KB) of a specific disease to support the above extraction tasks called KB-based Extraction. Methods We propose an approach to build a diabetes-centric knowledge base (a.k.a. DKB) via mining the Web. In particular, we first extract knowledge from semi-structured contents of vertical portals, fuse individual knowledge from each site, and further map them to a unified KB. The target DKB is then extracted from the overall KB based on a distance-based Expectation-Maximization (EM) algorithm. Results During the experiments, we selected eight popular vertical portals in China as data sources to construct DKB. There are 7703 instances and 96,041 edges in the final diabetes KB covering diseases, symptoms, western medicines, traditional Chinese medicines, examinations, departments, and body structures. The accuracy of DKB is 95.91%. Besides the quality assessment of extracted knowledge from vertical portals, we also carried out detailed experiments for evaluating the knowledge fusion performance as well as the convergence of the distance-based EM algorithm with positive results. Conclusions In this paper, we introduced an approach to constructing DKB. A knowledge extraction and fusion pipeline was first used to extract semi-structured data from vertical portals and individual KBs were further fused into a unified knowledge base. After that, we develop a distance based Expectation Maximization algorithm to extract a subset from the overall knowledge base forming the target DKB. Experiments showed that the data in DKB are rich and of high-quality. 
700 0 |a Yilei Chen  |e verfasserin  |4 aut 
700 0 |a Haofen Wang  |e verfasserin  |4 aut 
700 0 |a Hao Lu  |e verfasserin  |4 aut 
773 0 8 |i In  |t BMC Medical Informatics and Decision Making  |g  (01.04.2019)  |w (DE-601)DOAJ000086282  |x 1472-6947 
856 4 0 |u http://dx.doi.org/10.1186/s12911-019-0771-6 
856 4 0 |y DOAJ  |u https://doaj.org/article/3f03fc3cf0e342439e8bffe67d125777 
856 4 0 |u http://link.springer.com/article/10.1186/s12911-019-0771-6 
856 4 0 |u https://doaj.org/toc/1472-6947 
912 |a GBV_DOAJ 
951 |a AR 
952 |j 2019  |b 01  |c 04