Systematic review software
Software for systematic reviews can help you do your systematic review faster and more efficiently. Literature review software helps researchers organize record screening and data extraction. Users can create multiple reviews for different projects. Systematic review software can also make collaboration in large teams more straightforward. At Pitts, we have built a tool with all this basic functionality, but we also allow users to incorporate AI into their systematic workflow.
Search
Search is always the first step in the systematic review process. Users can search in bibliographic databases outside the tool. According to Bramer, W.M. et al., Embase, MEDLINE (including electronic publications ahead of print), Web of Science (Core Collection), and Google Scholar (the 200 first relevant references) are the minimal required databases to search for every systematic review1. If the subject of the review is closely related to the core theme of a specialized subject database, databases like CINAHL and PsycINFO should be included. Ather searching these databases you can upload a exprot of each database in the from of a .ris file to the Pitts tool.
Search for living systematic reviews.
In our tool you can automatically add new records automatically to the paper screening queue when they become available in PubMed. You can change the search strategy during subsequent living systematic review updates. You will receive an alert when previously included records are excluded from a narrowed search. Unfortunately, not all biographical databases have yet made API available for third parties, so for most databases, we can not yet make this feature avalible.
Screening
We have developed a web application for the title and abstract screening and full-text screening of research articles. The default setting is double-masked screening. We also have a single reviewer mode in the screening settings. We have added the option to resolve conflicts through a third reviewer and provide a dashboard overview of reviewing progress and a flowchart with inclusion and exclusion decisions. One of the core principles built into our tool is transparency in user decision-making applied to screening and data extraction. Users can add notes, and users can set who can view these notes.
Google chrome extension
The days of manually uploading PDFs to your screening applications are behind us. You can use the Pitts Google chrome extension directly to access and upload your records via your university library.
Data extraction
We have developed a data extraction interface. You can create your data extraction form with the population characteristics, outcomes, and other custom data items. Annotate text, highlight sentences and add notes are optional. Users can also do a risk of bias assessment using a variety of in-application risk of bias tools like ROB 2.0.
AI for data extraction
Our tool uses GPT 3.5 for large language model-assisted data extraction from text. Users can add a column with the data item they want to extract and configure GPT with a prompt to assist with data extraction.
Output and settings
The final output users can download is a spreadsheet in .csv or .xlsx format. You can manually configure the data extraction forms according to your needs. You can use the setting to configure the user roles, such as editor and reviewer, and assign tasks like screening and data extraction.
References
1. Bramer, W.M., Rethlefsen, M.L., Kleijnen, J. et al. Optimal database combinations for literature searches in systematic reviews: a prospective exploratory study. Syst Rev 6, 245 (2017). https://doi.org/10.1186/s13643-017-0644-y