Record link: 
http://hdl.handle.net/20.500.12708/148009
-
Title: 
Extracting the Population, Intervention, Comparison and Sentiment from Randomized Controlled Trials.
en
Citation: 
Zlabinger, M., Andersson, L., Brassey, J., & Hanbury, A. (2017). Extracting the Population, Intervention, Comparison and Sentiment from Randomized Controlled Trials. In A. Ugon, D. Karlsson, G. O. Klein, & A. Moen (Eds.), Building Continents of Knowledge in Oceans of Data: The Future of Co-Created eHealth – Proceedings of MIE2018 (Vol. 247, pp. 146–150). IOS Press. https://doi.org/10.3233/978-1-61499-852-5-146
-
Publisher DOI: 
10.3233/978-1-61499-852-5-146
-
Publication Type: 
Book Contribution - Edited Volume Contribution
en
Language: 
English
-
Authors: 
Zlabinger, Markus 
Andersson, Linda 
Brassey, Jon 
Hanbury, Allan 
-
Organisational Unit: 
E194-04 - Forschungsbereich Data Science 
E194-01 - Forschungsbereich Software Engineering 
-
Published in: 
Building Continents of Knowledge in Oceans of Data: The Future of Co-Created eHealth – Proceedings of MIE2018 
-
ISBN: 
978-1-61499-852-5
-
Date (published): 
2017
-
Number of Pages: 
5
-
Publisher: 
IOS Press, Amsterdam, Netherlands
-
Peer reviewed: 
Yes
-
Keywords: 
machine learning; Information extraction; natural language processing; sentiment analysis
-
Abstract: 
In this paper, an identification approach for the Population (e.g. patients with headache), the Intervention (e.g. aspirin) and the Comparison (e.g. vitamin C) in Randomized Controlled Trials (RCTs) is proposed. Contrary to previous approaches, the identification is done on a word level, rather than on a sentence level. Additionally, we classify the sentiment of RCTs to determine whether an Intervention is more effective than its Comparison. Two new corpora were created to evaluate both approaches. In the experiments, an average F1 score of 0.85 for the PIC identification and 0.72 for the sentiment classification was achieved.
en
Research Areas: 
Information Systems Engineering: 80%
Computer Engineering and Software-Intensive Systems: 20%
-
Science Branch: 
Informatik
-
Appears in Collections:
Book Contribution

Show full item record

Page view(s)

196
checked on Nov 22, 2023

Download(s)

2
checked on Nov 22, 2023

Google ScholarTM

Check