Drs. Ruchir Shah, Adrian Green and Ms. Bekki Elmore were invited to present SWIFT-Review and SWIFT-Active Screener tools to students in Dr. Carolyn Mattingly’s TOX 820: Special Problems in Toxicology: Professional Development course at NC State University. Sciome’s presentations focused on use of SWIFT software applications using machine learning and text mining methods to reduce the level of effort required to complete specific labor-intensive steps of the systematic/literature review process.
SWIFT-Review features a priority ranking algorithm for identifying studies relevant to a given research question, and provides numerous tools to assist during problem formulation to identify, categorize, and visualize research areas that are data rich/poor within a large literature corpus.
SWIFT-Active Screener is designed specifically to reduce the overall screening burden of a review. Validation studies have shown that on average, SWIFT Active Screener saves more than 50% of the screening time required, and results in significant time savings compared to traditional screening, with increased savings for larger project sizes. Moreover, the integration of patented, explicit recall estimation during screening solves an important challenge faced by all machine learning systems for document screening: when to stop screening.
Read more about SWIFT tools in our papers in Systematic Reviews and Environment International.
