There are several tools in Nested Knowledge that utilize artificial intelligence and machine learning to make systematic reviews easier and more effective to conduct. This page provides technical details on what these features are, and how your data is used.

• Used to highlight Populations, Interventions/Comparators, and Outcomes in abstracts during Screening
  • Optional: by default this feature is toggled on, but can be toggled off and will remain off for all abstracts in the queue/ongoing modules and Study Inspector until toggled back on.
• Used to generate most commonly reported terms among the literature, to inform the build of search queries in Search Exploration
  • Optional: Search Exploration is not a required step in AutoLit and simply offers assistance to build a search. However, when it is used, RoboPICO auto-generates terms when concepts are entered and “Refresh Exploration” is selected. This cannot be switched off when Search Exploration is used.

RoboPICO uses a fork of the machine learning system offered by RobotReviewer. Specifically, Named-entity Recognition models extract Patient/Problem, Intervention, and Outcome entities from data in article abstracts. NK's modifications to RobotReviewer are open and General Public Licensed.

Bibliomine is our citation-mining feature. It scans a report and auto-extract citations from a previous systematic review or landmark study and imports all cited references as records directly into your nest. This feature, and the tools behind it, does not have access to your data unless you use it.

Optional: This feature is helpful if, for example, you are performing an update on an existing review, but not required to successfully upload records to a nest.

Bibliomine uses Grobid, a machine learning library for citation mining documents.

Robot Screener uses a screening model (that requires training) to make reviewer-level screening decisions based on inclusion probabilities. In effect, it replaces one human reviewer when turned on in nests with a Dual Screening mode. This feature, and the tools behind it, does not have access to your data unless you turn it on in Settings.

Optional: This feature is helpful to speed up the Screening process, but is not required to successfully Dual Screen all records in a nest so it can remain toggled off.

The model uses the following data from your records as inputs:

• Bibliographic data
  • Time since publication of the record
  • Page count
  • Keywords/Descriptors
• Abstract Content
  • N-grams
  • OpenAI text embedding (ada-002)
• Citation Counts from Scite, accessed using the DOI
  • Number of citing publications
  • Number of supporting citation statements
  • Number of contrasting citation statements

Learn more about the screening model that powers Robot Screener.

Smart Tag Recommendations utilizes GPT 4, a language model provided by OpenAI, to search for tags and automatically highlight corresponding excerpts.

Optional: This feature is helpful to speed up the data extraction process, but is not required to perform data extraction of all records in the nest, so Standard Tag Recommendations should remain selected to keep this feature off.

Smart Tag Recommendations uses OpenAI's GPT-4 to generate recommendations for customized tag hierarchies and available full texts in the nest.