Description

While systematic reviews (SRs) are positioned as an essential element of modern evidence-based medical practice, the creation of these reviews is resource intensive. To mitigate this problem there has been some attempts to leverage supervised machine learning to automate the article triage procedure. This approach has been proved to be helpful for updating existing SRs. However, this technique holds very little promise for creating new SRs because training data is rarely available when it comes to SR creation. In this research we propose an active machine learning approach to overcome this labeling bottleneck and develop a classifier for supporting the creation of systematic reviews. The results indicate that active learning based sample selection could significantly reduce the human effort and is viable technique for automating medical systematic review creation with very few training dataset.

Download

Share

COinS
 

Active Learning for the Automation of Medical Systematic Review Creation

While systematic reviews (SRs) are positioned as an essential element of modern evidence-based medical practice, the creation of these reviews is resource intensive. To mitigate this problem there has been some attempts to leverage supervised machine learning to automate the article triage procedure. This approach has been proved to be helpful for updating existing SRs. However, this technique holds very little promise for creating new SRs because training data is rarely available when it comes to SR creation. In this research we propose an active machine learning approach to overcome this labeling bottleneck and develop a classifier for supporting the creation of systematic reviews. The results indicate that active learning based sample selection could significantly reduce the human effort and is viable technique for automating medical systematic review creation with very few training dataset.