[Back]

M. Zlabinger, L. Andersson, J. Brassey, A. Hanbury:
"Extracting the Population, Intervention, Comparison and Sentiment from Randomized Controlled Trials.";
Studies in health technology and informatics, 247 (2017), 146 - 150.

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.

Information extraction, natural language processing, machine learning, sentiment analysis

https://publik.tuwien.ac.at/files/publik_274030.pdf