Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

FINS: An interactive platform for automated zebrafish image analysis and morphological screening.

SLAS technology·2026
Same author

Comparative investigation of the potential of glyphosate and glyphosate-based formulations to cause oxidative stress and DNA damage in human skin and liver cell systems.

Toxicological sciences : an official journal of the Society of Toxicology·2026
Same author

Commentary on GRADE Guidance 40: GRADE evidence-to-decision framework for environmental and occupational health.

Journal of clinical epidemiology·2026
Same author

Transplatformer: translating toxicogenomic profiles between generations of platforms.

BMC bioinformatics·2026
Same author

OrbiTox: a visualization platform for NAMs and read-across exploration of multi-domain data.

Frontiers in pharmacology·2025
Same author

Addressing cultural and knowledge barriers to enable preclinical sex inclusive research.

eLife·2025

Related Experiment Video

Updated: Dec 25, 2025

Author Spotlight: An Automated Method for Assessing Visual Acuity in Infants and Toddlers Using an Eye-Tracking System
05:10

Author Spotlight: An Automated Method for Assessing Visual Acuity in Infants and Toddlers Using an Eye-Tracking System

Published on: March 17, 2023

3.6K

SWIFT-Active Screener: Accelerated document screening through active learning and integrated recall estimation.

Brian E Howard1, Jason Phillips1, Arpit Tandon1

  • 1Sciome LLC, 2 Davis Drive Durham, NC 27709, USA.

Environment International
|March 24, 2020
PubMed
Summary

SWIFT-Active Screener significantly reduces systematic review screening time by using machine learning to prioritize articles. This tool achieves 95% recall after screening only 40% of references, saving substantial labor for researchers.

Keywords:
Active learningDocument screeningEvidence mappingMachine learningRecall estimationSystematic review

More Related Videos

Using Rapid Serial Visual Presentation to Measure Set-Specific Capture, a Consequence of Distraction While Multitasking
05:58

Using Rapid Serial Visual Presentation to Measure Set-Specific Capture, a Consequence of Distraction While Multitasking

Published on: August 29, 2018

9.2K
Use of a Video Scoring Anchor for Rapid Serial Assessment of Social Communication in Toddlers
09:16

Use of a Video Scoring Anchor for Rapid Serial Assessment of Social Communication in Toddlers

Published on: March 14, 2018

10.6K

Related Experiment Videos

Last Updated: Dec 25, 2025

Author Spotlight: An Automated Method for Assessing Visual Acuity in Infants and Toddlers Using an Eye-Tracking System
05:10

Author Spotlight: An Automated Method for Assessing Visual Acuity in Infants and Toddlers Using an Eye-Tracking System

Published on: March 17, 2023

3.6K
Using Rapid Serial Visual Presentation to Measure Set-Specific Capture, a Consequence of Distraction While Multitasking
05:58

Using Rapid Serial Visual Presentation to Measure Set-Specific Capture, a Consequence of Distraction While Multitasking

Published on: August 29, 2018

9.2K
Use of a Video Scoring Anchor for Rapid Serial Assessment of Social Communication in Toddlers
09:16

Use of a Video Scoring Anchor for Rapid Serial Assessment of Social Communication in Toddlers

Published on: March 14, 2018

10.6K

Area of Science:

  • Bibliometrics
  • Information Science
  • Health Informatics

Background:

  • Systematic reviews require extensive article screening using strict inclusion/exclusion criteria.
  • Screening thousands of articles can demand hundreds of person-hours, representing a significant labor burden.

Purpose of the Study:

  • Introduce SWIFT-Active Screener, a web-based software to decrease the workload in systematic review screening.
  • Employ active learning and a negative binomial model to prioritize articles and estimate remaining relevant documents.

Main Methods:

  • Utilized active learning, incorporating user feedback to prioritize articles for review.
  • Implemented a negative binomial model for estimating the quantity of relevant articles yet to be screened.
  • Evaluated prioritization and recall estimation using simulations on 26 diverse systematic review datasets.

Main Results:

  • Achieved 95% recall of relevant articles after screening an average of 40% of the total references.
  • For large datasets (≥5,000 references), 95% recall was met after screening only 34% of references.
  • The proposed recall estimator provided a conservative and useful estimation of identified relevant documents.

Conclusions:

  • SWIFT-Active Screener offers substantial time savings over traditional screening methods, especially for large-scale reviews.
  • The integrated recall estimation addresses the critical question of when to cease screening in machine learning-assisted reviews.
  • The collaborative, online web application is readily available for multi-user systematic review projects.