Overview of the tool
ExaCTDemo is an information extraction system developed jointly by the National Research Council of Canada’s Digital Technologies Research Centre and the University of California, San Francisco. The system was originally conceived and trained to find key information from scientific clinical trial publications, namely the descriptions of the trial's interventions, population, outcome measures, funding sources, and other critical characteristics. The current, expanded version also extracts information from clinical trial registries, most notably from the National Institutes of Health’s database of privately and publicly funded clinical studies conducted around the world, called ClinicalTrials.gov.
Benefits to users
ExaCTDemo allows users to test how data is extracted from clinical trial documents of interest to them. ExaCTDemo indexes a user’s scientific document collection in a structured way. Automatically extracted answers are presented to users through a web browser-based interface that assists users in verifying and changing the extracted information. Users can then leverage the indexed information to determine the next steps for detailed searches and meta-analysis. For more information, please see the University of California at San Francisco’s Human Studyome Project as well as the Vivli centre for global clinical research data.
Targeted audience
- Clinical trial researchers and organizations
- Experts in artificial intelligence for health
System requirements
- To use the system, you must have access to a web browser and create an account consisting of a user name and a password.
- This is a trial version of the software. It has been moderately tested on Internet Explorer, Firefox, and Safari browsers. Some errors and unexpected behaviours can still occur.
Contact us
Svetlana Kiritchenko
Research officer, Text analytics
Telephone: 613-993-0630
Email: Svetlana.Kiritchenko@nrc-cnrc.gc.ca
Berry de Bruijn
Team leader, Text analytics
Telephone: 613-993-0604
Email: Berry.deBruijn@nrc-cnrc.gc.ca