News
Speed up your systematic review with ASReview LAB
Doing a systematic review means you need to thoroughly search in multiple databases to find all relevant literature on your topic. This often results in thousands of potentially relevant publications. Reading the titles and abstracts to identify publications that meet your inclusion criteria can be time consuming. ASReview LAB can assist you in screening and selecting publications more rapidly.
Open-source machine learning tool
ASReview LAB is a free open-source machine learning tool that screens and systematically labels a large collection of textual data. The tool is developed and coordinated by the Utrecht University. You can install the software locally on your device and keep full control over your data.
How does it work?
First, you run your literature searches in multiple bibliographic databases. Next, you export them, including at least the title and abstract, to a reference manager, like EndNote or Mendeley. Make sure that you export high quality data. After deduplication in your reference manager, you can start to import the references into ASReview LAB. You can also import publications from bibliographic databases, like Scopus or Web of Science into ASReview LAB and then deduplicate. However, deduplication in a reference manager is preferred.
After creating a project, you can start reviewing. ASReview LAB uses active learning. It learns from the decisions you make based on your inclusion/exclusion criteria. At the start, you have to provide the tool with a training set of at least one relevant and one irrelevant labelled record. After each decision, the tool re-ranks the publications that you haven’t seen yet and moves the publications that are probably more relevant to the top. When you continue screening, you’ll find more and more irrelevant publications. At a certain point, you can decide to stop screening and thus save a lot of time.
Other tools for screening and selecting studies
There are more AI tools available for systematic review. There are free tools like Abstrackr and Rayyan (only free for basic use) and subscription-based tools like Covidence, DistillerSR and EPPI Reviewer. All these tools are compatible with ASReview LAB, meaning data can be exported from these tools and imported into ASReview LAB.
Considerations when choosing an AI tool to help you screen publications
- What are your needs? Can you use a more conventional tool that covers these needs?
- How transparent is the tool you want to use? For example, how does the algorithm work?
- What is the AI policy of the journal in which you want to publish?
- What are the costs?
Information and support
You can download the ASReview software and find more information and tutorials on ASReview: AI-aided Open Source Systematic Review Software. For more assistance or any questions on systematic reviews or literature searches, please contact our Information Specialists. You can send an email to Servicedesk Facilities.